CN112084938B - Method and device for improving stability of plane target representation based on graph structure - Google Patents
Method and device for improving stability of plane target representation based on graph structure Download PDFInfo
- Publication number
- CN112084938B CN112084938B CN202010935717.0A CN202010935717A CN112084938B CN 112084938 B CN112084938 B CN 112084938B CN 202010935717 A CN202010935717 A CN 202010935717A CN 112084938 B CN112084938 B CN 112084938B
- Authority
- CN
- China
- Prior art keywords
- points
- triangle
- grid
- graph
- point
- 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
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- 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
- G06T17/20—Finite element generation, e.g. wire-frame surface description, tesselation
-
- 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
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- 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)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method and a device for improving the stability of planar target characterization based on a graph structure, wherein the method comprises the following steps: calculating the significance score of each pixel point by adopting a rapid binary test strategy in a FAST key point detection algorithm; generating an adaptive grid by utilizing a dividing mode of the adaptive adjustment grid; constructing a vertex set V by adopting a Spatial Softmax algorithm; the edge set E is constructed using the Delaunay triangulation method. According to the method, the target is characterized as a group of discrete point sets which have a topological structure and can be repeatedly detected, namely, a vertex set V and a side set E, the global and local structures of the target can be considered, and the robustness and the stability of the characterization method are improved.
Description
Technical Field
The invention relates to a planar target characterization method oriented to an augmented reality technology, in particular to a method and a device for improving planar target characterization stability based on a graph structure.
Background
Planar target tracking algorithms are one of the core software components in augmented reality technology. In the planar target tracking algorithm, one of the most fundamental and critical links is how to characterize a planar target. The robustness and stability of the planar target characterization method directly influence the accuracy of the tracking algorithm, and finally influence the fidelity of the augmented reality technology and the user experience.
Earlier planar target characterization methods have been to model the global structure of the target directly using gray scale maps. The advantage of this characterization method is that it is simple and easy to implement, but the biggest problem is that it cannot cope with well-varying illumination and local occlusion problems. Currently, the mainstream planar target characterization method is to characterize the target as an unordered set of key points. The characterization method overcomes the influence of illumination change and local shielding to a great extent, and has certain robustness. However, this characterization method models only a local part of the object, losing global structural information of the object. In addition, in the case of blurring or uneven texture distribution of the object, key points are often difficult to detect repeatedly, resulting in poor stability of such characterization methods.
Disclosure of Invention
The invention provides a method and a device for improving the stability of planar target representation based on a graph structure, aiming at the problems, wherein the method is based on a planar target representation method of undirected graph G= (V, E), and the targets are represented as a group of vertex set V and edge set E which have topological structures and can be repeatedly detected.
The technical scheme of the invention is as follows: the method for improving the stability of the planar target representation based on the graph structure comprises the following steps:
(1) Acquiring a pixel point saliency score graph: calculating the significance score of each pixel point of the input image by adopting a rapid binary test strategy in a FAST key point detection algorithm;
(2) Generating an adaptive mesh: according to the preset vertex number, the dividing mode of the grid is adaptively adjusted, and according to the gesture information of the target in the previous frame in the input diagram, the position of the grid point is further adaptively adjusted;
(3) Constructing a vertex set: calculating the relative saliency scores of all pixel points in each grid by adopting a SpatialSoftmax algorithm, and constructing a vertex set by using the pixel points with the highest relative saliency scores, so that the mode can ensure that a fixed number of vertices are repeatedly detected;
(4) Constructing an edge set: and (3) connecting the vertex sets obtained in the step (3) by adopting a Delaunay triangulation method, wherein the set of all triangular surfaces in the connection mode is a convex hull of the vertex set, so that the stability and the uniqueness of the undirected graph are ensured.
The invention further adopts the technical scheme that: the specific method of the step (1) is to calculate the saliency score of each pixel point in the input graph according to the difference degree of the gray value of the pixel of the central point in the input graph and the gray value of the pixels of the peripheral point taking the central point as the center and r as the radius, so as to obtain the saliency score graph of the input graph.
The invention further adopts the technical scheme that: the standard of the self-adaptive mesh division mode in the step (2) is that the number of divided meshes and the number in a preset vertex set are mutually corresponding, and the length-width ratio of each mesh is 1.
The invention further adopts the technical scheme that: the specific method for performing further self-adaptive adjustment on the positions of the grid points in the step (2) is to perform projection transformation on the grid points by using the attitude information to obtain new grid points.
The technical scheme of the invention is as follows: an apparatus for implementing a method for improving stability of planar target characterization based on graph structure is provided, the apparatus comprising: the pixel point saliency score map obtaining module is used for calculating the saliency score of each pixel point of the input map by adopting a rapid binary test strategy in a FAST key point detection algorithm; the self-adaptive grid generation module is used for self-adaptively adjusting the dividing mode of the grid according to the preset vertex number and further self-adaptively adjusting the position of the grid point according to the gesture information of the target in the previous frame in the input diagram; the vertex set constructing module is used for calculating the relative saliency scores of all the pixel points in each grid by adopting a Spatial Softmax algorithm, and constructing a vertex set by utilizing the pixel point with the highest relative saliency score; and constructing an edge set module for connecting the obtained vertex sets by adopting a Delaunay triangulation method.
The invention further adopts the technical scheme that: the specific method for obtaining the pixel point saliency score map is to calculate the saliency score of each pixel point in the input map according to the difference degree of the gray value of the pixel at the central point in the input map and the gray value of the pixels at the peripheral point taking the central point as the center of a circle and taking r as the radius, so as to obtain the saliency score map of the input map.
The invention further adopts the technical scheme that: the standard of the self-adaptive mesh adjustment dividing mode is that the number of divided meshes corresponds to the number in a preset vertex set, and the length-width ratio of each mesh is 1.
The invention further adopts the technical scheme that: the specific method for performing further self-adaptive adjustment on the positions of the grid points is to perform projection transformation on the grid points by using the attitude information H to obtain new grid points.
The method and the device for improving the stability of the plane target representation based on the graph structure have the beneficial effects that: the plane target characterization method characterizes the target as a group of discrete point sets which have topological structures and can be repeatedly detected, can give consideration to the global and local structures of the target, improves the robustness and stability of the characterization method, and has more obvious advantages especially under the conditions of image blurring and uneven distribution of the texture structure of the target.
Drawings
FIG. 1 is a schematic flow chart of an embodiment of a planar target characterization method of the present invention;
fig. 2 is a schematic diagram of a module structure of the present invention.
Detailed Description
In order to further describe the technical scheme of the invention in detail, the embodiment is implemented on the premise of the technical scheme of the invention, and detailed implementation modes and specific steps are given.
Fig. 1 is a schematic flow chart of an embodiment of a planar target characterization method according to the present invention, and specifically includes the following implementation steps:
(1) Acquiring a pixel point saliency score graph: and calculating the saliency score of each pixel point of the input image by adopting a rapid binary test strategy in a FAST key point detection algorithm.
The specific implementation process is as follows: according to the difference degree of the gray value of the pixel of the center point and the gray value of the pixels of the surrounding points taking the center point as the center and r as the radius, calculating the saliency score of each pixel point in the input graph, wherein the saliency score formula is as follows:
wherein s is m Representing pixel saliency scores, s c Representing the gray value of the pixel of the center point, s i The gray value of the pixel representing a point on the circumference, n represents the number of selected points on the circumference, in the embodiment n is 16. And obtaining a saliency score graph of the input graph, then inhibiting a non-maximum value, scanning the saliency score graph by using a local window with the size of W multiplied by H, reserving the maximum value of the saliency score in the local window, and setting the score of the non-maximum value position to zero, so that the positioning reliability can be improved.
(2) Generating an adaptive mesh: according to the preset vertex number, the dividing mode of the grid is adaptively adjusted, and according to the gesture information of the target in the previous frame in the input diagram, the position of the grid point is further adaptively adjusted.
The specific implementation process is as follows: according to the preset number N of the vertexes, the self-adaptive grid division is carried out on the target area of the input image, namely, the generation of the number of grids is guided according to the preset number N of the vertexes, and in order to improve the generation quality of the vertexes, the self-adaptive grid division standard is that the number of the divided grids corresponds to the number in the preset vertex set, and the length-width ratio of each grid is 1.
Preferred embodiments of the invention are: the self-adaptive grid point adjustment is carried out on grid points including grid lines according to the gesture information H of the target in the previous frame, and the specific implementation process is as follows: the posture information H, namely the homography projection matrix is used for carrying out projection transformation on grid points to obtain new grid points, and the purpose of doing so is to eliminate the problem of inconsistent grid division of the front frame and the rear frame caused by the change of the target posture as far as possible.
(3) Constructing a vertex set: the salialSoftmax algorithm is adopted to calculate the saliency scores of all the pixels in each grid, and the pixel points with the highest saliency scores are utilized to construct a vertex set, so that the repeated detection of a fixed number of vertices can be ensured.
The specific implementation process is as follows: the equation for the SpatialSoftmax algorithm is as follows:
wherein s is i Representing the relative saliency score of each pixel point in the grid, n represents the number of the pixel points in the grid, m i The saliency score of the pixel point is represented, and the saliency score of the pixel point is higher if only one pixel point with higher saliency score exists in the grid, which is obtained in the step (1); if there are multiple pixels within the grid with higher saliency scores, the location of the pixel with the highest relative saliency score will be a weighted average of the locations of the multiple pixels.
Constructing a vertex set V of the undirected graph G= (V, E), and selecting the pixel points with the highest relative significance scores in each grid to form the vertex set of the undirected graph.
(4) Constructing an edge set: and (3) connecting the vertex sets obtained in the step (3) by adopting a Delaunay triangulation method, wherein the set of all triangular surfaces in the connection mode is a convex hull of the vertex set, so that the stability and the uniqueness of the undirected graph are ensured.
The specific implementation process is as follows: constructing an edge set E of an undirected graph G= (V, E), connecting a vertex set V of the undirected graph by adopting a Delaunay triangulation method, and firstly constructing a super triangle containing all points of the point set V by adopting a Bowyer-Watson algorithm by adopting the Delaunay triangulation method, and putting the points into a triangle linked list; then sequentially inserting the scattered points in V, finding out a triangle (called an affected triangle of the point) with the scattered points and the circumscribed circle containing the inserted points in a triangle linked list, deleting the public edges of the affected triangle, and connecting the inserted points with all vertexes of the affected triangle, thereby completing the insertion of one point in the Delaunay triangle linked list; optimizing the triangle formed by local new formation according to an optimization criterion, and putting the formed triangle into a Delaunay triangle linked list; and executing the second step circularly until all the scattered points are inserted. For each edge of the edge set E of the obtained undirected graph, finding an edge which is the same with the vertex and is closest to the edge in the clockwise direction, and calculating the included angle between the two edges for the subsequent graph matching process.
As shown in fig. 2, the specific embodiments of the present invention are: the method comprises the steps of constructing a device for improving the stability of plane target characterization based on a graph structure, acquiring a pixel point saliency score graph module 1, generating a self-adaptive grid module 2, constructing a vertex aggregation module 3 and constructing an edge aggregation module 4, wherein the acquired pixel point saliency score graph module 1 calculates the saliency score of each pixel point of an input graph by adopting a rapid binary test strategy in a FAST key point detection algorithm; the self-adaptive grid generation module 2 self-adaptively adjusts the dividing mode of grids according to the preset vertex number, and further self-adaptively adjusts the positions of grid points according to the gesture information of a target in the previous frame in an input diagram; the vertex set constructing module 3 calculates the saliency scores of all the pixel points in each grid by adopting a Spatial Softmax algorithm, and constructs a vertex set by using the pixel point with the highest saliency score, so that the repeated detection of a fixed number of vertices can be ensured; the construction edge set module 4 is used for connecting the obtained vertex sets by adopting a Delaunay triangulation method.
Preferred embodiments of the invention are: the specific method for obtaining the pixel point saliency score map is to calculate the saliency score of each pixel point in the input map according to the difference degree of the gray value of the pixel at the central point in the input map and the gray value of the pixels at the peripheral point taking the central point as the center of a circle and taking r as the radius, so as to obtain the saliency score map of the input map.
Preferred embodiments of the invention are: the standard of the self-adaptive mesh adjustment dividing mode is that the number of divided meshes corresponds to the number in a preset vertex set, and the length-width ratio of each mesh is 1.
Preferred embodiments of the invention are: the specific method for performing further self-adaptive adjustment on the positions of the grid points is to perform projection transformation on the grid points by using the attitude information H to obtain new grid points.
The invention has the technical effects that: the method and the device for improving the stability of the planar target representation based on the graph structure are provided, and the method comprises the following steps: calculating the significance score of each pixel point by adopting a rapid binary test strategy in a FAST key point detection algorithm; generating an adaptive grid by utilizing a dividing mode of the adaptive adjustment grid; constructing a vertex set V by adopting a SpatialSoftmax algorithm; the edge set E is constructed using the Delaunay triangulation method. According to the method, the target is characterized as a group of discrete point sets which have a topological structure and can be repeatedly detected, namely, a vertex set V and a side set E, the global and local structures of the target can be considered, and the robustness and the stability of the characterization method are improved.
In this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, apparatus.
The foregoing is a further detailed description of the invention in connection with the preferred embodiments, and it is not intended that the invention be limited to the specific embodiments described. It will be apparent to those skilled in the art that several simple deductions or substitutions may be made without departing from the spirit of the invention, and these should be considered to be within the scope of the invention.
Claims (8)
1. The method for improving the stability of the planar target representation based on the graph structure is characterized by comprising the following steps of:
(1) Acquiring a pixel point saliency score graph: calculating the saliency score of each pixel point of the input image by adopting a rapid binary test strategy in a FAST key point detection algorithm to obtain a pixel point saliency score image of the input image;
(2) Generating an adaptive mesh: according to the preset vertex number, the dividing mode of the grid is adaptively adjusted, and according to the gesture information of the target in the previous frame in the input diagram, the position of the grid point is adaptively adjusted;
(3) Constructing a vertex set: calculating the saliency scores of all pixel points in each grid by adopting a Spatial Softmax algorithm, and constructing a vertex set by using the pixel points with the highest saliency scores, wherein the method specifically comprises the following steps: constructing a vertex set V of an undirected graph G= (V, E), and selecting pixel points with highest significance scores in each grid to form the vertex set of the undirected graph;
(4) Constructing an edge set: and (3) connecting the vertex sets obtained in the step (3) by adopting a Delaunay triangulation method, wherein the set of all triangular surfaces in the connection mode is a convex hull of the vertex set, and the method specifically comprises the following steps: the method of Delaunay triangulation, which constructs the edge set E of the undirected graph G= (V, E), uses a Bowyer-Watson algorithm that specifically includes:
firstly, constructing a super triangle, wherein the super triangle comprises all points of a point set V, and putting the points into a triangle linked list;
secondly, sequentially inserting the scattered points in the V, finding out an affected triangle with the inserted points in a triangle linked list, deleting the public edges of the affected triangle, and connecting the inserted points with all vertexes of the affected triangle, thereby completing the insertion of one point in the Delaunay triangle linked list;
thirdly, optimizing the triangle formed by local new formation according to an optimization criterion, and putting the formed triangle into a Delaunay triangle linked list;
and fourthly, circularly executing the second step until all the scattered points are inserted.
2. The method for improving stability of planar target characterization based on graph structure according to claim 1, wherein the specific method in step (1) is as follows: and calculating the saliency score of each pixel point in the input graph according to the difference degree of the gray value of the pixel at the central point in the input graph and the gray value of the pixels at the peripheral points taking the central point as the center and the radius r to obtain a saliency score graph of the input graph.
3. The method for improving stability of planar target representation based on graph structure according to claim 1, wherein the criteria for adaptively adjusting the division manner of the grids in the step (2) is that the number of divided grids corresponds to the number of vertex sets set in advance, and the aspect ratio of each grid is 1.
4. The method for improving stability of planar target representation based on graph structure according to claim 3, wherein the specific method for adaptively adjusting the positions of grid points in the step (2) is to perform projective transformation on grid points by using gesture information to obtain new grid points.
5. The device for improving the stability of the planar target representation based on the graph structure is characterized by comprising:
the pixel point saliency score map obtaining module is used for calculating the saliency score of each pixel point of the input map by adopting a rapid binary test strategy in a FAST key point detection algorithm;
the self-adaptive grid generation module is used for self-adaptively adjusting the dividing mode of grids according to the preset vertex number and self-adaptively adjusting the positions of grid points according to the gesture information of a target in a previous frame in an input diagram;
the vertex set constructing unit module is used for calculating the saliency scores of all the pixel points in each grid by adopting a Spatial Softmax algorithm, and constructing a vertex set by using the pixel point with the highest saliency score, and specifically comprises the following steps: constructing a vertex set V of an undirected graph G= (V, E), and selecting pixel points with highest significance scores in each grid to form the vertex set of the undirected graph;
and (3) constructing an edge set unit module, which is used for connecting the vertex sets obtained in the step (3) by adopting a Delaunay triangulation method, wherein the set of all triangular surfaces in the connection mode is a convex hull of the vertex set, and the method specifically comprises the following steps: the method of Delaunay triangulation, which constructs the edge set E of the undirected graph G= (V, E), uses a Bowyer-Watson algorithm that specifically includes:
firstly, constructing a super triangle, wherein the super triangle comprises all points of a point set V, and putting the points into a triangle linked list;
secondly, sequentially inserting the scattered points in the V, finding out an affected triangle with the inserted points in a triangle linked list, deleting the public edges of the affected triangle, and connecting the inserted points with all vertexes of the affected triangle, thereby completing the insertion of one point in the Delaunay triangle linked list;
thirdly, optimizing the triangle formed by local new formation according to an optimization criterion, and putting the formed triangle into a Delaunay triangle linked list;
and fourthly, circularly executing the second step until all the scattered points are inserted.
6. The device for improving stability of planar target characterization based on graph structure according to claim 5, wherein the specific method for obtaining the pixel saliency score graph is as follows: and calculating the saliency score of each pixel point in the input graph according to the difference degree of the gray value of the pixel at the central point in the input graph and the gray value of the pixels at the peripheral points taking the central point as the center and the radius r to obtain a saliency score graph of the input graph.
7. The device for improving stability of planar target representation based on graph structure according to claim 5, wherein the criteria for adaptively adjusting the division manner of the grids is that the number of divided grids corresponds to the number of preset vertex sets, and the aspect ratio of each grid is 1.
8. The method for improving stability of planar target characterization based on graph structure according to claim 7, wherein the specific method for adaptively adjusting the position of the grid point is to perform projective transformation on the grid point by using the gesture information to obtain a new grid point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010935717.0A CN112084938B (en) | 2020-09-08 | 2020-09-08 | Method and device for improving stability of plane target representation based on graph structure |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010935717.0A CN112084938B (en) | 2020-09-08 | 2020-09-08 | Method and device for improving stability of plane target representation based on graph structure |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112084938A CN112084938A (en) | 2020-12-15 |
| CN112084938B true CN112084938B (en) | 2023-07-28 |
Family
ID=73732667
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010935717.0A Active CN112084938B (en) | 2020-09-08 | 2020-09-08 | Method and device for improving stability of plane target representation based on graph structure |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112084938B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117771664B (en) * | 2024-01-03 | 2024-06-07 | 广州创一网络传媒有限公司 | Interactive game projection method of self-adaptive projection surface |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103065357A (en) * | 2013-01-10 | 2013-04-24 | 电子科技大学 | Manufacturing method of shadow figure model based on common three-dimensional model |
| CN107067370A (en) * | 2017-04-12 | 2017-08-18 | 长沙全度影像科技有限公司 | A kind of image split-joint method based on distortion of the mesh |
| CN109345557A (en) * | 2018-09-19 | 2019-02-15 | 东南大学 | A kind of preceding background separating method based on three-dimensional reconstruction achievement |
| CN109902585A (en) * | 2019-01-29 | 2019-06-18 | 中国民航大学 | A kind of three modality fusion recognition methods of finger based on graph model |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100278391A1 (en) * | 2006-10-12 | 2010-11-04 | Yung-Tai Hsu | Apparatus for behavior analysis and method thereof |
-
2020
- 2020-09-08 CN CN202010935717.0A patent/CN112084938B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103065357A (en) * | 2013-01-10 | 2013-04-24 | 电子科技大学 | Manufacturing method of shadow figure model based on common three-dimensional model |
| CN107067370A (en) * | 2017-04-12 | 2017-08-18 | 长沙全度影像科技有限公司 | A kind of image split-joint method based on distortion of the mesh |
| CN109345557A (en) * | 2018-09-19 | 2019-02-15 | 东南大学 | A kind of preceding background separating method based on three-dimensional reconstruction achievement |
| CN109902585A (en) * | 2019-01-29 | 2019-06-18 | 中国民航大学 | A kind of three modality fusion recognition methods of finger based on graph model |
Non-Patent Citations (1)
| Title |
|---|
| 三角网格模型上的四边形曲线网生成新方法;王海霞;孙玉文;苏学成;;工程设计学报(03);第63-68页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112084938A (en) | 2020-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020151212A1 (en) | Calibration method for extrinsic camera parameter of on-board camera system, and calibration system | |
| CN104574347B (en) | Satellite in orbit image geometry positioning accuracy evaluation method based on multi- source Remote Sensing Data data | |
| GB2581374A (en) | 3D Face reconstruction system and method | |
| US10521970B2 (en) | Refining local parameterizations for applying two-dimensional images to three-dimensional models | |
| CN106952338B (en) | Three-dimensional reconstruction method and system based on deep learning and readable storage medium | |
| CN110941999B (en) | Method for adaptively calculating size of Gaussian kernel in crowd counting system | |
| CN109584327B (en) | Face aging simulation method, device and equipment | |
| CN110807459B (en) | License plate correction method and device and readable storage medium | |
| CN109671039B (en) | Image vectorization method based on layering characteristics | |
| CN111382618B (en) | Illumination detection method, device, equipment and storage medium for face image | |
| CN105719248A (en) | Real-time human face deforming method and system | |
| CN108629742B (en) | True ortho image shadow detection and compensation method, device and storage medium | |
| CN114022639A (en) | Three-dimensional reconstruction model generation method and system, electronic device and storage medium | |
| CN113781621A (en) | Three-dimensional reconstruction processing method, device, equipment and storage medium | |
| WO2023116430A1 (en) | Video and city information model three-dimensional scene fusion method and system, and storage medium | |
| US8638330B1 (en) | Water surface generation | |
| CN112084938B (en) | Method and device for improving stability of plane target representation based on graph structure | |
| CN115511752A (en) | BP neural network-based point coordinate distortion removal method and storage medium | |
| CN114241119A (en) | Game model generation method, device and system and computer storage medium | |
| CN110956700A (en) | Density regulation and control method for generating point cloud based on motion recovery structure | |
| CN117671031A (en) | Binocular camera calibration method, device, equipment and storage medium | |
| CN113658144A (en) | Method, device, equipment and medium for determining pavement disease geometric information | |
| CN116152121B (en) | Curved surface screen generating method and correcting method based on distortion parameters | |
| CN116468632A (en) | Grid denoising method and device based on self-adaptive feature preservation | |
| CN116402904A (en) | Combined calibration method based on laser radar inter-camera and monocular camera |
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 |