CN113011327A - Three-dimensional graph recognition method, device, equipment and storage medium - Google Patents
Three-dimensional graph recognition method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113011327A CN113011327A CN202110292252.6A CN202110292252A CN113011327A CN 113011327 A CN113011327 A CN 113011327A CN 202110292252 A CN202110292252 A CN 202110292252A CN 113011327 A CN113011327 A CN 113011327A
- Authority
- CN
- China
- Prior art keywords
- target
- dimensional object
- graph
- dimensional
- graphic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000009877 rendering Methods 0.000 claims abstract description 42
- 238000003909 pattern recognition Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000013519 translation Methods 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 125000004122 cyclic group Chemical group 0.000 abstract 1
- 238000012567 pattern recognition method Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/10—Geometric effects
- G06T15/20—Perspective computation
- G06T15/205—Image-based rendering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Geometry (AREA)
- Computer Graphics (AREA)
- Processing Or Creating Images (AREA)
Abstract
本发明公开了一种三维图形识别方法、装置、设备及存储介质，根据目标源图形中每个图形特征点的位置坐标，确定图形特征点之间的特征点距；循环查找在预设范围内，特征点距相同的相似图元对象，并根据所述相似图元对象的图元数据类型进行分组；通过抽取每组中的相似图元对象，组成新的图形，获取图形数据；通过浏览器的图像渲染元素对预先获取的图形数据进行渲染，生成目标三维对象，所述图形数据显示于所述目标三维对象的表面；在浏览器的浏览页面中显示所述目标三维对象。上述方案有效解决了三维图形几何形状的识别问题，避免了使用多个相机采集图像导致的不同步问题，提高识别准确率。
The invention discloses a three-dimensional graphic recognition method, device, equipment and storage medium. According to the position coordinates of each graphic feature point in the target source graphic, the feature point distance between graphic feature points is determined; the cyclic search is within a preset range. , similar primitive objects with the same feature point distance, and grouped according to the primitive data types of the similar primitive objects; by extracting similar primitive objects in each group, a new graph is formed, and graph data is obtained; through the browser The image rendering element renders the pre-acquired graphic data to generate a target three-dimensional object, and the graphic data is displayed on the surface of the target three-dimensional object; the target three-dimensional object is displayed on the browsing page of the browser. The above solution effectively solves the recognition problem of the geometric shape of the three-dimensional graphics, avoids the asynchronous problem caused by using multiple cameras to collect images, and improves the recognition accuracy.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a three-dimensional image recognition method, a three-dimensional image recognition device, three-dimensional image recognition equipment and a storage medium.
Background
The dimension object recognition is a research hotspot in the field of computer vision in recent years, and has important application prospects in the aspects of automatic driving, medical image processing and the like. However, the existing three-dimensional pattern recognition technology still has the problems that the existing three-dimensional pattern recognition technology is more complex, and the three-dimensional pattern recognition based on deep learning needs more training data and is not flexible enough, so that a more effective scheme needs to be provided.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a three-dimensional pattern recognition method, a device, equipment and a storage medium, which effectively solve the problems that deep learning three-dimensional pattern recognition needs more training data and is not flexible enough, and improve the recognition accuracy.
The invention solves the technical problems by the following technical means:
a method of three-dimensional pattern recognition, the method comprising:
determining the characteristic point distance between the graphic characteristic points according to the position coordinates of each graphic characteristic point in the target source graphic;
similar primitive objects with the same characteristic point distance in a preset range are searched in a circulating mode, and grouping is conducted according to the primitive data types of the similar primitive objects;
forming a new graph by extracting similar primitive objects in each group to obtain graph data;
rendering pre-acquired graphic data through an image rendering element of a browser to generate a target three-dimensional object, wherein the graphic data are displayed on the surface of the target three-dimensional object;
and displaying the target three-dimensional object in a browsing page of the browser.
Preferably, before determining the feature point distance between the feature points according to the position coordinates of each feature point in the target source graph, the method further includes: acquiring a preselected target source graph;
collecting a plurality of graph feature points in a target source graph;
the method also comprises the following steps of before acquiring the source graph: a predefined configuration file is read.
Preferably, the determining the feature point distances between the feature points of the graph according to the position coordinates of each feature point of the graph in the target source graph comprises:
inputting a preselected target source graph into a neural network for feature extraction to obtain image features of the target source graph in at least one network level;
calculating the Euclidean distance between the real value corresponding to the image feature and the network predicted value;
calculating the Euclidean distance between a real value corresponding to the image feature and a network predicted value according to the following formula:
wherein x is a 3D point, R and t are a rotation matrix and a translation vector corresponding to the true value,
and
the prediction values are rotation matrix and translation vector.
Preferably, the forming a new graph by extracting similar primitive objects in each group includes:
acquiring the quantity of graphic elements in a target source graph;
and when the number of the primitives is equal to that of the primitives of the similar primitive object, stopping the extraction action and obtaining a new graph.
Preferably, the image rendering element includes: a two-dimensional image rendering element and a three-dimensional image rendering element; the rendering the text data through the image rendering element of the browser to generate a target three-dimensional object includes: drawing the text data on a canvas through a character drawing interface of the two-dimensional image rendering element to obtain a target canvas; converting the target canvas through a picture conversion interface of the two-dimensional image rendering element to generate a target picture; and rendering the target picture to an original three-dimensional object through a three-dimensional drawing interface called by the three-dimensional image rendering element to obtain the target three-dimensional object.
Preferably, the displaying the target three-dimensional object in a browsing page of the browser includes: acquiring speed data of the target three-dimensional object; dynamically displaying the target three-dimensional object in the browsing page according to the speed data; wherein the speed data is used for controlling the movement speed of the target three-dimensional object on the browsing page; the speed data includes: the speed of a vertical axis used for controlling the target three-dimensional object to move upwards or downwards in the browsed page and the speed of a horizontal axis used for controlling the target three-dimensional object to move leftwards or rightwards in the browsed page.
Preferably, the displaying the target three-dimensional object in a browsing page of the browser includes: responding to the moving operation of the target three-dimensional object, and dynamically displaying the target three-dimensional object in the browsing page according to the moving track indicated by the moving operation; and matching the movement track of the target three-dimensional object in the browsing page with the movement track indicated by the movement operation.
A three-dimensional pattern recognition apparatus, the apparatus comprising:
the determining module is used for determining the characteristic point distance between the graphic characteristic points according to the position coordinates of each graphic characteristic point in the target source graph;
the searching module is used for circularly searching similar primitive objects with the same characteristic point distance in a preset range and grouping the similar primitive objects according to the primitive data types of the similar primitive objects;
the acquisition module is used for forming a new graph by extracting the similar primitive objects in each group and acquiring graph data;
the generating module is used for rendering pre-acquired graphic data through an image rendering element of a browser to generate a target three-dimensional object, and the graphic data are displayed on the surface of the target three-dimensional object;
and the display module is used for displaying the target three-dimensional object in a browsing page of the browser.
An apparatus for recognizing a three-dimensional figure, comprising: at least one processor, at least one memory, and computer program instructions stored in the memory that, when executed by the processor, implement the method as a three-dimensional pattern recognition.
A computer-readable storage medium having computer program instructions stored thereon which, when executed by a processor, implement a method such as three-dimensional pattern recognition.
The invention has the beneficial effects that:
the invention provides a three-dimensional graph recognition method, a device, equipment and a storage medium, which overcome the problems of low voxel data resolution and texture loss, and obtain better recognition accuracy than the prior method by using less parameters. Firstly, determining the characteristic point distance between the characteristic points of the graphs according to the position coordinates of each characteristic point of the graphs in the target source graph; similar primitive objects with the same characteristic point distance in a preset range are searched in a circulating mode, and grouping is conducted according to the primitive data types of the similar primitive objects; secondly, forming a new graph by extracting similar primitive objects in each group to obtain graph data; and finally, rendering the pre-acquired graphic data through an image rendering element of the browser to generate a target three-dimensional object, and displaying the target three-dimensional object in a browsing page of the browser. The problem of the recognition of the geometric shape of the three-dimensional graph is effectively solved, and the problem of asynchronism caused by the fact that a plurality of cameras are used for collecting images is avoided. The method can replace the traditional multi-camera acquisition of graphic images, thereby eliminating the measurement error caused by asynchronous image acquisition.
Drawings
In order to more clearly illustrate the detailed description of the invention or the technical solutions in the prior art, the drawings that are needed in the detailed description of the invention or the prior art will be briefly described below. Throughout the drawings, like elements or portions are generally identified by like reference numerals. In the drawings, elements or portions are not necessarily drawn to scale.
Fig. 1 is a flowchart of a three-dimensional pattern recognition method provided by the present invention.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and therefore are only examples, and the protection scope of the present invention is not limited thereby.
It is to be noted that, unless otherwise specified, technical or scientific terms used herein shall have the ordinary meaning as understood by those skilled in the art to which the invention pertains.
As shown in fig. 1, the present invention provides a general solution to a three-dimensional pattern recognition method for overcoming the drawbacks of the prior art, which mainly comprises the following steps:
step S1, determining the characteristic point distance between the graphic characteristic points according to the position coordinates of each graphic characteristic point in the target source graphic;
step S2, circularly searching similar primitive objects with the same characteristic point distance in a preset range, and grouping according to the primitive data types of the similar primitive objects;
step S3, forming a new graph by extracting similar primitive objects in each group, and acquiring graph data;
step S4, rendering pre-acquired graphic data through an image rendering element of a browser to generate a target three-dimensional object, wherein the graphic data are displayed on the surface of the target three-dimensional object;
and step S5, displaying the target three-dimensional object in a browsing page of the browser.
In step S1, before determining the feature point distance between the feature points of the graph according to the position coordinates of each feature point of the graph in the target source graph, the method further includes: acquiring a preselected target source graph;
collecting a plurality of graph feature points in a target source graph;
the method also comprises the following steps of before acquiring the source graph: a predefined configuration file is read.
Determining the feature point distance between the feature points of the graph according to the position coordinates of each feature point of the graph in the target source graph comprises the following steps:
inputting a preselected target source graph into a neural network for feature extraction to obtain image features of the target source graph in at least one network level;
calculating the Euclidean distance between the real value corresponding to the image feature and the network predicted value;
calculating the Euclidean distance between a real value corresponding to the image feature and a network predicted value according to the following formula:
wherein x is a 3D point, R and t are a rotation matrix and a translation vector corresponding to the true value,
and
the prediction values are rotation matrix and translation vector.
In step S3, forming a new graph by extracting similar primitive objects in each group includes:
acquiring the quantity of graphic elements in a target source graph;
and when the number of the primitives is equal to that of the primitives of the similar primitive object, stopping the extraction action and obtaining a new graph.
In step S4, the image rendering element includes: a two-dimensional image rendering element and a three-dimensional image rendering element; the rendering the text data through the image rendering element of the browser to generate a target three-dimensional object includes: drawing the text data on a canvas through a character drawing interface of the two-dimensional image rendering element to obtain a target canvas; converting the target canvas through a picture conversion interface of the two-dimensional image rendering element to generate a target picture; and rendering the target picture to an original three-dimensional object through a three-dimensional drawing interface called by the three-dimensional image rendering element to obtain the target three-dimensional object.
In step S5, the displaying the target three-dimensional object in the browsing page of the browser includes: acquiring speed data of the target three-dimensional object; dynamically displaying the target three-dimensional object in the browsing page according to the speed data; wherein the speed data is used for controlling the movement speed of the target three-dimensional object on the browsing page; the speed data includes: the speed of a vertical axis used for controlling the target three-dimensional object to move upwards or downwards in the browsed page and the speed of a horizontal axis used for controlling the target three-dimensional object to move leftwards or rightwards in the browsed page.
Displaying the target three-dimensional object in a browsing page of the browser, including: responding to the moving operation of the target three-dimensional object, and dynamically displaying the target three-dimensional object in the browsing page according to the moving track indicated by the moving operation; and matching the movement track of the target three-dimensional object in the browsing page with the movement track indicated by the movement operation.
Example 2:
based on the same technical concept, the specific embodiment of the present invention further provides a three-dimensional image recognition apparatus, including:
the determining module is used for determining the characteristic point distance between the graphic characteristic points according to the position coordinates of each graphic characteristic point in the target source graph;
the searching module is used for circularly searching similar primitive objects with the same characteristic point distance in a preset range and grouping the similar primitive objects according to the primitive data types of the similar primitive objects;
the acquisition module is used for forming a new graph by extracting the similar primitive objects in each group and acquiring graph data;
the generating module is used for rendering pre-acquired graphic data through an image rendering element of a browser to generate a target three-dimensional object, and the graphic data are displayed on the surface of the target three-dimensional object;
and the display module is used for displaying the target three-dimensional object in a browsing page of the browser.
Further, according to the technical idea of the above embodiment, the embodiments of the present invention also provide a three-dimensional figure recognition apparatus and a computer-readable storage medium. Wherein, a three-dimensional figure's recognition equipment includes: at least one processor, at least one memory, and computer program instructions stored in the memory that, when executed by the processor, implement the method of embodiment 1.
A computer-readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the method of embodiment 1.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present invention, and they should be construed as being included in the following claims and description.
Claims (10)
1. A method for three-dimensional pattern recognition, the method comprising:
determining the characteristic point distance between the graphic characteristic points according to the position coordinates of each graphic characteristic point in the target source graphic;
similar primitive objects with the same characteristic point distance in a preset range are searched in a circulating mode, and grouping is conducted according to the primitive data types of the similar primitive objects;
forming a new graph by extracting similar primitive objects in each group to obtain graph data;
rendering pre-acquired graphic data through an image rendering element of a browser to generate a target three-dimensional object, wherein the graphic data are displayed on the surface of the target three-dimensional object;
and displaying the target three-dimensional object in a browsing page of the browser.
2. The method of claim 1, wherein determining the feature point distance between the graph feature points based on the position coordinates of each graph feature point in the target source graph further comprises: acquiring a preselected target source graph;
collecting a plurality of graph feature points in a target source graph;
the method also comprises the following steps of before acquiring the source graph: a predefined configuration file is read.
3. The method of claim 1, wherein determining the feature point distances between the graph feature points based on the position coordinates of each graph feature point in the target source graph comprises:
inputting a preselected target source graph into a neural network for feature extraction to obtain image features of the target source graph in at least one network level;
calculating the Euclidean distance between the real value corresponding to the image feature and the network predicted value;
calculating the Euclidean distance between a real value corresponding to the image feature and a network predicted value according to the following formula:
wherein x is a 3D point, R and t are a rotation matrix and a translation vector corresponding to the true value,
and
the prediction values are rotation matrix and translation vector.
4. The method of claim 1, wherein composing a new graph by extracting similar primitive objects in each group comprises:
acquiring the quantity of graphic elements in a target source graph;
and when the number of the primitives is equal to that of the primitives of the similar primitive object, stopping the extraction action and obtaining a new graph.
5. The method of claim 1, wherein the image rendering element comprises: a two-dimensional image rendering element and a three-dimensional image rendering element; the rendering the text data through the image rendering element of the browser to generate a target three-dimensional object includes: drawing the text data on a canvas through a character drawing interface of the two-dimensional image rendering element to obtain a target canvas; converting the target canvas through a picture conversion interface of the two-dimensional image rendering element to generate a target picture; and rendering the target picture to an original three-dimensional object through a three-dimensional drawing interface called by the three-dimensional image rendering element to obtain the target three-dimensional object.
6. The method of claim 1, wherein said displaying the target three-dimensional object in a browse page of the browser comprises: acquiring speed data of the target three-dimensional object; dynamically displaying the target three-dimensional object in the browsing page according to the speed data; wherein the speed data is used for controlling the movement speed of the target three-dimensional object on the browsing page; the speed data includes: the speed of a vertical axis used for controlling the target three-dimensional object to move upwards or downwards in the browsed page and the speed of a horizontal axis used for controlling the target three-dimensional object to move leftwards or rightwards in the browsed page.
7. The method of claim 1, wherein said displaying the target three-dimensional object in a browse page of the browser comprises: responding to the moving operation of the target three-dimensional object, and dynamically displaying the target three-dimensional object in the browsing page according to the moving track indicated by the moving operation; and matching the movement track of the target three-dimensional object in the browsing page with the movement track indicated by the movement operation.
8. A three-dimensional pattern recognition apparatus, the apparatus comprising:
the determining module is used for determining the characteristic point distance between the graphic characteristic points according to the position coordinates of each graphic characteristic point in the target source graph;
the searching module is used for circularly searching similar primitive objects with the same characteristic point distance in a preset range and grouping the similar primitive objects according to the primitive data types of the similar primitive objects;
the acquisition module is used for forming a new graph by extracting the similar primitive objects in each group and acquiring graph data;
the generating module is used for rendering pre-acquired graphic data through an image rendering element of a browser to generate a target three-dimensional object, and the graphic data are displayed on the surface of the target three-dimensional object;
and the display module is used for displaying the target three-dimensional object in a browsing page of the browser.
9. An apparatus for recognizing a three-dimensional figure, comprising: at least one processor, at least one memory, and computer program instructions stored in the memory that, when executed by the processor, implement the method of claims 1-7.
10. A computer-readable storage medium having computer program instructions stored thereon, which when executed by a processor implement the method of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110292252.6A CN113011327A (en) | 2021-03-18 | 2021-03-18 | Three-dimensional graph recognition method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110292252.6A CN113011327A (en) | 2021-03-18 | 2021-03-18 | Three-dimensional graph recognition method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113011327A true CN113011327A (en) | 2021-06-22 |
Family
ID=76402541
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110292252.6A Pending CN113011327A (en) | 2021-03-18 | 2021-03-18 | Three-dimensional graph recognition method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113011327A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024021590A1 (en) * | 2022-07-28 | 2024-02-01 | 东方晶源微电子科技（北京）有限公司 | Position deviation-allowed graphic grouping method, apparatus and device, and storage medium |
| CN117911615A (en) * | 2023-12-29 | 2024-04-19 | 圣名科技(广州)有限责任公司 | A method and device for generating a virtual organism |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101383910A (en) * | 2007-09-05 | 2009-03-11 | 索尼株式会社 | Apparatus and method for rendering a 3d scene |
| CN101673410A (en) * | 2008-09-12 | 2010-03-17 | 中国科学院计算技术研究所 | Vector building drawing based method for reconstructing three-dimensional model |
| CN103635937A (en) * | 2011-05-30 | 2014-03-12 | 原子能和辅助替代能源委员会 | Method for positioning a camera and 3D reconstruction in a partially known environment |
| US20160070952A1 (en) * | 2014-09-05 | 2016-03-10 | Samsung Electronics Co., Ltd. | Method and apparatus for facial recognition |
| CN105913372A (en) * | 2016-04-05 | 2016-08-31 | 厦门汇利伟业科技有限公司 | Two-dimensional room plane graph to three-dimensional graph conversion method and system thereof |
| CN110347462A (en) * | 2019-06-21 | 2019-10-18 | 秦皇岛尼特智能科技有限公司 | WMF fire-fighting graph processing method and device based on OPENGL |
| WO2020075252A1 (en) * | 2018-10-11 | 2020-04-16 | 三菱電機株式会社 | Information processing device, program, and information processing method |
| CN111210506A (en) * | 2019-12-30 | 2020-05-29 | 塔普翊海（上海）智能科技有限公司 | Three-dimensional reduction method, system, terminal equipment and storage medium |
| CN112204623A (en) * | 2018-06-01 | 2021-01-08 | 电子湾有限公司 | Rendering three-dimensional digital model generation |
| CN112446312A (en) * | 2020-11-19 | 2021-03-05 | 深圳市中视典数字科技有限公司 | Three-dimensional model identification method and device, electronic equipment and storage medium |
-
2021
- 2021-03-18 CN CN202110292252.6A patent/CN113011327A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101383910A (en) * | 2007-09-05 | 2009-03-11 | 索尼株式会社 | Apparatus and method for rendering a 3d scene |
| CN101673410A (en) * | 2008-09-12 | 2010-03-17 | 中国科学院计算技术研究所 | Vector building drawing based method for reconstructing three-dimensional model |
| CN103635937A (en) * | 2011-05-30 | 2014-03-12 | 原子能和辅助替代能源委员会 | Method for positioning a camera and 3D reconstruction in a partially known environment |
| US20160070952A1 (en) * | 2014-09-05 | 2016-03-10 | Samsung Electronics Co., Ltd. | Method and apparatus for facial recognition |
| CN105913372A (en) * | 2016-04-05 | 2016-08-31 | 厦门汇利伟业科技有限公司 | Two-dimensional room plane graph to three-dimensional graph conversion method and system thereof |
| CN112204623A (en) * | 2018-06-01 | 2021-01-08 | 电子湾有限公司 | Rendering three-dimensional digital model generation |
| WO2020075252A1 (en) * | 2018-10-11 | 2020-04-16 | 三菱電機株式会社 | Information processing device, program, and information processing method |
| CN110347462A (en) * | 2019-06-21 | 2019-10-18 | 秦皇岛尼特智能科技有限公司 | WMF fire-fighting graph processing method and device based on OPENGL |
| CN111210506A (en) * | 2019-12-30 | 2020-05-29 | 塔普翊海（上海）智能科技有限公司 | Three-dimensional reduction method, system, terminal equipment and storage medium |
| CN112446312A (en) * | 2020-11-19 | 2021-03-05 | 深圳市中视典数字科技有限公司 | Three-dimensional model identification method and device, electronic equipment and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024021590A1 (en) * | 2022-07-28 | 2024-02-01 | 东方晶源微电子科技（北京）有限公司 | Position deviation-allowed graphic grouping method, apparatus and device, and storage medium |
| CN117911615A (en) * | 2023-12-29 | 2024-04-19 | 圣名科技(广州)有限责任公司 | A method and device for generating a virtual organism |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104331699B (en) | A kind of method that three-dimensional point cloud planarization fast search compares | |
| CN108122256B (en) | A method of it approaches under state and rotates object pose measurement | |
| CN111401266B (en) | Method, equipment, computer equipment and readable storage medium for positioning picture corner points | |
| CN109101981B (en) | A loop closure detection method based on global image stripe code in street scene scene | |
| CN112149590A (en) | A method of hand key point detection | |
| CN110688947A (en) | Method for synchronously realizing human face three-dimensional point cloud feature point positioning and human face segmentation | |
| CN108010082B (en) | Geometric matching method | |
| CN114463503B (en) | Method and device for integrating three-dimensional model and geographic information system | |
| CN113011327A (en) | Three-dimensional graph recognition method, device, equipment and storage medium | |
| CN110516528A (en) | A moving target detection and tracking method based on moving background | |
| CN114331995A (en) | A real-time localization method based on multi-template matching based on improved 2D-ICP | |
| Liu et al. | ASFlow: Unsupervised optical flow learning with adaptive pyramid sampling | |
| CN114241469A (en) | Information identification method and device for electricity meter rotation process | |
| CN109977834A (en) | The method and apparatus divided manpower from depth image and interact object | |
| CN108655571A (en) | A kind of digital-control laser engraving machine, control system and control method, computer | |
| CN115008454A (en) | An online hand-eye calibration method for robots based on multi-frame pseudo-label data enhancement | |
| CN115222912A (en) | Target pose estimation method and device, computing equipment and storage medium | |
| CN116386089B (en) | Human body posture estimation method, device, equipment and storage medium under motion scene | |
| CN111179271B (en) | Object angle information labeling method based on retrieval matching and electronic equipment | |
| CN106056575B (en) | A kind of image matching method based on like physical property proposed algorithm | |
| CN118154524A (en) | Image defect detection method, device, medium and electronic equipment | |
| CN118097467A (en) | Aviation image directed target detection method based on semi-supervised learning | |
| CN116485759A (en) | Method, system and electronic equipment for target boundary recognition in ultrasonic images | |
| CN114612494A (en) | Design method of mobile robot vision odometer in dynamic scene | |
| CN114820899A (en) | Attitude estimation method and device based on multi-view rendering |
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 |