CN114963991A - Hull stone volume measurement system based on three-dimensional reconstruction - Google Patents
Hull stone volume measurement system based on three-dimensional reconstruction Download PDFInfo
- Publication number
- CN114963991A CN114963991A CN202210776816.8A CN202210776816A CN114963991A CN 114963991 A CN114963991 A CN 114963991A CN 202210776816 A CN202210776816 A CN 202210776816A CN 114963991 A CN114963991 A CN 114963991A
- Authority
- CN
- China
- Prior art keywords
- stone
- dimensional
- point cloud
- unit
- dimensional 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.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01F—MEASURING VOLUME, VOLUME FLOW, MASS FLOW OR LIQUID LEVEL; METERING BY VOLUME
- G01F17/00—Methods or apparatus for determining the capacity of containers or cavities, or the volume of solid bodies
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/766—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using regression, e.g. by projecting features on hyperplanes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30132—Masonry; Concrete
-
- 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
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Fluid Mechanics (AREA)
- Geometry (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a ship body stone volume measuring system based on three-dimensional reconstruction, which is characterized by comprising the following components: the acquisition module is used for acquiring three-dimensional point cloud data of the ship body stone; the processing module is connected with the acquisition module and used for performing three-dimensional reconstruction according to the three-dimensional point cloud data to obtain a three-dimensional point cloud picture; the modeling module is connected with the processing module and used for constructing a stone three-dimensional model according to the three-dimensional point cloud picture and sealing the stone three-dimensional model to obtain a sealed stone three-dimensional model; and the measuring module is connected with the modeling module and used for obtaining the volume of the stone based on the closed stone three-dimensional model. The invention reduces the input and consumption of manpower, material resources and time in the measuring process, and the error of the calculated stone volume and the actual volume is smaller, thereby achieving the purpose of quickly measuring the stone volume of the ship body.
Description
Technical Field
The invention belongs to the field of volume measurement, and particularly relates to a ship body stone volume measurement system based on three-dimensional reconstruction.
Background
With the implementation of large-scale channel construction and bank protection engineering, a large amount of stones are needed in a large amount of stone throwing engineering, and the volume of the stones needs to be measured and estimated quickly before the stones are delivered for use so as to determine the material cost and the stone throwing square amount. Because the demand for riprapping is huge, and the tonnage models of the bodies of the transport ships are different, the traditional manual measuring method wastes time and labor, has low efficiency and has larger interference on construction. The consumption of manpower, material resources and time in the traditional measuring process is huge and the error is higher. In order to improve the efficiency of measuring the volume of the stone of the ship body, a new stone volume measuring method is to be developed.
Disclosure of Invention
The invention aims to provide a ship hull stone volume measuring system based on three-dimensional reconstruction, which is used for solving the problems in the prior art.
In order to achieve the above object, the present invention provides a ship hull stone volume measuring system based on three-dimensional reconstruction, comprising:
the acquisition module is used for acquiring three-dimensional point cloud data of the ship body stone;
the processing module is connected with the acquisition module and used for performing three-dimensional reconstruction according to the three-dimensional point cloud data to obtain a three-dimensional point cloud picture;
the modeling module is connected with the processing module and used for constructing a three-dimensional stone model according to the three-dimensional point cloud picture and sealing the three-dimensional stone model to obtain a sealed three-dimensional stone model;
and the measuring module is connected with the modeling module and used for obtaining the volume of the stone based on the closed stone three-dimensional model.
Preferably, the processing module comprises:
the preprocessing unit is used for carrying out noise reduction processing on the three-dimensional point cloud data by using a mean value filtering operator to obtain noise-reduced three-dimensional point cloud data;
and the three-dimensional reconstruction unit is used for performing three-dimensional reconstruction on the three-dimensional point cloud data subjected to noise reduction to obtain a three-dimensional point cloud picture.
Preferably, the three-dimensional reconstruction unit includes:
the matching unit is used for carrying out stereo matching on the three-dimensional point cloud data subjected to noise reduction to obtain a disparity map;
and the drawing unit is used for obtaining a depth map according to the parallax map and drawing a three-dimensional point cloud map based on the depth map.
Preferably, the processing module comprises:
the identification unit is used for marking the stone according to the profile and the type of the stone to generate marking information;
and the segmentation unit is used for segmenting the three-dimensional point cloud picture of the stone according to the three-dimensional point cloud picture and the marking information.
Preferably, the modeling module comprises:
the first modeling unit is used for constructing a first stone three-dimensional model based on the three-dimensional point cloud picture of the stone;
and the second modeling unit is used for carrying out closed processing on the first stone three-dimensional model to obtain a second stone three-dimensional model.
Preferably, the second modeling unit includes:
the sectioning unit is used for sectioning the first stone three-dimensional model to obtain an initial contour line;
the cutting unit is used for cutting off the convex area on the initial contour line to obtain a target contour line;
the interpolation unit is used for carrying out interpolation processing on the target contour line to obtain a regular triangle mesh boundary;
and the closing unit is used for closing the first stone three-dimensional model based on the target contour line and the regular triangle grid boundary to obtain a second stone three-dimensional model.
Preferably, the interpolation unit includes:
the generating unit is used for carrying out interpolation processing on the target contour line to obtain a plurality of regular triangle meshes;
and the extracting unit is used for extracting a plurality of regular triangle grids to obtain the boundaries of the regular triangle grids.
The invention has the technical effects that:
when a stone three-dimensional model is constructed, the collected three-dimensional point cloud data of the ship stones is cut, so that the accuracy of stone volume measurement is greatly improved; and the measurement efficiency of the whole measurement and calculation is accelerated in the segmentation process. When the built three-dimensional stone model is subjected to sealing treatment, the convex area is cut off by utilizing convex hull, so that the error between the calculated stone volume and the actual volume can be reduced. In addition, the measuring and calculating process reduces the input consumption of manpower, material resources and time in the measuring process, and can achieve the purpose of quickly measuring the volume of the stone of the ship body.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application. In the drawings:
fig. 1 is a system configuration diagram in the embodiment of the present invention.
Detailed Description
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
Example one
In order to achieve the above object, as shown in fig. 1, the present invention provides a ship hull stone volume measuring system based on three-dimensional reconstruction, comprising:
the acquisition module is used for acquiring three-dimensional point cloud data of the ship stones;
the embodiment adopts a three-dimensional scanner to collect three-dimensional point cloud data of the stone of the ship body. The basic working principle of the three-dimensional scanner is as follows: a composite three-dimensional non-contact measurement technology combining a structured light technology, a phase measurement technology and a computer vision technology is adopted. By adopting the measurement principle, the object can be photogrammetrically measured, namely, the object in the visual field is photographed by the camera similarly, but the camera takes a two-dimensional image of the object, and the three-dimensional scanner adopted by the embodiment obtains three-dimensional information of the object. Unlike the conventional three-dimensional scanner, the three-dimensional scanner used in the present embodiment can measure one surface at a time. During measurement, corresponding images are synchronously acquired according to two cameras forming a certain included angle, then decoding and phase calculation are carried out on the images, and the three-dimensional coordinates of pixel points in the common visual area of the two cameras are calculated by utilizing a matching technology and a triangle measurement principle.
And the processing module is connected with the acquisition module and used for performing three-dimensional reconstruction according to the three-dimensional point cloud data to obtain a three-dimensional point cloud picture. Further, the processing module comprises: the preprocessing unit is used for carrying out noise reduction processing on the three-dimensional point cloud data by using mean filtering to obtain noise-reduced three-dimensional point cloud data; and the three-dimensional reconstruction unit is used for performing three-dimensional reconstruction on the three-dimensional point cloud data subjected to noise reduction to obtain a three-dimensional point cloud picture. Further, the three-dimensional reconstruction unit includes: the matching unit is used for carrying out stereo matching on the three-dimensional point cloud data subjected to noise reduction to obtain a disparity map; and the drawing unit is used for obtaining a depth map according to the parallax map and drawing a three-dimensional point cloud map based on the depth map. Further, the processing module comprises: the identification unit is used for marking the stone according to the profile and the type of the stone to generate marking information; and the segmentation unit is used for segmenting the three-dimensional point cloud picture of the stone according to the three-dimensional point cloud picture and the marking information.
Specifically, the present embodiment provides a method for identifying and segmenting a three-dimensional point cloud. The object in the three-dimensional point cloud data is identified and segmented, the semantic segmentation and the example segmentation in the convolutional neural network can achieve the object segmentation effect, but different objects can only be segmented from the background in the semantic segmentation, and the segmentation effect cannot be achieved for similar objects, so that the example segmentation network is selected, the pixel-level classification is carried out, and different examples need to be distinguished on the basis of specific classes.
The example segmentation network adopted by the embodiment is a Mask-RCNN network, and the Mask-RCNN network segments target pixels while realizing target detection by adding a branch network on the basis of target detection Faster-RCNN. Each candidate object in the target detection has two outputs, namely a class label (1abe1) and a bounding-bounding offset (bounding-bounding offset); the example is divided into a third branch for improving the precision and adding the mask (binary mask) of the output object. But the additional mask output, unlike the class and box output, requires a finer spatial layout of the extracted objects. At the same time, the classification also depends on the mask prediction.
The Mask-RCNN neural network segmentation process comprises the following steps: inputting the acquired image data of the ship hull stone, preprocessing the image, changing the image into a fixed size, extracting the features through the convolution layer, and outputting the feature map. And sending the feature map into an RPN (resilient packet network) which is used for distinguishing and preliminarily positioning a plurality of ROIs generated by the convolutional network and outputting four predicted values of the regression frame. Wherein, the ROI Align (region feature aggregation mode) is used for fixing the ROI on the feature map into the feature map with a specific size through a maximum pooling operation so as to perform subsequent classification and bounding box regression operation. And finally, outputting a classification result and a regression box through averagePooling (global average pooling operation), and outputting a mask through deconv deconvolution operation.
The example split network implementation process used in this embodiment is as follows:
(1) marking
Marking the type (stone) of the object to be identified, including the contour mark and the type label of the object, processing the marked picture to generate a mask, and finally converting the mask into a file format required in training.
(2) Training
And dividing the converted image file into a training set and a test set, wherein 1000 pictures in the test set are verified by 200 pictures.
(3) Detection of
The input image of the convolutional neural network is preprocessed. Since the captured image is in PNG format, with four channels, only three channels of input are required in the neural network, requiring conversion of the picture to JPG format. During detection, a detection image is obtained and input into the convolutional neural network. The input images are processed by a convolution neural network to generate a corresponding outline box of an object in the picture, the object class and the confidence rate, and a binary mask of the object.
The embodiment can accurately identify and segment the target object from the three-dimensional scene so as to improve the volume measurement precision of the target object.
The embodiment also comprises a modeling module which is connected with the processing module and used for constructing a three-dimensional model of the stone according to the three-dimensional point cloud picture. Further, the modeling module includes: the first modeling unit is used for constructing a first stone three-dimensional model based on the three-dimensional point cloud picture of the stone; and the second modeling unit is used for carrying out closed processing on the first stone three-dimensional model to obtain a second stone three-dimensional model. Further, the second modeling unit includes: the sectioning unit is used for sectioning the first stone three-dimensional model to obtain an initial contour line; the cutting unit is used for cutting off the convex area on the initial contour line to obtain a target contour line; the interpolation unit is used for carrying out interpolation processing on the target contour line to obtain a regular triangle mesh boundary; and the closing unit is used for closing the first stone three-dimensional model based on the target contour line and the regular triangle grid boundary to obtain a second stone three-dimensional model. Further, the interpolation unit includes: the generating unit is used for carrying out interpolation processing on the target contour line to obtain a plurality of regular triangle meshes; and the extracting unit is used for extracting the plurality of regular triangle meshes to obtain the boundaries of the regular triangle meshes. And the measuring module is connected with the modeling module and used for obtaining the volume of the stone based on the three-dimensional model of the stone.
The embodiment utilizes convex hull to replace the triangulation of three-dimensional point cloud data of stone materials, and can solve the problem that the volume of an unsealed three-dimensional model cannot be measured, thereby further improving the practicability.
Firstly, a contour line generated by sectioning a stone three-dimensional model through a sectioning plane is obtained, wherein the stone three-dimensional model is a solid triangular mesh model and comprises a plurality of triangles in a triangular mesh form.
When building a stone three-dimensional model based on three-dimensional point cloud data, a topological relation between point clouds can be built according to a storage ring, so that an entity triangular mesh model capable of accurately reflecting the shape of a dead zone is built. The entity triangular mesh model comprises a plurality of triangles in a triangular mesh form.
The sectioning plane can be a plane for sectioning the three-dimensional stone model according to actual requirements. Because the stone three-dimensional model comprises a plurality of triangles, the process of sectioning the stone three-dimensional model by adopting the sectioning plane can be regarded as the process of sectioning the plurality of triangles by adopting the sectioning plane. There will be points of intersection with the cut plane in the cut triangle. The intersection points belonging to the same triangle can form an intersection line segment, and the intersection line segments corresponding to a plurality of triangles can be combined into a sectioning plane to section the stone three-dimensional model to obtain a contour line.
Generally, a sectioning plane is adopted to section the three-dimensional model of the stone material to obtain a positive area triangular net and a negative area triangular net. In order to ensure the integrity of the newly generated triangular mesh model, the cross section of the model needs to be closed. Generally, the model section may be one or more irregular polygons, and the essence of closing the model section is to triangulate the irregular polygons internally on a plane, i.e., to triangulate the polygons formed by the aforementioned contours.
And cutting off the convex area of the contour line to obtain a target contour line, wherein the target contour line is a polygonal contour line.
In the embodiment of the present application, for the outline in the form of a polygon, it may include a partially convex region. In order to ensure the smooth proceeding of the subsequent interpolation and avoid generating a very long and narrow triangle during the closing, the convex area on the contour line can be cut off to obtain the target contour line. It should be noted that the contour of the target obtained by cutting off the protruding region is still a polygon.
For an initial contour line, its beginning and end points may be defined first. It should be noted that, for the extracted initial contour line, one intersection point may be randomly defined as a head point, and the corresponding other intersection point is a tail point. After the initial contour line is selected, the initial contour line may be deleted from the intersection container. Then, all the intersecting line segments in the intersecting line container can be traversed, the adjacent intersecting line segments of the initial contour line are determined, and the tail points of the initial contour line are updated according to the target points of the adjacent intersecting line segments until the final contour line is generated. The target point of the adjacent intersection line segment is the point farther away from the initial contour line in the head point and the tail point of the adjacent intersection line segment.
And carrying out internal interpolation on the target contour line so as to generate a plurality of regular triangle meshes in the target contour line.
In this embodiment, the internal interpolation of the target contour line may refer to determining a plurality of interpolation points in a polygon formed by the target contour line by means of interpolation, and the interpolation points may form a plurality of regular triangle meshes with each other.
In a specific implementation, an interpolation interval, that is, a side length of a regular triangle, may be determined first. Then, an initial interpolation point is determined in a polygon formed by the target contour line, and the initial interpolation point is used as a vertex of the regular triangle to respectively form a plurality of regular triangles with the interpolation distance as the side length towards the periphery.
In general, the starting interpolation point may be as close as possible to the central region of the polygon formed by the target contour line. According to the characteristics of regular triangles, the start interpolation point is used as a vertex of the regular triangle, and at most six regular triangles can be formed around the start interpolation point. After the six regular triangles are formed, one side of each regular triangle can be used as one side of another regular triangle, and the new regular triangle is formed by continuing to expand towards the periphery until a plurality of regular triangle meshes are formed in the area surrounded by the target contour line.
It should be noted that the boundaries of the regular triangular meshes finally formed in the region surrounded by the target contour line should not exceed the target contour line. That is, the respective vertices of the plurality of regular triangular meshes formed within the region surrounded by the target contour line should be located within the region surrounded by the target contour line.
And extracting the regular triangle mesh boundary formed by the plurality of regular triangle meshes.
Since the regular triangles formed in the foregoing steps are all located within the range surrounded by the target contour line, the boundaries of the regular triangle mesh formed by these regular triangles should also be located within the range surrounded by the target contour line. The computer equipment can extract the corresponding regular triangle mesh boundary according to the finally formed regular triangle mesh.
And closing the section of the stone three-dimensional model based on the regular triangle mesh boundary and the target contour line.
In the embodiment of the present application, the polygon formed by the boundary of the regular triangle mesh and the object outline can be regarded as two independent non-intersecting coils. The computer equipment can seal the cross section of the stone three-dimensional model based on the regular triangle mesh boundary and the target contour line, so that a perfect sealed model cross section can be generated on the premise of avoiding generating a long and narrow triangle, and the sealed stone three-dimensional model can be obtained.
And finally, carrying out volume measurement and calculation based on the closed stone three-dimensional model to obtain the volume of the ship body stones.
The above description is only for the preferred embodiment of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present application should be covered within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (7)
1. A ship body stone volume measuring system based on three-dimensional reconstruction is characterized by comprising:
the acquisition module is used for acquiring three-dimensional point cloud data of the ship stones;
the processing module is connected with the acquisition module and used for performing three-dimensional reconstruction according to the three-dimensional point cloud data to obtain a three-dimensional point cloud picture;
the modeling module is connected with the processing module and used for constructing a three-dimensional stone model according to the three-dimensional point cloud picture and sealing the three-dimensional stone model to obtain a sealed three-dimensional stone model;
and the measuring module is connected with the modeling module and used for obtaining the volume of the stone based on the closed stone three-dimensional model.
2. The three-dimensional reconstruction based hull stone volume measuring system of claim 1,
the processing module comprises:
the preprocessing unit is used for carrying out noise reduction processing on the three-dimensional point cloud data by using mean filtering to obtain noise-reduced three-dimensional point cloud data;
and the three-dimensional reconstruction unit is used for performing three-dimensional reconstruction on the three-dimensional point cloud data subjected to noise reduction to obtain a three-dimensional point cloud picture.
3. The three-dimensional reconstruction based hull stone volume measuring system of claim 2,
the three-dimensional reconstruction unit includes:
the matching unit is used for carrying out stereo matching on the three-dimensional point cloud data subjected to noise reduction to obtain a disparity map;
and the drawing unit is used for obtaining a depth map according to the parallax map and drawing a three-dimensional point cloud map based on the depth map.
4. The three-dimensional reconstruction based hull stone volume measuring system of claim 1,
the processing module comprises:
the identification unit is used for marking the stone according to the profile and the type of the stone to generate marking information;
and the segmentation unit is used for segmenting the three-dimensional point cloud picture of the stone according to the three-dimensional point cloud picture and the marking information.
5. The three-dimensional reconstruction based hull stone volume measuring system of claim 1,
the modeling module includes:
the first modeling unit is used for constructing a first stone three-dimensional model based on the three-dimensional point cloud picture of the stone;
and the second modeling unit is used for carrying out closed processing on the first stone three-dimensional model to obtain a second stone three-dimensional model.
6. The three-dimensional reconstruction based hull stone volume measuring system according to claim 5,
the second modeling unit includes:
the sectioning unit is used for sectioning the first stone three-dimensional model to obtain an initial contour line;
the cutting unit is used for cutting off the convex area on the initial contour line to obtain a target contour line;
the interpolation unit is used for carrying out interpolation processing on the target contour line to obtain a regular triangle mesh boundary;
and the closing unit is used for closing the first stone three-dimensional model based on the target contour line and the regular triangle grid boundary to obtain a second stone three-dimensional model.
7. The ship hull stone volume measuring system based on three-dimensional reconstruction as claimed in claim 6,
the interpolation unit includes:
the generating unit is used for carrying out interpolation processing on the target contour line to obtain a plurality of regular triangle meshes;
and the extracting unit is used for extracting a plurality of regular triangle grids to obtain the boundaries of the regular triangle grids.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210776816.8A CN114963991A (en) | 2022-07-04 | 2022-07-04 | Hull stone volume measurement system based on three-dimensional reconstruction |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210776816.8A CN114963991A (en) | 2022-07-04 | 2022-07-04 | Hull stone volume measurement system based on three-dimensional reconstruction |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114963991A true CN114963991A (en) | 2022-08-30 |
Family
ID=82971620
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210776816.8A Withdrawn CN114963991A (en) | 2022-07-04 | 2022-07-04 | Hull stone volume measurement system based on three-dimensional reconstruction |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114963991A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115542337A (en) * | 2022-11-28 | 2022-12-30 | 成都维泰油气能源技术有限公司 | Drilling return rock debris monitoring method and device and storage medium |
-
2022
- 2022-07-04 CN CN202210776816.8A patent/CN114963991A/en not_active Withdrawn
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115542337A (en) * | 2022-11-28 | 2022-12-30 | 成都维泰油气能源技术有限公司 | Drilling return rock debris monitoring method and device and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109872397B (en) | Three-dimensional reconstruction method of airplane parts based on multi-view stereo vision | |
CN109655019B (en) | Cargo volume measurement method based on deep learning and three-dimensional reconstruction | |
Shen | Accurate multiple view 3d reconstruction using patch-based stereo for large-scale scenes | |
Xu et al. | Reconstruction of scaffolds from a photogrammetric point cloud of construction sites using a novel 3D local feature descriptor | |
US8270704B2 (en) | Method and apparatus for reconstructing 3D shape model of object by using multi-view image information | |
Rau et al. | Bridge crack detection using multi-rotary UAV and object-base image analysis | |
CN110473221B (en) | Automatic target object scanning system and method | |
JP4058293B2 (en) | Generation method of high-precision city model using laser scanner data and aerial photograph image, generation system of high-precision city model, and program for generation of high-precision city model | |
CN111951197B (en) | Point cloud segmentation method based on structured light | |
CN114187310A (en) | Large-scale point cloud segmentation method based on octree and PointNet ++ network | |
Yogeswaran et al. | 3d surface analysis for automated detection of deformations on automotive body panels | |
US11587299B2 (en) | Systems and methods for detection of anomalies in civil infrastructure using context aware semantic computer vision techniques | |
Oliveira et al. | Scene representations for autonomous driving: an approach based on polygonal primitives | |
Alidoost et al. | Y-shaped convolutional neural network for 3d roof elements extraction to reconstruct building models from a single aerial image | |
CN114963991A (en) | Hull stone volume measurement system based on three-dimensional reconstruction | |
CN109727255B (en) | Building three-dimensional model segmentation method | |
Böhm et al. | Model refinement by integrated processing of laser scanning and photogrammetry | |
Petrovai et al. | Obstacle detection using stereovision for Android-based mobile devices | |
Xu et al. | Deep learning guided building reconstruction from satellite imagery-derived point clouds | |
CN116863083A (en) | Method and device for processing three-dimensional point cloud data of transformer substation | |
Balado Frías et al. | Automatic detection and characterization of ground occlusions in urban point clouds from mobile laser scanning data | |
Madhavan et al. | A computer vision based approach for 3D building modelling of airborne laser scanner DSM data | |
Lv et al. | Semantically guided multi-view stereo for dense 3d road mapping | |
Lhuillier | Local-convexity reinforcement for scene reconstruction from sparse point clouds | |
Wolf et al. | Applicability of neural networks for image classification on object detection in mobile mapping 3d point clouds |
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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220830 |
|
WW01 | Invention patent application withdrawn after publication |