CN113409457B - Three-dimensional reconstruction and visualization method and equipment for stereoscopic image - Google Patents
Three-dimensional reconstruction and visualization method and equipment for stereoscopic image Download PDFInfo
- Publication number
- CN113409457B CN113409457B CN202110962173.1A CN202110962173A CN113409457B CN 113409457 B CN113409457 B CN 113409457B CN 202110962173 A CN202110962173 A CN 202110962173A CN 113409457 B CN113409457 B CN 113409457B
- Authority
- CN
- China
- Prior art keywords
- image
- point
- points
- visualization
- frame
- 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
- 238000007794 visualization technique Methods 0.000 title abstract description 26
- 238000000034 method Methods 0.000 claims abstract description 59
- 238000009877 rendering Methods 0.000 claims abstract description 45
- 238000012800 visualization Methods 0.000 claims abstract description 39
- 230000011218 segmentation Effects 0.000 claims abstract description 20
- 230000000007 visual effect Effects 0.000 claims abstract description 11
- 239000011159 matrix material Substances 0.000 claims description 16
- 230000009466 transformation Effects 0.000 claims description 16
- 238000001914 filtration Methods 0.000 claims description 11
- 230000015654 memory Effects 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 9
- 230000001131 transforming effect Effects 0.000 claims description 8
- 238000004040 coloring Methods 0.000 claims description 7
- 238000004891 communication Methods 0.000 claims description 7
- 230000002146 bilateral effect Effects 0.000 claims description 5
- HPTJABJPZMULFH-UHFFFAOYSA-N 12-[(Cyclohexylcarbamoyl)amino]dodecanoic acid Chemical compound OC(=O)CCCCCCCCCCCNC(=O)NC1CCCCC1 HPTJABJPZMULFH-UHFFFAOYSA-N 0.000 claims description 4
- 230000000694 effects Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 6
- 238000012876 topography Methods 0.000 description 6
- 238000009499 grossing Methods 0.000 description 4
- 239000003086 colorant Substances 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000001502 supplementing effect Effects 0.000 description 2
- 238000012952 Resampling Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000003706 image smoothing Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/005—General purpose rendering architectures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4007—Scaling of whole images or parts thereof, e.g. expanding or contracting based on interpolation, e.g. bilinear interpolation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20028—Bilateral filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
-
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Processing Or Creating Images (AREA)
- Image Processing (AREA)
Abstract
The invention provides a three-dimensional reconstruction and visualization method and equipment of a stereoscopic image. The method comprises the following steps: carrying out single-frame denoising aiming at a spatial domain and a pixel range domain of the stereoscopic image, and carrying out clustering segmentation on the denoised image to obtain a classified image; performing interpolation fitting on the classified images to obtain a target object smooth image, and acquiring absolute coordinates of each frame of target object smooth image and intensity information of points; registering and splicing the smooth images of the multi-frame target object according to the absolute coordinates to obtain a first image, and performing three-dimensional visual color rendering on the first image according to the intensity information of the points to complete three-dimensional reconstruction and visualization of the stereoscopic image. The invention can remove noise points and clutter, realize accurate registration and splicing of multi-frame data, and improve the visual level and real-time rendering efficiency of sonar images.
Description
Technical Field
The embodiment of the invention relates to the technical field of target imaging, in particular to a three-dimensional reconstruction and visualization method and equipment of a stereoscopic image.
Background
The sonar image of the underwater environment has the problems of low resolution, serious noise interference, multipath phenomenon, sidelobe interference, doppler effect and the like. The original sonar point cloud data generated by the sonar original data collected by the sonar receiving array has the defects of more noise points, more reflection clutter, poor image experience and the like. In addition, when the submarine topography is measured, the traditional beam forming method is adopted, the relation among multiple frames is not clear, so that multiple frames of data cannot be spliced, the obtained topography imaging result is rough, and the high-precision mapping requirement cannot be met. Therefore, developing a method and apparatus for three-dimensional reconstruction and visualization of stereoscopic images can effectively overcome the defects in the related art, and is a technical problem to be solved in the industry.
Disclosure of Invention
Aiming at the problems existing in the prior art, the embodiment of the invention provides a three-dimensional reconstruction and visualization method and equipment of a stereoscopic image.
In a first aspect, an embodiment of the present invention provides a three-dimensional reconstruction and visualization method of a stereoscopic image, including: carrying out single-frame denoising aiming at a spatial domain and a pixel range domain of the stereoscopic image, and carrying out clustering segmentation on the denoised image to obtain a classified image; performing interpolation fitting on the classified images to obtain a target object smooth image, and acquiring absolute coordinates of each frame of target object smooth image and intensity information of points; registering and splicing the smooth images of the multi-frame target object according to the absolute coordinates to obtain a first image, and performing three-dimensional visual color rendering on the first image according to the intensity information of the points to complete three-dimensional reconstruction and visualization of the stereoscopic image.
Based on the content of the embodiment of the method, the three-dimensional reconstruction and visualization method for the stereoscopic image provided by the embodiment of the invention performs single-frame filtering denoising for the spatial domain and the pixel range domain of the stereoscopic image, and comprises the following steps:
the BF is image information which is output after p points of the I stereoscopic image are subjected to bilateral filtering; p is the current point;a multidimensional space that is p; i is a stereoscopic image;p point is I; q is a point in the neighborhood;a multidimensional space of q; s is a neighborhood set of p;whether within the p's domain set;is taken as a norm;spatial domain weights and pixel domain weights, respectively;p point is I;is the q point of I.
Based on the content of the embodiment of the method, the three-dimensional reconstruction and visualization method for the stereo image provided by the embodiment of the invention includes the steps of: positioning a first point in a space, obtaining a first plurality of points which are at a preset distance from the first point, judging the distance from the first plurality of points to the first point, and taking the points with the distance smaller than a distance threshold value and the first point as a first point set; and positioning a second point in the first point set, obtaining a second plurality of points which are at a preset distance from the second point, judging the distance from the second plurality of points to the second point, adding the point with the distance smaller than the distance threshold and the second point into the first point set, repeating the steps until no new point is added into the first point set, and completing clustering segmentation on the denoised image.
Based on the content of the embodiment of the method, the three-dimensional reconstruction and visualization method for the stereoscopic image provided in the embodiment of the present invention, the registering and stitching the smooth images of the multi-frame object according to the absolute coordinates, to obtain the first image, includes: acquiring an overlapping region of a previous frame of object smooth image and a next frame of object smooth image, dividing the overlapping region into a first data set and a second data set, respectively acquiring a first control point set of the first data set and a second control point set of the second data set by adopting a back projection method, carrying out iterative registration on the first control point set and the second control point set to obtain a first transformation matrix of the first control point set and a second transformation matrix of the second control point set, transforming the previous frame of image by adopting the first transformation matrix, transforming the next frame of image by adopting the second transformation matrix, and realizing registration and splicing of the previous frame of object smooth image and the next frame of object smooth image to obtain the first image.
Based on the content of the embodiment of the method, the three-dimensional reconstruction and visualization method for the stereoscopic image provided in the embodiment of the present invention performs three-dimensional visualization color rendering on the first image according to the intensity information of the points, including: and carrying out curved surface reconstruction on the first image, constructing a triangular patch of the three-dimensional surface, and coloring the triangular patch by adopting red, green and blue color rendering based on intensity or color rendering based on normal and curvature.
Based on the content of the embodiment of the method, the three-dimensional reconstruction and visualization method for the stereoscopic image provided by the embodiment of the invention constructs a triangular patch of a three-dimensional surface, which comprises the following steps: projecting the three-dimensional point to a plane through a normal; triangularizing the projected image in a plane area, and performing topological connection on three-dimensional points in the plane to obtain a triangular mesh curved surface model.
Based on the content of the embodiment of the method, the three-dimensional reconstruction and visualization method for the stereoscopic image provided in the embodiment of the invention performs triangularization in a plane area on the image obtained by projection, and performs topological connection on three-dimensional points in the plane to obtain a triangular mesh curved surface model, which comprises the following steps: and selecting a sample triangular plate as an initial curved surface, continuously expanding the boundary of the initial curved surface, and determining topological connection among all original three-dimensional points according to the connection relation of the projection image to form a complete triangular mesh curved surface, wherein the complete triangular mesh curved surface is a triangular mesh curved surface model.
In a second aspect, an embodiment of the present invention provides a three-dimensional reconstruction and visualization apparatus of a stereoscopic image, including: the first main module is used for carrying out single-frame denoising aiming at the spatial domain and the pixel range domain of the stereoscopic image, and carrying out cluster segmentation on the denoised image to obtain a classified image; the second main module is used for carrying out interpolation fitting on the classified images to obtain a target object smooth image, and acquiring absolute coordinates of each frame of target object smooth image and strength information of points; and the third main module is used for registering and splicing the multi-frame object smooth images according to the absolute coordinates to obtain a first image, and performing three-dimensional visual color rendering on the first image according to the intensity information of the points to complete three-dimensional reconstruction and visualization of the stereoscopic image.
In a third aspect, an embodiment of the present invention provides an electronic device, including:
at least one processor; and
at least one memory communicatively coupled to the processor, wherein:
the memory stores program instructions executable by the processor, the processor invoking the program instructions capable of performing the three-dimensional reconstruction and visualization method of stereoscopic images provided by any of the various implementations of the first aspect.
In a fourth aspect, embodiments of the present invention provide a non-transitory computer-readable storage medium storing computer instructions that cause a computer to perform a method for three-dimensional reconstruction and visualization of stereoscopic images provided by any of the various implementations of the first aspect.
According to the three-dimensional reconstruction and visualization method and the device for the stereo image, provided by the embodiment of the invention, the denoised image is subjected to clustering segmentation, the classified image is subjected to interpolation fitting to obtain the object smooth image, the multi-frame object smooth image is subjected to registration splicing according to the absolute coordinates of each frame of object smooth image, and then three-dimensional visualization color rendering is performed, so that noise points and clutter can be removed, the multi-frame data can be accurately registered and spliced, and the visualization level and the real-time rendering efficiency of the sonar image are improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, a brief description will be given below of the drawings required for the embodiments or the prior art descriptions, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without any inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a three-dimensional reconstruction and visualization method for a stereoscopic image according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a three-dimensional reconstruction and visualization device for stereoscopic images according to an embodiment of the present invention;
fig. 3 is a schematic diagram of an entity structure of an electronic device according to an embodiment of the present invention;
FIG. 4 is a schematic view of a three-dimensional image smoothing effect according to an embodiment of the present invention;
fig. 5 is a schematic diagram of multi-frame registration splicing effect of the lakebed of Qingjiang river provided by the embodiment of the invention;
FIG. 6 is a schematic diagram of the effect of constructing a triangular mesh curved surface model according to an embodiment of the present invention;
fig. 7 is a schematic diagram of an image color rendering effect after three-dimensional mesh curved surface stitching according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention. In addition, the technical features of each embodiment or the single embodiment provided by the invention can be combined with each other at will to form a feasible technical scheme, and the combination is not limited by the sequence of steps and/or the structural composition mode, but is necessarily based on the fact that a person of ordinary skill in the art can realize the combination, and when the technical scheme is contradictory or can not realize, the combination of the technical scheme is not considered to exist and is not within the protection scope of the invention claimed.
The three-dimensional reconstruction and visualization method for the stereoscopic image is provided, and the original image data acquired by sonar are processed through processes of denoising filtering, image clustering segmentation, target extraction, three-dimensional reconstruction, registration splicing, three-dimensional visualization rendering and the like, interference such as noise points, clutter and the like is removed, and registration splicing and curved surface reconstruction are carried out on the image, so that a target image similar to the shape and the topography of a target object in a real underwater environment is obtained, and the visualization and the authenticity of the sonar image are enhanced. Based on this idea, an embodiment of the present invention provides a three-dimensional reconstruction and visualization method of a stereoscopic image, referring to fig. 1, the method includes: carrying out single-frame denoising aiming at a spatial domain and a pixel range domain of the stereoscopic image, and carrying out clustering segmentation on the denoised image to obtain a classified image; performing interpolation fitting on the classified images to obtain a target object smooth image, and acquiring absolute coordinates of each frame of target object smooth image and intensity information of points; registering and splicing the smooth images of the multi-frame target object according to the absolute coordinates to obtain a first image, and performing three-dimensional visual color rendering on the first image according to the intensity information of the points to complete three-dimensional reconstruction and visualization of the stereoscopic image. The dot intensity information refers to color intensity information of the pixel dot.
Based on the foregoing disclosure of the method embodiment, as an optional embodiment, the three-dimensional reconstruction and visualization method of a stereoscopic image provided in the embodiment of the present invention performs single-frame filtering denoising for a spatial domain and a pixel range domain of the stereoscopic image, including:
the BF is image information which is output after p points of the I stereoscopic image are subjected to bilateral filtering; p is the current point;a multidimensional space that is p; i is a stereoscopic image;p point is I; q is a point in the neighborhood;a multidimensional space of q; s is a neighborhood set of p;whether within the p's domain set;is taken as a norm;spatial domain weights and pixel domain weights, respectively;p point is I;is the q point of I.
Specifically, filtering denoising is a compromise process combining the spatial proximity of the image and the pixel value similarity, and meanwhile, the spatial domain information and the gray level similarity are considered, so that the purpose of edge protection denoising is achieved. The method has the characteristics of simplicity, non-iteration and local property, and can better save the edges. For the spatial domain (spatial domain) and the pixel range domain (range domain) of the image, there are two weights at the time of designThe specific formula is shown as formula (1).
Based on the foregoing content of the foregoing method embodiment, as an optional embodiment, the three-dimensional reconstruction and visualization method for a stereoscopic image provided in the embodiment of the present invention, where the performing cluster segmentation on the denoised image to obtain a classified image includes: positioning a first point in a space, obtaining a first plurality of points which are at a preset distance from the first point, judging the distance from the first plurality of points to the first point, and taking the points with the distance smaller than a distance threshold value and the first point as a first point set; and positioning a second point in the first point set, obtaining a second plurality of points which are at a preset distance from the second point, judging the distance from the second plurality of points to the second point, adding the point with the distance smaller than the distance threshold and the second point into the first point set, repeating the steps until no new point is added into the first point set, and completing clustering segmentation on the denoised image.
Specifically, a scene has a plurality of targets, target recognition needs to be performed, different targets are separated, so that different targets can be rendered by different colors during rendering, and the specific implementation method of cluster segmentation is as follows: 1) Finding a certain point p10 in the space, finding n nearest points from kdToe (k-dimensional tree), and judging the distance from the n points to p; placing points p12, p13, p14 having a distance less than a distance threshold r in class Q (i.e., a first set of points); finding a point p12 in Q\p10, repeating the step 1); finding a point at q\p10, p12, repeating the steps of 1), finding p22, p23, p24. And when the class Q can not be added with new points any more, completing searching, namely completing clustering segmentation on the denoised image. Performing interpolation fitting on the classified images to obtain a smooth image of the target object, wherein the method specifically comprises the following steps: fitting by three-dimensional reconstruction, interpolation aims at smoothing a three-dimensional image, supplementing empty points, reconstructing the surface to form a triangular surface area sheet, rendering and coloring to obtain a complete target object, and displaying better. Errors in the measurement can cause irregular data, if the surface is reconstructed directly, the reconstructed surface can be unsmooth or leaky, and resampling of the data can be used to solve the problem. The least square method can be used for carrying out surface fitting, smoothing the surface, interpolating the image and supplementing empty points. The effect of smoothing the three-dimensional image by using the least square method can be seen in fig. 4, and the gray part in fig. 4 is the smoothed image, so that the smoothing effect can be seen to be better.
Based on the foregoing disclosure of the method embodiment, as an optional embodiment, the three-dimensional reconstruction and visualization method for a stereoscopic image provided in the embodiment of the present invention, the registering and stitching are performed on a smooth image of a multi-frame object according to absolute coordinates, so as to obtain a first image, which includes: acquiring an overlapping region of a previous frame of object smooth image and a next frame of object smooth image, dividing the overlapping region into a first data set and a second data set, respectively acquiring a first control point set of the first data set and a second control point set of the second data set by adopting a back projection method, carrying out iterative registration on the first control point set and the second control point set to obtain a first transformation matrix of the first control point set and a second transformation matrix of the second control point set, transforming the previous frame of image by adopting the first transformation matrix, transforming the next frame of image by adopting the second transformation matrix, and realizing registration and splicing of the previous frame of object smooth image and the next frame of object smooth image to obtain the first image.
Specifically, the position coordinates and azimuth angles of the sonar are obtained through a GPS sensor, a gyroscope and the like, and are fused with image data, so that absolute coordinate information and strength of each frame of image can be obtained. Because of the influence of ship shaking, measurement errors and the like in the test process, interpolation needs to be carried out on single frame data, and registration of multi-frame images is carried out after fitting, so that a real and good effect is obtained in display of continuous multi-frames. The sensor is used for obtaining the sonar position and angle information, rough registration of the images can be performed, and then the back projection algorithm is used for performing accurate registration to generate new images. The effect of multi-frame registration splicing at the bottom of the Qingjiang river can be seen in fig. 5, and the relief of the terrain can be clearly seen. The middle area is an undetected area, and is out of range. And measuring the obtained data, wherein the edge of the actual position is 60-65 m, the middle area is 90-95 m, and the splicing result is consistent with the actual topography and topography.
Based on the foregoing disclosure of the method embodiment, as an optional embodiment, the three-dimensional reconstruction and visualization method for a stereoscopic image provided in the embodiment of the present invention, where the three-dimensional visualization color rendering is performed on the first image according to the intensity information of the point, includes: and carrying out curved surface reconstruction on the first image, constructing a triangular patch of the three-dimensional surface, and coloring the triangular patch by adopting red, green and blue color rendering based on intensity or color rendering based on normal and curvature.
Based on the foregoing content of the method embodiment, as an optional embodiment, the three-dimensional reconstruction and visualization method of a stereoscopic image provided in the embodiment of the present invention, the constructing a triangular patch of a three-dimensional surface includes: projecting the three-dimensional point to a plane through a normal; triangularizing the projected image in a plane area, and performing topological connection on three-dimensional points in the plane to obtain a triangular mesh curved surface model.
Based on the foregoing disclosure of the method embodiment, as an optional embodiment, the three-dimensional reconstruction and visualization method for a stereoscopic image provided in the embodiment of the present invention, where triangulating an image obtained by projection in a planar area, and performing topological connection on three-dimensional points in the plane to obtain a triangular mesh curved surface model, includes: and selecting a sample triangular plate as an initial curved surface, continuously expanding the boundary of the initial curved surface, and determining topological connection among all original three-dimensional points according to the connection relation of the projection image to form a complete triangular mesh curved surface, wherein the complete triangular mesh curved surface is a triangular mesh curved surface model.
Specifically, referring to fig. 6, the triangular mesh curved surface model constructed can be seen, the system adopts red, green and blue colors to render the image spliced by the three-dimensional mesh curved surface according to the direction of the distance sonar, and the color of the same distance slice is the same, so that the effect shown in fig. 7 is obtained.
According to the three-dimensional reconstruction and visualization method for the stereo image, provided by the embodiment of the invention, the denoised image is subjected to cluster segmentation, the classified image is subjected to interpolation fitting to obtain the object smooth image, the multi-frame object smooth image is subjected to registration splicing according to the absolute coordinates of each frame of object smooth image, and then three-dimensional visualization color rendering is performed, so that noise points and clutter can be removed, accurate registration splicing of multi-frame data is realized, and the visualization level and real-time rendering efficiency of sonar images are improved.
According to the three-dimensional reconstruction and visualization method for the stereoscopic image, provided by the embodiment of the invention, noise points and clutter are effectively removed through a bilateral filtering method; according to GPS and attitude instrument information, the moving distance and azimuth of the ship are calculated, the multi-frame data are registered and spliced by combining an improved icp registration algorithm, and the precision can meet the requirements of topographic map drawing. And the real-time rendering of the topography of the lake bottom is realized under the condition of ensuring the precision. Two frames of data can be realized in real time in one second, and 10 frames per second can be played back; introducing triangular surface area, moving a cube algorithm, converting image data into grid index and vertex data, and rendering an image, a grid and a curved surface respectively by using OpenGL; the visualization of the sonar images is improved, so that a user obtains better experience; and partial functions of OpenGL are accelerated by using a GPU through a CUDA GPU algorithm, so that the real-time rendering efficiency is improved.
The implementation basis of the embodiments of the present invention is realized by a device with a processor function to perform programmed processing. Therefore, in engineering practice, the technical solutions and the functions of the embodiments of the present invention can be packaged into various modules. Based on this reality, on the basis of the above embodiments, an embodiment of the present invention provides a three-dimensional reconstruction and visualization apparatus of a stereoscopic image, which is used to perform the three-dimensional reconstruction and visualization method of a stereoscopic image in the above method embodiment. Referring to fig. 2, the apparatus includes: the first main module is used for carrying out single-frame denoising aiming at the spatial domain and the pixel range domain of the stereoscopic image, and carrying out cluster segmentation on the denoised image to obtain a classified image; the second main module is used for carrying out interpolation fitting on the classified images to obtain a target object smooth image, and acquiring absolute coordinates of each frame of target object smooth image and strength information of points; and the third main module is used for registering and splicing the multi-frame object smooth images according to the absolute coordinates to obtain a first image, and performing three-dimensional visual color rendering on the first image according to the intensity information of the points to complete three-dimensional reconstruction and visualization of the stereoscopic image.
According to the three-dimensional reconstruction and visualization device for the stereoscopic image, provided by the embodiment of the invention, the modules in the figure 2 are adopted, the denoised images are subjected to clustering segmentation, the classified images are subjected to interpolation fitting to obtain the object smooth images, the multi-frame object smooth images are subjected to registration and splicing according to the absolute coordinates of each frame of object smooth images, and then three-dimensional visualization color rendering is carried out, so that noise points and clutter can be removed, accurate registration and splicing of multi-frame data is realized, and the visualization level and real-time rendering efficiency of sonar images are improved.
It should be noted that, the device in the device embodiment provided by the present invention may be used to implement the method in the above method embodiment, and may also be used to implement the method in other method embodiments provided by the present invention, where the difference is merely that the corresponding functional module is provided, and the principle is basically the same as that of the above device embodiment provided by the present invention, so long as a person skilled in the art refers to a specific technical solution in the above device embodiment based on the above device embodiment, and obtains a corresponding technical means by combining technical features, and a technical solution formed by these technical means, and on the premise that the technical solution is ensured to have practicability, the device in the above device embodiment may be modified, so as to obtain a corresponding device embodiment, and be used to implement the method in other method embodiment. For example:
based on the content of the above device embodiment, as an optional embodiment, the three-dimensional reconstruction and visualization device for stereoscopic image provided in the embodiment of the present invention further includes: the first sub-module is configured to implement the single-frame filtering denoising for the spatial domain and the pixel range domain of the stereoscopic image, and includes:
the BF is image information which is output after p points of the I stereoscopic image are subjected to bilateral filtering; p is the current point;a multidimensional space that is p; i is a stereoscopic image;p point is I; q is a point in the neighborhood;a multidimensional space of q; s is a neighborhood set of p;whether within the p's domain set;is taken as a norm;spatial domain weights and pixel domain weights, respectively;p point is I;is the q point of I.
Based on the content of the above device embodiment, as an optional embodiment, the three-dimensional reconstruction and visualization device for stereoscopic image provided in the embodiment of the present invention further includes: the second sub-module is configured to implement the clustering segmentation on the denoised image to obtain a classified image, and includes: positioning a first point in a space, obtaining a first plurality of points which are at a preset distance from the first point, judging the distance from the first plurality of points to the first point, and taking the points with the distance smaller than a distance threshold value and the first point as a first point set; and positioning a second point in the first point set, obtaining a second plurality of points which are at a preset distance from the second point, judging the distance from the second plurality of points to the second point, adding the point with the distance smaller than the distance threshold and the second point into the first point set, repeating the steps until no new point is added into the first point set, and completing clustering segmentation on the denoised image.
Based on the content of the above device embodiment, as an optional embodiment, the three-dimensional reconstruction and visualization device for stereoscopic image provided in the embodiment of the present invention further includes: the third sub-module is configured to implement registration stitching on the smoothed image of the multi-frame target object according to the absolute coordinates, to obtain a first image, and includes: acquiring an overlapping region of a previous frame of object smooth image and a next frame of object smooth image, dividing the overlapping region into a first data set and a second data set, respectively acquiring a first control point set of the first data set and a second control point set of the second data set by adopting a back projection method, carrying out iterative registration on the first control point set and the second control point set to obtain a first transformation matrix of the first control point set and a second transformation matrix of the second control point set, transforming the previous frame of image by adopting the first transformation matrix, transforming the next frame of image by adopting the second transformation matrix, and realizing registration and splicing of the previous frame of object smooth image and the next frame of object smooth image to obtain the first image.
Based on the content of the above device embodiment, as an optional embodiment, the three-dimensional reconstruction and visualization device for stereoscopic image provided in the embodiment of the present invention further includes: a fourth sub-module, configured to implement three-dimensional visual color rendering of the first image according to the intensity information of the point, including: and carrying out curved surface reconstruction on the first image, constructing a triangular patch of the three-dimensional surface, and coloring the triangular patch by adopting red, green and blue color rendering based on intensity or color rendering based on normal and curvature.
Based on the content of the above device embodiment, as an optional embodiment, the three-dimensional reconstruction and visualization device for stereoscopic image provided in the embodiment of the present invention further includes: a fifth sub-module, configured to implement the triangular patch for constructing a three-dimensional surface, including: projecting the three-dimensional point to a plane through a normal; triangularizing the projected image in a plane area, and performing topological connection on three-dimensional points in the plane to obtain a triangular mesh curved surface model.
Based on the content of the above device embodiment, as an optional embodiment, the three-dimensional reconstruction and visualization device for stereoscopic image provided in the embodiment of the present invention further includes: a sixth sub-module, configured to implement the triangularization in the planar area of the image obtained by projection, and obtain a triangular mesh curved surface model according to topology connection of three-dimensional points in a plane, where the method includes: and selecting a sample triangular plate as an initial curved surface, continuously expanding the boundary of the initial curved surface, and determining topological connection among all original three-dimensional points according to the connection relation of the projection image to form a complete triangular mesh curved surface, wherein the complete triangular mesh curved surface is a triangular mesh curved surface model.
The method of the embodiment of the invention is realized by the electronic equipment, so that the related electronic equipment is necessary to be introduced. To this end, an embodiment of the present invention provides an electronic device, as shown in fig. 3, including: at least one processor (processor), a communication interface (Communications Interface), at least one memory (memory) and a communication bus, wherein the at least one processor, the communication interface, and the at least one memory communicate with each other via the communication bus. The at least one processor may invoke logic instructions in the at least one memory to perform all or part of the steps of the methods provided by the various method embodiments described above.
Further, the logic instructions in at least one of the memories described above may be implemented in the form of a software functional unit and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. Based on this knowledge, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In this patent, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or 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, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. A method for three-dimensional reconstruction and visualization of stereoscopic images, comprising: carrying out single-frame denoising aiming at a spatial domain and a pixel range domain of the stereoscopic image, and carrying out clustering segmentation on the denoised image to obtain a classified image; performing interpolation fitting on the classified images to obtain a target object smooth image, and acquiring absolute coordinates of each frame of target object smooth image and intensity information of points; registering and splicing the smooth images of the multi-frame target object according to the absolute coordinates to obtain a first image, and performing three-dimensional visual color rendering on the first image according to the intensity information of the points to complete three-dimensional reconstruction and visualization of the stereoscopic image; the three-dimensional visual color rendering of the first image according to the intensity information of the points comprises: performing curved surface reconstruction on the first image, constructing a triangular patch of the three-dimensional surface, and coloring the triangular patch by adopting red, green and blue color rendering based on intensity or color rendering based on normal and curvature; introducing triangular surface area, moving a cube algorithm, converting image data into grid index and vertex data, and rendering an image, a grid and a curved surface respectively by using OpenGL; the visualization of the sonar images is improved, so that a user obtains better experience; accelerating partial functions of OpenGL by using a GPU through a CUDA GPU algorithm, and improving real-time rendering efficiency;
the method for clustering and segmenting the denoised image to obtain the classified image comprises the following steps: positioning a first point in a space, obtaining a first plurality of points which are at a preset distance from the first point, judging the distance from the first plurality of points to the first point, and taking the points with the distance smaller than a distance threshold value and the first point as a first point set; and positioning a second point in the first point set, obtaining a second plurality of points which are at a preset distance from the second point, judging the distance from the second plurality of points to the second point, adding the point with the distance smaller than the distance threshold and the second point into the first point set, repeating the steps until no new point is added into the first point set, and completing clustering segmentation on the denoised image.
2. The method for three-dimensional reconstruction and visualization of stereoscopic images according to claim 1, wherein said single frame filtering denoising for stereoscopic image spatial domain and pixel range domain comprises:
wherein ,the p point of the I stereo image is subjected to bilateral filtering to obtain image information; p is the current point; />A multidimensional space that is p; i is a stereoscopic image; q is a point in the neighborhood; />A multidimensional space of q; s is a neighborhood set of p; />Is->Whether within the p's domain set; the norm is taken; omega s and ωr Spatial domain weights and pixel domain weights, respectively; />P point is I; />Is the q point of I.
3. The method for three-dimensional reconstruction and visualization of stereoscopic images according to claim 1, wherein the registering and stitching the smoothed images of the multiple frames of objects according to the absolute coordinates to obtain the first image comprises: acquiring an overlapping region of a previous frame of object smooth image and a next frame of object smooth image, dividing the overlapping region into a first data set and a second data set, respectively acquiring a first control point set of the first data set and a second control point set of the second data set by adopting a back projection method, carrying out iterative registration on the first control point set and the second control point set to obtain a first transformation matrix of the first control point set and a second transformation matrix of the second control point set, transforming the previous frame of image by adopting the first transformation matrix, transforming the next frame of image by adopting the second transformation matrix, and realizing registration and splicing of the previous frame of object smooth image and the next frame of object smooth image to obtain the first image.
4. A method of three-dimensional reconstruction and visualization of stereoscopic images according to claim 3, wherein said constructing a triangular patch of a three-dimensional surface comprises: introducing triangular surface patches, moving a cube algorithm, and converting image data into index and vertex data of a grid; and constructing a triangular patch of the three-dimensional surface, and rendering by taking the triangular patch as a unit.
5. The method for three-dimensional reconstruction and visualization of stereoscopic images according to claim 4, wherein constructing a triangular patch of a three-dimensional surface, and rendering the triangular patch as a unit, comprises: coloring the triangular patch by adopting red, green and blue color rendering based on intensity or color rendering based on normal direction and curvature; introducing OpenGL to respectively render images, grids and curved surfaces; the visualization of the sonar images is improved, so that a user obtains better experience; and partial functions of OpenGL are accelerated by using a GPU through a CUDA GPU algorithm, so that the real-time rendering efficiency is improved.
6. A three-dimensional reconstruction and visualization apparatus for stereoscopic images, comprising: the first main module is used for carrying out single-frame denoising aiming at the spatial domain and the pixel range domain of the stereoscopic image, and carrying out cluster segmentation on the denoised image to obtain a classified image; the second main module is used for carrying out interpolation fitting on the classified images to obtain a target object smooth image, and acquiring absolute coordinates of each frame of target object smooth image and strength information of points; the third main module is used for registering and splicing the multi-frame object smooth images according to the absolute coordinates to obtain a first image, and performing three-dimensional visual color rendering on the first image according to the intensity information of the points to complete three-dimensional reconstruction and visualization of the stereoscopic image; the three-dimensional visual color rendering of the first image according to the intensity information of the points comprises: performing curved surface reconstruction on the first image, constructing a triangular patch of the three-dimensional surface, and coloring the triangular patch by adopting red, green and blue color rendering based on intensity or color rendering based on normal and curvature; introducing triangular surface area, moving a cube algorithm, converting image data into grid index and vertex data, and rendering an image, a grid and a curved surface respectively by using OpenGL; the visualization of the sonar images is improved, so that a user obtains better experience; accelerating partial functions of OpenGL by using a GPU through a CUDA GPU algorithm, and improving real-time rendering efficiency;
the method for clustering and segmenting the denoised image to obtain the classified image comprises the following steps: positioning a first point in a space, obtaining a first plurality of points which are at a preset distance from the first point, judging the distance from the first plurality of points to the first point, and taking the points with the distance smaller than a distance threshold value and the first point as a first point set; and positioning a second point in the first point set, obtaining a second plurality of points which are at a preset distance from the second point, judging the distance from the second plurality of points to the second point, adding the point with the distance smaller than the distance threshold and the second point into the first point set, repeating the steps until no new point is added into the first point set, and completing clustering segmentation on the denoised image.
7. An electronic device, comprising:
at least one processor, at least one memory, and a communication interface; wherein,
the processor, the memory and the communication interface are communicated with each other;
the memory stores program instructions executable by the processor, the processor invoking the program instructions to perform the method of any of claims 1-5.
8. A non-transitory computer readable storage medium storing computer instructions that cause the computer to perform the method of any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110962173.1A CN113409457B (en) | 2021-08-20 | 2021-08-20 | Three-dimensional reconstruction and visualization method and equipment for stereoscopic image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110962173.1A CN113409457B (en) | 2021-08-20 | 2021-08-20 | Three-dimensional reconstruction and visualization method and equipment for stereoscopic image |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113409457A CN113409457A (en) | 2021-09-17 |
CN113409457B true CN113409457B (en) | 2023-06-16 |
Family
ID=77688962
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110962173.1A Active CN113409457B (en) | 2021-08-20 | 2021-08-20 | Three-dimensional reconstruction and visualization method and equipment for stereoscopic image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113409457B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117934858B (en) * | 2024-03-21 | 2024-06-04 | 之江实验室 | Point cloud processing method and device, storage medium and electronic equipment |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7804498B1 (en) * | 2004-09-15 | 2010-09-28 | Lewis N Graham | Visualization and storage algorithms associated with processing point cloud data |
CN102074046A (en) * | 2010-12-17 | 2011-05-25 | 浙江大学 | Offline processing system and method for phased array three-dimensional sonar images |
WO2012079465A1 (en) * | 2010-12-17 | 2012-06-21 | 浙江大学 | Real-time processing system and method for phased array three-dimensional acoustics image pickup sonar |
WO2017016511A1 (en) * | 2015-07-29 | 2017-02-02 | 努比亚技术有限公司 | Image processing method and device, and terminal |
CN107085726A (en) * | 2017-01-04 | 2017-08-22 | 安阳师范学院 | Oracle bone rubbing individual character localization method based on multi-method denoising and connected component analysis |
CN108335350A (en) * | 2018-02-06 | 2018-07-27 | 聊城大学 | The three-dimensional rebuilding method of binocular stereo vision |
CN108596923A (en) * | 2018-05-14 | 2018-09-28 | 江苏哈工智能机器人股份有限公司 | Acquisition methods, device and the electronic equipment of three-dimensional data |
CN111462030A (en) * | 2020-03-27 | 2020-07-28 | 高小翎 | Multi-image fused stereoscopic set vision new angle construction drawing method |
CN111880185A (en) * | 2020-08-14 | 2020-11-03 | 宁波博海深衡科技有限公司 | Underwater target surveying processing method and system |
CN112598789A (en) * | 2020-12-30 | 2021-04-02 | 深圳中科智美科技有限公司 | Image texture reconstruction method, device and equipment and storage medium |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20140147729A (en) * | 2013-06-20 | 2014-12-30 | (주)로딕스 | Apparatus for dynamic texturing based on stream image in rendering system and method thereof |
US9392262B2 (en) * | 2014-03-07 | 2016-07-12 | Aquifi, Inc. | System and method for 3D reconstruction using multiple multi-channel cameras |
CN108109113A (en) * | 2017-11-09 | 2018-06-01 | 齐鲁工业大学 | Single image to the fog method and device based on bilateral filtering and medium filtering |
CN112562082A (en) * | 2020-08-06 | 2021-03-26 | 长春理工大学 | Three-dimensional face reconstruction method and system |
-
2021
- 2021-08-20 CN CN202110962173.1A patent/CN113409457B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7804498B1 (en) * | 2004-09-15 | 2010-09-28 | Lewis N Graham | Visualization and storage algorithms associated with processing point cloud data |
CN102074046A (en) * | 2010-12-17 | 2011-05-25 | 浙江大学 | Offline processing system and method for phased array three-dimensional sonar images |
WO2012079465A1 (en) * | 2010-12-17 | 2012-06-21 | 浙江大学 | Real-time processing system and method for phased array three-dimensional acoustics image pickup sonar |
WO2017016511A1 (en) * | 2015-07-29 | 2017-02-02 | 努比亚技术有限公司 | Image processing method and device, and terminal |
CN107085726A (en) * | 2017-01-04 | 2017-08-22 | 安阳师范学院 | Oracle bone rubbing individual character localization method based on multi-method denoising and connected component analysis |
CN108335350A (en) * | 2018-02-06 | 2018-07-27 | 聊城大学 | The three-dimensional rebuilding method of binocular stereo vision |
CN108596923A (en) * | 2018-05-14 | 2018-09-28 | 江苏哈工智能机器人股份有限公司 | Acquisition methods, device and the electronic equipment of three-dimensional data |
CN111462030A (en) * | 2020-03-27 | 2020-07-28 | 高小翎 | Multi-image fused stereoscopic set vision new angle construction drawing method |
CN111880185A (en) * | 2020-08-14 | 2020-11-03 | 宁波博海深衡科技有限公司 | Underwater target surveying processing method and system |
CN112598789A (en) * | 2020-12-30 | 2021-04-02 | 深圳中科智美科技有限公司 | Image texture reconstruction method, device and equipment and storage medium |
Non-Patent Citations (2)
Title |
---|
Real-Time 3D sonar Image recognition for underwater vehicles[C].In Proc.Symposium on Underwater Technology and Workshop on Scientific Use of Submarine Cables and Related Technologies;Yu S C;《In Proc.Symposium on Underwater Technology and Workshop on Scientific Use of Submarine Cables and Related Technologies》;第142-146页 * |
数字博物馆文物图像真实性再现仿真***设计;陈强;张立红;;科学技术与工程(第11期);第200-205页 * |
Also Published As
Publication number | Publication date |
---|---|
CN113409457A (en) | 2021-09-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP2622581B1 (en) | Multi-view ray tracing using edge detection and shader reuse | |
KR101554241B1 (en) | A method for depth map quality enhancement of defective pixel depth data values in a three-dimensional image | |
KR101165523B1 (en) | Geospatial modeling system and related method using multiple sources of geographic information | |
CN110969624A (en) | Laser radar three-dimensional point cloud segmentation method | |
CN109961401A (en) | A kind of method for correcting image and storage medium of binocular camera | |
CN114241125B (en) | Multi-view satellite image-based fine three-dimensional modeling method and system | |
CN111080662A (en) | Lane line extraction method and device and computer equipment | |
US20210209776A1 (en) | Method and device for depth image fusion and computer-readable storage medium | |
CN108629742B (en) | True ortho image shadow detection and compensation method, device and storage medium | |
CN113781621A (en) | Three-dimensional reconstruction processing method, device, equipment and storage medium | |
CN114332125A (en) | Point cloud reconstruction method and device, electronic equipment and storage medium | |
CN113409457B (en) | Three-dimensional reconstruction and visualization method and equipment for stereoscopic image | |
CN113920275B (en) | Triangular mesh construction method and device, electronic equipment and readable storage medium | |
CN113593033A (en) | Three-dimensional model feature extraction method based on grid subdivision structure | |
CN114519778B (en) | Target three-dimensional reconstruction method, device, equipment and medium of multi-angle SAR data | |
CN113012063A (en) | Dynamic point cloud repairing method and device and computer equipment | |
CN115631317B (en) | Tunnel lining ortho-image generation method and device, storage medium and terminal | |
Deng et al. | Automatic true orthophoto generation based on three-dimensional building model using multiview urban aerial images | |
CN116189140A (en) | Binocular vision-based vehicle three-dimensional target detection algorithm | |
CN112258635B (en) | Three-dimensional reconstruction method and device based on improved binocular matching SAD algorithm | |
Oko et al. | Evaluation of image processing algorithms on vehicle safety system based on free-viewpoint image rendering | |
Zakaria | Application of Ifsar technology in topographic mapping: JUPEM’s experience | |
CN116805355B (en) | Multi-view three-dimensional reconstruction method for resisting scene shielding | |
CN113284230B (en) | Three-dimensional reconstruction method for image sequence | |
CN116883499A (en) | Image positioning method, image positioning device, electronic equipment and readable storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |