CN112686877B - Binocular camera-based three-dimensional house damage model construction and measurement method and system - Google Patents
Binocular camera-based three-dimensional house damage model construction and measurement method and system Download PDFInfo
- Publication number
- CN112686877B CN112686877B CN202110009707.9A CN202110009707A CN112686877B CN 112686877 B CN112686877 B CN 112686877B CN 202110009707 A CN202110009707 A CN 202110009707A CN 112686877 B CN112686877 B CN 112686877B
- Authority
- CN
- China
- Prior art keywords
- damage
- house
- dimensional
- binocular camera
- algorithm
- 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
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a binocular camera-based three-dimensional house damage model construction and measurement method and system, which utilize the binocular camera imaging parallax principle to obtain a house indoor plane image through scanning of a binocular camera, and calculate according to a binocular stereo matching algorithm to obtain a depth image; further obtaining the actual size information of each position and each component of the house structure, and realizing non-contact high-precision three-dimensional measurement and nondestructive detection on the house structure; then, a damage recognition and segmentation algorithm is adopted to segment the crack damage from the house indoor plane image of the left eye camera in the binocular camera; projecting the pixel points obtained by segmentation onto a depth map by adopting a 3D damage refinement and quantization algorithm, so as to obtain three-dimensional information of each point in the crack damage; and the 3D Convex hull Convex hull algorithm is used for calculating the three-dimensional volume of the crack damage, so that the actual data of the house damage can be directly obtained, and the rapid detection and safety evaluation after the disaster of the large-scale urban building group are facilitated.
Description
Technical Field
The invention relates to the technical field of house measurement.
Background
In daily use, due to accidental or potential events such as fire, earthquake and the like, the civil building often causes the conditions of cracks, steel bar corrosion, concrete falling and the like of the building, and the conditions can influence the normal use of the building and even endanger the safety of the building structure. The house quality monitoring means that a professional carries out daily inspection and measurement on the house structure quality by using a certain technical means and method, and regular monitoring is carried out. The house quality detection means that a professional detects and evaluates damage of a house and makes a quality report.
The current house quality monitoring and detecting contents mainly include structure settlement, inclination, cracks, material strength detection, house shock resistance detection and identification and the like, main technical equipment of the house quality monitoring and detecting method comprises a distance meter, a box ruler, a vernier caliper, a total station, a steel bar detector, a resiliometer and the like, and the detecting equipment and the detecting method are low in detecting precision, low in speed, high in cost and incapable of realizing long-time monitoring on one hand, and on the other hand, the whole detecting program is complex, the detecting result is usually determined by experience and is easily influenced by human factors. Therefore, how to accurately and quickly carry out daily monitoring and detection on the quality and the damage of the house, and quick detection and safety assessment after disasters of large-scale urban building groups become a problem to be solved urgently.
Disclosure of Invention
The invention aims to overcome the technical defects, provides a binocular camera-based three-dimensional house damage model construction and measurement method and system, and solves the problems that the existing house detection is low in precision, low in efficiency and complex in program, and large-scale building groups cannot be rapidly detected and safety evaluated.
In order to achieve the technical purpose, a first aspect of the technical scheme of the invention provides a binocular camera-based three-dimensional house damage model construction and measurement method, which comprises the following steps:
scanning by a binocular camera to obtain a house indoor plane image, and calculating according to a binocular stereo matching algorithm to obtain a depth image;
a damage identification and segmentation algorithm is adopted to segment the crack damage from the house indoor plane image of the left eye camera in the binocular camera;
projecting the pixel points obtained by segmentation onto a depth map by adopting a 3D damage refinement and quantization algorithm, so as to obtain three-dimensional information of each point in the crack damage;
and performing three-dimensional volume calculation on the fracture damage by using a 3D Convex hull Convex hull algorithm.
The invention provides a binocular camera-based three-dimensional house damage model construction and measurement system, which comprises the following functional modules:
the image acquisition and calculation module is used for obtaining an indoor plane image of the house through scanning of a binocular camera and calculating a depth image according to a binocular stereo matching algorithm;
the crack damage segmentation module is used for segmenting the crack damage from the house indoor plane image of the left-eye camera in the binocular camera by adopting a damage identification segmentation algorithm;
the depth projection module is used for projecting the pixel points obtained by segmentation onto a depth map by adopting a 3D damage refinement quantization algorithm, so that the three-dimensional information of each point in the crack damage can be obtained;
and the damage volume calculation module is used for performing three-dimensional volume calculation on the crack damage by using a 3D Convex hull Convex hull algorithm.
A third aspect of the present invention provides a server, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the binocular camera-based three-dimensional house damage model building and measuring method when executing the computer program.
A fourth aspect of the present invention provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the computer program implements the steps of the binocular camera-based three-dimensional house damage model construction measurement method.
Compared with the prior art, the method utilizes the binocular camera imaging parallax principle to calculate and obtain the depth map of the house, further obtain the actual size information of each position and each component of the house structure, realize non-contact high-precision three-dimensional measurement and nondestructive detection on the house structure, and has high detection efficiency; meanwhile, the crack damage is segmented from the house indoor plane image of the left eye camera in the binocular camera, the crack damage is projected to the 3D view from the 2D view, the three-dimensional volume of the crack damage is calculated by using a 3D Convex hull Convex hull algorithm, the actual data of the house damage can be directly obtained, and the rapid detection and safety evaluation after the large-scale urban building crowd is in disaster are facilitated.
Drawings
Fig. 1 is a flow chart of a binocular camera-based three-dimensional house damage model construction measurement method according to an embodiment of the present invention;
fig. 2 is a block diagram of a binocular camera-based three-dimensional house damage model construction measurement system according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.
As shown in fig. 1, an embodiment of the present invention provides a binocular camera-based three-dimensional house damage model construction and measurement method, which includes the following steps:
s1, scanning through a binocular camera to obtain an indoor plane image of the house, and calculating according to a binocular stereo matching algorithm to obtain a depth image.
Based on the house indoor plane image, an indoor three-dimensional reconstruction model is established by using a three-dimensional modeling module, all bearing components and non-bearing components are subjected to instance segmentation in three-dimensional point cloud data by using a point cloud instance segmentation algorithm, and different component types are segmented and positioned.
Specifically, internal parameter information of a camera in a binocular camera is obtained, and distortion correction is performed on an image obtained by the camera according to the internal parameter information of the camera; the camera coordinate system can be corrected through the IMU (inertial sensor), unknown rigid body transformation of the IMU and the camera can be obtained through calibrating the initial poses of the IMU and the camera, and real-time image stabilization can be better performed by utilizing IMU feedback data. And calibrating according to the three coordinate systems in the camera calibration process, and solving the relation between every two coordinate systems. Which are the image coordinate system, the camera coordinate system and the world coordinate system, respectively. And calibrating the camera by using a checkerboard calibration method, and solving internal parameters and external parameters of the camera. And taking the external parameters as coordinate values of data points acquired by the camera under a world coordinate system, and using the internal parameters for solving a homography matrix in an image stabilizing process to finish the calibration of the relative pose of the IMU-camera.
And then, scanning the indoor scene by 360 degrees through a binocular camera to obtain a house indoor plane image and point cloud data, filtering the point cloud data based on a Static Outer Removal (SOR) filter, constructing by using an RTAB-map robot mapping model of an SDK library to obtain an indoor three-dimensional reconstruction model, and measuring the actual size information of an indoor structural member in real time through the indoor three-dimensional reconstruction model to replace a contact type measuring method used in the existing house quality detection.
The method is characterized in that a pointent + + training network is adopted to identify bearing components and non-bearing components, and different components are respectively segmented and displayed in three-dimensional point cloud data through different colors, so that segmentation and positioning of different component types are realized.
In order to simulate the capturing of human eyes on a stereoscopic scene and the recognition capability of different scenes, a binocular stereo matching algorithm (SGBM algorithm) requires that two cameras are adopted to replace human eyes, and two images which are very close to each other are obtained to obtain the depth of field (parallax), so that the distances between different scenes and the cameras are calculated, and a depth of field image is obtained. The invention adopts a binocular camera to replace human eyes, namely when two cameras on the same horizontal line shoot, the same object is shot in the two cameras, the object has different coordinates relative to the center point of the cameras in the two cameras, xleft is the relative position of the object in the left camera, and Xright is the relative position of the object in the right camera. When two images are overlapped, the projection position of the P on the left video camera and the projection position of the P on the right video camera have a distance | Xleft | + | Xright |, the distance is called parallax error, based on the parallax error principle, the coordinate of a left eye camera in the binocular camera is used as an alignment coordinate, the depth z of the object P from the video camera can be obtained according to a similar triangle, and then a depth map is obtained. The calculation formula of the depth of field z is as follows:
z＝sf/d
wherein, S is the distance between two cameras, f is the focal length, and d is the parallax Disparity (| | Xleft | - | Xright |).
And S2, segmenting the crack damage from the house indoor plane image of the left eye camera in the binocular camera by adopting a damage identification segmentation algorithm.
Namely, the depth network Mask R-CNN is segmented from the house indoor plane image of the left eye camera in the binocular camera.
And S3, projecting the segmented pixel points to a depth map by adopting a 3D damage refinement quantization algorithm, and acquiring the three-dimensional information of each point in the crack damage.
Specifically, because the depth map and the coordinates of the left eye camera are aligned when the SGBM stereo matching is performed, the color of the left eye RGB can be added to each coordinate, and one point of the obtained point cloud is described as [ X, Y, Z, R, G, B ].
And representing the position of the forcibly occupied matrix by NAN (neighbor self-adaptive matching) to align the positions of the 2D image coordinate and the 3D point cloud coordinate. Such as point cloud data like severe reflections, infinity, etc., which is actually noise.
The basis of the alignment of the 2D image coordinate and the 3D point cloud coordinate is that a disparity map is formed by selecting the disparity of each pixel point, a global energy function related to the disparity map is set, the energy function is minimized, and the purpose of solving the optimal disparity of each pixel is achieved, wherein the function expression is as follows:
wherein D represents a disparity map, and E (D) represents an energy function corresponding to the disparity map; p, q represents a certain pixel in the image; n is a radical of hydrogen p The neighboring pixel points (typically 8 connected) of the representative pixel p; c (p, D) p ) Indicates that the parallax of the current pixel point is D p Then, cost of the pixel point; p is a radical of formula 1 Is a penalty coefficient, which is applied to those pixels whose disparity values are different from the disparity value of p by 1 in the neighboring pixels of the pixel p; p is a radical of 2 A penalty factor is applied to the pixels with the disparity value of p different from that of p by more than 1 in the adjacent pixels of the pixel p; i.]Indicating that the function returns a1 if the parameter in the function is true, otherwise returns a 0.
After projection, static Outer Remove (SOR) filter is used for filtering point cloud data, and therefore damage identification and segmentation in the 3D point cloud are completed.
In addition, the multidimensional size information can be accurately obtained by projecting the coordinate alignment to the 3D point cloud, and because each point cloud has actual spatial coordinates (x, y, z), the length, width and height of the damage can be calculated by calculating the distance between two point clouds, for example, the distance D between the point cloud A1 (x 1, y1, z 1) and the point cloud A2 (x 2, y2, z 2) can be calculated by the following formula:
and S4, performing three-dimensional volume calculation on the fracture damage by using a 3D Convex hull Convex hull algorithm.
Before the three-dimensional volume calculation is carried out on the crack damage by using a 3D Convex hull Convex hull algorithm, interpolation is carried out on the extracted point cloud, the point cloud density is added, and downsampling and voxelization are carried out to simulate the geometrical form of the point cloud.
In the binocular scanning process, point clouds in some areas are not scanned or are polluted by noise, some noise points are deleted after denoising, and lack of enough points can cause inaccuracy of volume calculation of the 3D covex hull in the later period, so that interpolation is performed between two adjacent points by using an interpolation method to add the point clouds;
compared with a projection or voxel segmentation method for processing point clouds, the method for directly extracting the characteristics of the point clouds can better keep three-dimensional structure information, but due to the disorder of the point clouds, a direct processing method needs higher calculation cost when neighborhood is searched. Therefore, the point cloud is downsampled, the operation of all point clouds is converted to key points obtained by downsampling, and the calculated amount is reduced; specifically, a three-dimensional voxel grid is constructed by using FPS (fast point sampling), and then other points in the voxel are approximately displayed by using the gravity centers of all points in the voxel in each voxel, so that all points in the voxel are represented by using one gravity center point, and the filtering effect is achieved, and the data volume is greatly reduced.
The point cloud is converted into a three-dimensional voxel grid because the down-sampling is to construct the three-dimensional voxel grid, each point in the point cloud data has a voxel corresponding to the point cloud data in a three-dimensional space, and the voxelization of the point cloud data can be realized only by attaching a voxel label to each point.
Calculating the point cloud geometrical shape of the crack damage by using a 3D Convex hull Convex hull algorithm to obtain the three-dimensional volume of the crack damage, wherein the calculation formula is as follows:
in the formula, P represents a set of points in a real vector space; alpha represents the number of convex edges; n represents the number of dots.
According to the binocular camera-based three-dimensional house damage model construction and measurement method, the binocular camera imaging parallax principle is utilized, the depth map of a house is obtained through calculation, further, the actual size information of each position and each component of the house structure is obtained, non-contact high-precision three-dimensional measurement and nondestructive detection of the house structure are achieved, and the detection efficiency is high; meanwhile, crack damage is segmented from the house indoor plane image of the left-eye camera in the binocular camera, the crack damage is projected to the 3D view from the 2D view, the three-dimensional volume of the crack damage is calculated by using a 3D Convex hull Convex hull algorithm, and actual data of the house damage can be directly obtained, so that rapid detection and safety evaluation after a large-scale urban building group is in danger are facilitated.
As shown in fig. 2, the embodiment of the invention also discloses a binocular camera-based three-dimensional house damage model construction and measurement system, which comprises the following functional modules:
the image acquisition and calculation module 10 is used for obtaining a house indoor plane image through binocular camera scanning and calculating to obtain a depth image according to a binocular stereo matching algorithm;
the crack damage segmentation module 20 is used for segmenting the crack damage from the house indoor plane image of the left-eye camera in the binocular camera by adopting a damage identification segmentation algorithm;
the depth projection module 30 is configured to project the segmented pixel points onto a depth map by using a 3D damage refinement quantization algorithm, so that three-dimensional information of each point in the crack damage can be obtained;
and the damage volume calculation module 40 is used for performing three-dimensional volume calculation on the crack damage by using a 3D Convex hull Convex hull algorithm.
The execution mode of the binocular camera-based three-dimensional house damage model building and measuring system in this embodiment is basically the same as that of the binocular camera-based three-dimensional house damage model building and measuring method, and therefore, detailed description is omitted.
The server in this embodiment is a device for providing computing services, and generally refers to a computer with high computing power, which is provided to a plurality of consumers via a network. The server of this embodiment includes: a memory including an executable program stored thereon, a processor, and a system bus, it will be understood by those skilled in the art that the terminal device structure of the present embodiment does not constitute a limitation of the terminal device, and may include more or less components than those shown, or some components in combination, or a different arrangement of components.
The memory may be used to store software programs and modules, and the processor may execute various functional applications of the terminal and data processing by operating the software programs and modules stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the terminal, etc. Further, the memory may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.
The method comprises the steps of storing a executable program of a binocular camera-based three-dimensional house damage model building and measuring method on a memory, wherein the executable program can be divided into one or more modules/units, the one or more modules/units are stored in the memory and are executed by a processor to complete information acquisition and implementation processes, and the one or more modules/units can be a series of computer program instruction segments capable of completing specific functions and are used for describing the execution process of the computer program in the server. For example, the computer program may be segmented into an image acquisition computation module, a fracture damage segmentation module, a depth projection module, a damage volume computation module.
The processor is a control center of the server, connects various parts of the whole terminal equipment by various interfaces and lines, and executes various functions of the terminal and processes data by running or executing software programs and/or modules stored in the memory and calling data stored in the memory, thereby performing overall monitoring of the terminal. Alternatively, the processor may include one or more processing units; preferably, the processor may integrate an application processor, which mainly handles operating systems, application programs, etc., and a modem processor, which mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor.
The system bus is used to connect functional units in the computer, and can transmit data information, address information and control information, and the types of the functional units can be PCI bus, ISA bus, VESA bus, etc. The system bus is responsible for data and instruction interaction between the processor and the memory. Of course, the system bus may also access other devices such as network interfaces, display devices, etc.
The server at least includes a CPU, a chipset, a memory, a disk system, and the like, and other components are not described herein again.
In the embodiment of the present invention, the executable program executed by the processor included in the terminal specifically includes: a binocular camera-based three-dimensional house damage model construction and measurement method comprises the following steps:
scanning by a binocular camera to obtain a house indoor plane image, and calculating according to a binocular stereo matching algorithm to obtain a depth image;
a damage identification and segmentation algorithm is adopted to segment the crack damage from the house indoor plane image of the left eye camera in the binocular camera;
projecting the pixel points obtained by segmentation onto a depth map by adopting a 3D damage refinement and quantization algorithm, so as to obtain three-dimensional information of each point in the crack damage;
and performing three-dimensional volume calculation on the fracture damage by using a 3D Convex hull Convex hull algorithm.
It can be clearly understood by those skilled in the art that, for convenience and simplicity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the description of each embodiment has its own emphasis, and reference may be made to the related description of other embodiments for parts that are not described or recited in any embodiment.
Those of ordinary skill in the art would appreciate that the modules, elements, and/or method steps of the various embodiments described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; although the present 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 solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (7)
1. A binocular camera-based three-dimensional house damage model construction and measurement method is characterized by comprising the following steps:
scanning by a binocular camera to obtain an indoor plane image of the house, and calculating according to a binocular stereo matching algorithm to obtain a depth image;
dividing crack damage from the house indoor plane image of the left eye camera in the binocular cameras by adopting a damage identification and division algorithm;
projecting the pixel points obtained by segmentation onto a depth map by adopting a 3D damage refinement quantization algorithm, so as to obtain three-dimensional information of each point in the crack damage;
performing three-dimensional volume calculation on the crack damage by using a 3D Convex hull Convex hull algorithm;
calculating the point cloud cluster of the crack damage by using a 3D Convex hull Convex hull algorithm, wherein the calculation formula is as follows:
in the formula, P represents a point set in a real vector space; alpha represents the number of convex edges; n represents the number of points;
before the fracture damage is segmented from the house indoor plane image of the left eye camera in the binocular camera by adopting the damage identification segmentation algorithm, the binocular camera-based three-dimensional house damage model construction and measurement method further comprises the following steps:
based on the house indoor plane image, an indoor three-dimensional reconstruction model is established by using a three-dimensional modeling module, all bearing components and non-bearing components are subjected to instance segmentation in three-dimensional point cloud data by using a point cloud instance segmentation algorithm, and different component types are segmented and positioned.
2. The binocular camera based three-dimensional house damage model construction and measurement method of claim 1, wherein point cloud data filtering needs to be performed on an indoor plane image of a house before an indoor three-dimensional reconstruction model is established.
3. The binocular camera based three-dimensional house damage model building and measuring method according to claim 1, wherein the depth image is a house indoor plane image based on a left eye camera in a binocular camera, and is obtained through calculation by combining a binocular stereo matching algorithm.
4. The binocular camera-based three-dimensional house damage model building and measuring method of claim 1, wherein the 3D damage refinement and quantization algorithm is adopted to project the segmented pixel points onto the depth map, specifically:
and forcibly calculating a 1080x720 six-channel point cloud from the 1080x720 three-channel image by adopting a 3D damage refinement quantization algorithm, wherein the point cloud coordinates which cannot be calculated represent the positions of the matrix occupied by the forced images by NAN, so that the positions of the 2D image coordinates and the 3D point cloud coordinates are aligned.
5. The binocular camera based three-dimensional house damage model building and measuring method of claim 1, wherein before performing three-dimensional volume calculation on crack damage by using a 3D Convex hull Convex hull algorithm, interpolation is required to be performed on the extracted point cloud, point cloud density is added, and downsampling and voxelization are performed to simulate the geometrical shape of the point cloud.
6. A server comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor when executing the computer program implements the steps of the binocular camera based three-dimensional house damage model construction measurement method according to any one of claims 1 to 5.
7. A computer-readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the steps of the binocular camera based three-dimensional house damage model construction measurement method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110009707.9A CN112686877B (en) | 2021-01-05 | 2021-01-05 | Binocular camera-based three-dimensional house damage model construction and measurement method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110009707.9A CN112686877B (en) | 2021-01-05 | 2021-01-05 | Binocular camera-based three-dimensional house damage model construction and measurement method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112686877A CN112686877A (en) | 2021-04-20 |
| CN112686877B true CN112686877B (en) | 2022-11-11 |
Family
ID=75457398
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110009707.9A Active CN112686877B (en) | 2021-01-05 | 2021-01-05 | Binocular camera-based three-dimensional house damage model construction and measurement method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112686877B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113469652A (en) * | 2021-06-30 | 2021-10-01 | 上海市建筑科学研究院有限公司 | Existing building damage recording system based on cloud platform |
| CN113870326B (en) * | 2021-09-01 | 2023-11-28 | 浙江大学 | Structural damage mapping, quantifying and visualizing method based on image and three-dimensional point cloud registration |
| CN114596313B (en) * | 2022-05-09 | 2022-10-04 | 深圳大学 | Building component damage detection method based on indoor point cloud and related equipment |
| CN115880243B (en) * | 2022-12-02 | 2023-07-07 | 广东机电职业技术学院 | Rail surface damage detection method, system and medium based on 3D point cloud segmentation |
| CN115597551B (en) * | 2022-12-14 | 2023-04-07 | 成都量芯集成科技有限公司 | Handheld laser-assisted binocular scanning device and method |
| CN116109954B (en) * | 2023-04-04 | 2023-07-04 | 深圳市城市公共安全技术研究院有限公司 | House potential safety hazard identification method, device and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101147685A (en) * | 1999-11-18 | 2008-03-26 | 罗切斯特大学 | Apparatus and method for cone beam volume computed tomography mammography |
| CN103983228A (en) * | 2014-06-04 | 2014-08-13 | 长江工程地球物理勘测武汉有限公司 | Method for measuring borehole fracture attitude by use of electronic rock core |
| CN104792804A (en) * | 2015-03-27 | 2015-07-22 | 江苏大学 | Method for diagnosing internal damage of cereal grains based on micro-CT (computed tomography) technology |
| CN106023226A (en) * | 2016-05-31 | 2016-10-12 | 彭博 | Crack automatic detection method based on three-dimensional virtual pavement |
| CN106791773A (en) * | 2016-12-30 | 2017-05-31 | 浙江工业大学 | A kind of novel view synthesis method based on depth image |
| CN107179322A (en) * | 2017-06-15 | 2017-09-19 | 长安大学 | A kind of bridge bottom crack detection method based on binocular vision |
| CN109242855A (en) * | 2018-07-19 | 2019-01-18 | 中国科学院自动化研究所 | Roof dividing method, system and equipment based on Three-dimensional Multi-resolution statistical information |
| CN110349251A (en) * | 2019-06-28 | 2019-10-18 | 深圳数位传媒科技有限公司 | A kind of three-dimensional rebuilding method and device based on binocular camera |
| CN111537610A (en) * | 2020-05-15 | 2020-08-14 | 华东理工大学 | Sensor array optimization method for damage positioning of metal bent plate |
| CN112102491A (en) * | 2020-08-12 | 2020-12-18 | 西安交通大学 | Skin damage surface three-dimensional reconstruction method based on surface structured light |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016197006A1 (en) * | 2015-06-04 | 2016-12-08 | Eoplex Limited | Solid state battery and fabrication process therefor |
-
2021
- 2021-01-05 CN CN202110009707.9A patent/CN112686877B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101147685A (en) * | 1999-11-18 | 2008-03-26 | 罗切斯特大学 | Apparatus and method for cone beam volume computed tomography mammography |
| CN103983228A (en) * | 2014-06-04 | 2014-08-13 | 长江工程地球物理勘测武汉有限公司 | Method for measuring borehole fracture attitude by use of electronic rock core |
| CN104792804A (en) * | 2015-03-27 | 2015-07-22 | 江苏大学 | Method for diagnosing internal damage of cereal grains based on micro-CT (computed tomography) technology |
| CN106023226A (en) * | 2016-05-31 | 2016-10-12 | 彭博 | Crack automatic detection method based on three-dimensional virtual pavement |
| CN106791773A (en) * | 2016-12-30 | 2017-05-31 | 浙江工业大学 | A kind of novel view synthesis method based on depth image |
| CN107179322A (en) * | 2017-06-15 | 2017-09-19 | 长安大学 | A kind of bridge bottom crack detection method based on binocular vision |
| CN109242855A (en) * | 2018-07-19 | 2019-01-18 | 中国科学院自动化研究所 | Roof dividing method, system and equipment based on Three-dimensional Multi-resolution statistical information |
| CN110349251A (en) * | 2019-06-28 | 2019-10-18 | 深圳数位传媒科技有限公司 | A kind of three-dimensional rebuilding method and device based on binocular camera |
| CN111537610A (en) * | 2020-05-15 | 2020-08-14 | 华东理工大学 | Sensor array optimization method for damage positioning of metal bent plate |
| CN112102491A (en) * | 2020-08-12 | 2020-12-18 | 西安交通大学 | Skin damage surface three-dimensional reconstruction method based on surface structured light |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112686877A (en) | 2021-04-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112686877B (en) | Binocular camera-based three-dimensional house damage model construction and measurement method and system | |
| CN108986161B (en) | Three-dimensional space coordinate estimation method, device, terminal and storage medium | |
| CN110568447B (en) | Visual positioning method, device and computer readable medium | |
| US11521311B1 (en) | Collaborative disparity decomposition | |
| US10068344B2 (en) | Method and system for 3D capture based on structure from motion with simplified pose detection | |
| Golparvar-Fard et al. | Evaluation of image-based modeling and laser scanning accuracy for emerging automated performance monitoring techniques | |
| CN108898676B (en) | Method and system for detecting collision and shielding between virtual and real objects | |
| EP1596330B1 (en) | Estimating position and orientation of markers in digital images | |
| CN108694741B (en) | Three-dimensional reconstruction method and device | |
| JP6760957B2 (en) | 3D modeling method and equipment | |
| US20100204964A1 (en) | Lidar-assisted multi-image matching for 3-d model and sensor pose refinement | |
| US8155387B2 (en) | Method and system for position determination using image deformation | |
| JP2014112055A (en) | Estimation method for camera attitude and estimation system for camera attitude | |
| EP3633606B1 (en) | Information processing device, information processing method, and program | |
| CN112880687A (en) | Indoor positioning method, device, equipment and computer readable storage medium | |
| US20170038212A1 (en) | Automatic connection of images using visual features | |
| CN111582022A (en) | Fusion method and system of mobile video and geographic scene and electronic equipment | |
| KR20160117143A (en) | Method, device and system for generating an indoor two dimensional plan view image | |
| CN113361365A (en) | Positioning method and device, equipment and storage medium | |
| CN115830135A (en) | Image processing method and device and electronic equipment | |
| US8340399B2 (en) | Method for determining a depth map from images, device for determining a depth map | |
| CN111105467A (en) | Image calibration method and device and electronic equipment | |
| CN110766731A (en) | Method and device for automatically registering panoramic image and point cloud and storage medium | |
| CN114066999A (en) | Target positioning system and method based on three-dimensional modeling | |
| CN113034347A (en) | Oblique photographic image processing method, device, processing equipment and 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 |