CN111354080A - Content-based three-dimensional reconstruction data supplementary acquisition method - Google Patents
Content-based three-dimensional reconstruction data supplementary acquisition method Download PDFInfo
- Publication number
- CN111354080A CN111354080A CN202010190506.9A CN202010190506A CN111354080A CN 111354080 A CN111354080 A CN 111354080A CN 202010190506 A CN202010190506 A CN 202010190506A CN 111354080 A CN111354080 A CN 111354080A
- Authority
- CN
- China
- Prior art keywords
- data
- acquisition
- dimensional reconstruction
- model
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 230000003287 optical effect Effects 0.000 claims abstract description 19
- 238000004364 calculation method Methods 0.000 claims abstract description 9
- 239000013589 supplement Substances 0.000 claims abstract description 7
- 230000000295 complement effect Effects 0.000 claims description 7
- 238000005516 engineering process Methods 0.000 claims description 6
- 238000005266 casting Methods 0.000 claims description 4
- 238000005070 sampling Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 238000006467 substitution reaction 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
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a three-dimensional reconstruction data supplement acquisition method based on content, which comprises the steps of uniformly acquiring data on a spherical surface around a reconstruction object; carrying out three-dimensional reconstruction on the acquired data to form a model, and obtaining the surface geometry and optical properties of the object; evaluating the quality of three-dimensional reconstruction, and judging the accuracy of data subjected to three-dimensional reconstruction and the part of an incomplete model; counting the three-dimensional space coordinates of the problematic data, and calculating the pose of the acquisition equipment needing to supplement the acquired data; and (4) generating supplementary acquisition data according to the calculated pose of the acquisition equipment, integrating the supplementary acquisition data into the data set acquired in the step one, and further performing three-dimensional reconstruction to obtain more complete and accurate object surface geometry and optical attributes thereof. The invention comprises the following steps: 1. the integrity and the correctness of the reconstruction model can be perfected and corrected, and the reconstruction quality is greatly improved. 2. The calculation is performed according to the attributes of the object, the shape and the optical attributes of the object are not limited, and the method has wider applicability.
Description
Technical Field
The invention relates to a content-based three-dimensional reconstruction data supplementary acquisition method, and belongs to the technical field of computer vision three-dimensional reconstruction.
Background
The three-dimensional reconstruction technology based on computer vision is an important method for acquiring the three-dimensional geometric profile and the surface optical property of a real object at present. Three-dimensional reconstruction techniques can be divided into two categories, namely active and passive methods. In the active method, a depth sensor with an active emission detection signal is used to acquire depth data of the sensor to the surface of an object, and then the depth data is used to construct the surface geometry of the object through numerical calculation. The passive method is to acquire an image of an object only through a camera, understand and calculate the image, and reconstruct the surface geometry or surface optical properties of the object. Such methods include monocular-based shadow-to-shape, texture-to-shape, etc. methods, as well as multi-ocular-based stereo vision methods. In order to reconstruct the object as accurately and completely as possible, while accurately estimating the surface optical properties, it is necessary to acquire data from as many viewing angles as possible. However, redundant acquired data can cause redundancy, the complexity of calculation is greatly improved, and the feasibility of three-dimensional reconstruction is reduced. Therefore, reasonable data acquisition becomes an important component of three-dimensional reconstruction of real-world objects.
There are two main types of data acquisition methods for three-dimensional reconstruction, where a single acquisition device captures data around the reconstructed object and multiple fixed devices distribute around the object and acquire data simultaneously. The acquisition scheme of multiple devices has high acquisition speed, but the structure and the data acquisition points of the acquisition scheme are fixed, so that the acquisition scheme is lack of flexibility, and meanwhile, the acquisition scheme has the disadvantages of complex structure, high manufacturing cost and low system stability. The acquisition speed of the acquisition scheme of the single equipment is low, but the structure is simple, the cost is low, and the flexibility is high. Due to the fact that three-dimensional reconstruction is dependent on collected data, high calculation complexity of an algorithm and complex variability of a reconstructed object, the positions of the collection points and the number of the collection points cannot be determined when the data are collected, and the three-dimensional reconstruction result usually has wrong numerical values and an incomplete object surface. Therefore, a method for complementary acquisition of three-dimensional reconstruction data based on content is urgently needed to solve the problem existing in the prior art.
In order to solve the technical problems, a new technical scheme is especially provided.
Disclosure of Invention
The invention aims to provide a content-based three-dimensional reconstruction data supplementary acquisition method to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme: a method for complementary acquisition of three-dimensional reconstruction data based on content, the method comprising the steps of:
uniformly collecting data on a spherical surface around a reconstructed object;
performing three-dimensional reconstruction on the acquired data to form a model, and obtaining the surface geometry and optical properties of the object;
evaluating the quality of three-dimensional reconstruction, and judging the accuracy of data for three-dimensional reconstruction and the part with an incomplete model;
counting the three-dimensional space coordinates of the problematic data, and calculating the pose of the acquisition equipment needing to supplement the acquired data;
and fifthly, generating supplementary acquisition data according to the pose of the acquisition equipment calculated in the fourth step, integrating the supplementary acquisition data into the data set acquired in the first step, and further performing three-dimensional reconstruction to acquire more complete and accurate object surface geometry and optical attributes thereof.
Preferably, in the second step, the existing three-dimensional reconstruction technology is utilized, and the data acquired in the first step are subjected to numerical calculation to reconstruct the surface geometry and the optical properties of the object.
Preferably, the method for determining the accuracy of the data in the third step comprises the following steps:
s1, subdividing the model and eliminating triangular patches with large areas;
s2, generating a depth map of the pose at each data acquisition point position according to a ray casting algorithm;
s3, sequentially projecting each vertex on the model to the position of each acquisition point, acquiring the depth value of the acquisition point, comparing the depth value with the corresponding position value in the depth map of the acquisition point, and if the absolute value of the difference is less than a given threshold value, determining that the point is visible at the acquisition point; otherwise, this point is invisible at the acquisition point, and the visibility of each point on the model at all the acquisition points is counted;
s4, calculating the coverage of each vertex on the model to the acquisition point visible for changing points, wherein if the coverage area is less than a given threshold value, the accuracy of the point data is low; otherwise, the reconstructed data for that point is deemed to be accurate.
Preferably, the method for determining the incomplete part of the model in the third step is to determine the incomplete part of the model by detecting the edge of the reconstructed model, counting the hole part, and determining the hole part as the missing part of the model.
Compared with the prior art, the invention has the beneficial effects that: 1. the integrity and the correctness of the reconstruction model can be perfected and corrected, and the reconstruction quality is greatly improved. 2. The calculation is performed according to the attributes of the object, the shape and the optical attributes of the object are not limited, and the method has wider applicability. 3. The supplementary acquisition method estimates the pose of the supplementary acquisition data, controls the acquisition equipment to automatically acquire the data without manual participation, improves the automation degree, and reduces the labor cost of complete and accurate three-dimensional reconstruction.
Drawings
FIG. 1 is a schematic diagram of a structure for uniformly acquiring data on a spherical surface around a reconstructed object through a railcar and an annular orbit matched with the railcar in the present invention.
Fig. 2 is an overall flow chart of the invention.
FIG. 3 is a flow chart of the present invention for assessing reconstruction quality.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to the attached drawings of the specification, the invention provides a technical scheme that: a method for complementary acquisition of three-dimensional reconstruction data based on content, the method comprising the steps of:
uniformly acquiring data on a spherical surface surrounding a reconstructed object on the spherical surface by surrounding the reconstructed object 3 through a rail car 1 and an annular rail 2 matched with the rail car 1, wherein the mechanical arm 6 is arranged on the rail car 1, and a camera 5 is arranged on the mechanical arm 4;
performing three-dimensional reconstruction on the acquired data to form a model, and obtaining the surface geometry and optical properties of the object;
evaluating the quality of three-dimensional reconstruction, and judging the accuracy of data for three-dimensional reconstruction and the part with an incomplete model;
counting the three-dimensional space coordinates of the problematic data, and calculating the pose of the acquisition equipment needing to supplement the acquired data;
and fifthly, generating supplementary acquisition data according to the pose of the acquisition equipment calculated in the fourth step, integrating the supplementary acquisition data into the data set acquired in the first step, and further performing three-dimensional reconstruction to acquire more complete and accurate object surface geometry and optical attributes thereof.
Preferably, in the second step, the existing three-dimensional reconstruction technology is utilized, and the data acquired in the first step are subjected to numerical calculation to reconstruct the surface geometry and the optical properties of the object.
Preferably, the method for determining the accuracy of the data in the third step comprises the following steps:
s1, subdividing the model and eliminating triangular patches with large areas;
s2, generating a depth map of the pose at each data acquisition point position according to a ray casting algorithm;
s3, sequentially projecting each vertex on the model to the position of each acquisition point, acquiring the depth value of the acquisition point, comparing the depth value with the corresponding position value in the depth map of the acquisition point, and if the absolute value of the difference is less than a given threshold value, determining that the point is visible at the acquisition point; otherwise, this point is invisible at the acquisition point, and the visibility of each point on the model at all the acquisition points is counted;
s4, calculating the coverage of each vertex on the model to the acquisition point visible for changing points, wherein if the coverage area is less than a given threshold value, the accuracy of the point data is low; otherwise, the reconstructed data for that point is deemed to be accurate.
Preferably, the method for determining the incomplete part of the model in the third step is to determine the incomplete part of the model by detecting the edge of the reconstructed model, counting the hole part, and determining the hole part as the missing part of the model.
When in use, the working process of the invention is as follows:
1. data is acquired uniformly over a spherical surface around the reconstructed object using a single device acquisition scheme.
Because of the diversity of the reconstructed object, the system uses the most common acquisition method, i.e., spherical uniform acquisition of data around the reconstructed object, before the object is not reconstructed, as shown in FIG. 1.
2. And carrying out three-dimensional reconstruction on the acquired data to obtain the surface geometry and the optical property of the object.
And performing numerical calculation on the data acquired in the first step by using the existing three-dimensional reconstruction technology, reconstructing the surface geometry and the optical properties of the object, and meanwhile, deriving the pose of the acquisition equipment at each acquisition point.
3. And evaluating the reconstruction quality, and judging the accuracy of the reconstruction data and the incomplete part of the model.
The evaluation of the reconstruction quality has two main aspects, namely the accuracy of data and the integrity of a model. The data accuracy judging method comprises the following steps:
a. and (5) subdividing the model to eliminate the triangular patch with larger area.
b. And generating a depth map at the position of the pose according to a ray-casting algorithm at the position of each data acquisition point.
c. For each vertex on the model, sequentially projecting the vertex to the position of each acquisition point to acquire the depth value of the acquisition point, comparing the depth value with the corresponding position value in the depth map of the acquisition point, and if the absolute value of the difference is smaller than a given threshold value, determining that the point is visible at the acquisition point; otherwise, this point is not visible at the acquisition point. The visibility of each point on the statistical model at all acquisition points.
d. For each vertex on the model, calculating the coverage condition of the acquisition point visible for changing the point, wherein if the coverage area is less than a given threshold value, the accuracy possibility of the point data is low; otherwise, the reconstructed data for that point is deemed to be accurate.
And a model integrity judgment method, wherein the surface of the model is continuously smooth under the general condition. And (4) counting the cavity part by detecting the edge of the reconstructed model, and determining the cavity part as the missing part of the model.
4. And (4) counting the three-dimensional space coordinates of the problematic data, and calculating the pose of the acquisition equipment needing to supplement the acquired data.
And according to the spatial positions of the inaccurate data part and the incomplete model part counted in the previous step, the poses of the sampling points are synthesized, and the poses of the sampling points needing to supplement the acquired data are calculated.
5. Supplementary acquisition data are generated by the position and posture of the acquisition equipment calculated in the last step, the supplementary acquisition data are integrated into the data set acquired in the first step, three-dimensional reconstruction is further carried out, and more complete and accurate object surface geometry and optical attributes thereof are obtained.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (4)
1. A method for complementary acquisition of three-dimensional reconstruction data based on content, the method comprising the steps of:
uniformly collecting data on a spherical surface around a reconstructed object;
performing three-dimensional reconstruction on the acquired data to form a model, and obtaining the surface geometry and optical properties of the object;
evaluating the quality of three-dimensional reconstruction, and judging the accuracy of data for three-dimensional reconstruction and the part with an incomplete model;
counting the three-dimensional space coordinates of the problematic data, and calculating the pose of the acquisition equipment needing to supplement the acquired data;
and fifthly, generating supplementary acquisition data according to the pose of the acquisition equipment calculated in the fourth step, integrating the supplementary acquisition data into the data set acquired in the first step, and further performing three-dimensional reconstruction to acquire more complete and accurate object surface geometry and optical attributes thereof.
2. The method for complementary acquisition of three-dimensional reconstruction data based on content according to claim 1, characterized in that: and step two, the existing three-dimensional reconstruction technology is utilized, the data acquired in the step one are subjected to numerical calculation, and the surface geometry and the optical properties of the object are reconstructed.
3. The method for complementary acquisition of three-dimensional reconstruction data based on content according to claim 1, characterized in that: the method for judging the accuracy of the data in the third step comprises the following steps:
s1, subdividing the model and eliminating triangular patches with large areas;
s2, generating a depth map of the pose at each data acquisition point position according to a ray casting algorithm;
s3, sequentially projecting each vertex on the model to the position of each acquisition point, acquiring the depth value of the acquisition point, comparing the depth value with the corresponding position value in the depth map of the acquisition point, and if the absolute value of the difference is less than a given threshold value, determining that the point is visible at the acquisition point; otherwise, this point is invisible at the acquisition point, and the visibility of each point on the model at all the acquisition points is counted;
s4, calculating the coverage of each vertex on the model to the acquisition point visible for changing points, wherein if the coverage area is less than a given threshold value, the accuracy of the point data is low; otherwise, the reconstructed data for that point is deemed to be accurate.
4. The method for complementary acquisition of three-dimensional reconstruction data based on content according to claim 1, characterized in that: and thirdly, judging the incomplete part of the model by detecting the edge of the reconstructed model, counting the cavity part and determining the cavity part as the missing part of the model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010190506.9A CN111354080A (en) | 2020-03-18 | 2020-03-18 | Content-based three-dimensional reconstruction data supplementary acquisition method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010190506.9A CN111354080A (en) | 2020-03-18 | 2020-03-18 | Content-based three-dimensional reconstruction data supplementary acquisition method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111354080A true CN111354080A (en) | 2020-06-30 |
Family
ID=71197537
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010190506.9A Pending CN111354080A (en) | 2020-03-18 | 2020-03-18 | Content-based three-dimensional reconstruction data supplementary acquisition method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111354080A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH03138784A (en) * | 1989-10-25 | 1991-06-13 | Hitachi Ltd | Reconstructing method and display method for three-dimensional model |
| CN108876908A (en) * | 2018-06-12 | 2018-11-23 | 哈尔滨工业大学 | It is a kind of based on the extraterrestrial target three-dimensional reconstruction appraisal procedure of reconstruction model integrity degree and application |
| CN110246186A (en) * | 2019-04-15 | 2019-09-17 | 深圳市易尚展示股份有限公司 | A kind of automatized three-dimensional colour imaging and measurement method |
| CN110243307A (en) * | 2019-04-15 | 2019-09-17 | 深圳市易尚展示股份有限公司 | A kind of automatized three-dimensional colour imaging and measuring system |
| CN110660125A (en) * | 2019-09-17 | 2020-01-07 | 仙居县恒信电力有限公司 | Three-dimensional modeling device for power distribution network system |
-
2020
- 2020-03-18 CN CN202010190506.9A patent/CN111354080A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH03138784A (en) * | 1989-10-25 | 1991-06-13 | Hitachi Ltd | Reconstructing method and display method for three-dimensional model |
| CN108876908A (en) * | 2018-06-12 | 2018-11-23 | 哈尔滨工业大学 | It is a kind of based on the extraterrestrial target three-dimensional reconstruction appraisal procedure of reconstruction model integrity degree and application |
| CN110246186A (en) * | 2019-04-15 | 2019-09-17 | 深圳市易尚展示股份有限公司 | A kind of automatized three-dimensional colour imaging and measurement method |
| CN110243307A (en) * | 2019-04-15 | 2019-09-17 | 深圳市易尚展示股份有限公司 | A kind of automatized three-dimensional colour imaging and measuring system |
| CN110660125A (en) * | 2019-09-17 | 2020-01-07 | 仙居县恒信电力有限公司 | Three-dimensional modeling device for power distribution network system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104713885B (en) | A kind of structure light for pcb board on-line checking aids in binocular measuring method | |
| CN109087274A (en) | Electronic device defect inspection method and device based on multidimensional fusion and semantic segmentation | |
| CN112085675B (en) | Depth image denoising method, foreground segmentation method and human motion monitoring method | |
| CN115077425B (en) | Product detection equipment and method based on structured light three-dimensional vision | |
| Belton et al. | Processing tree point clouds using Gaussian Mixture Models | |
| CN110598590A (en) | Close interaction human body posture estimation method and device based on multi-view camera | |
| CN107702663A (en) | A kind of point cloud registration method based on the rotation platform with index point | |
| CN115482195B (en) | Train part deformation detection method based on three-dimensional point cloud | |
| CN103884294B (en) | The method and its device of a kind of infrared light measuring three-dimensional morphology of wide visual field | |
| CN113298194A (en) | Data fusion method and system based on multiple sensors and storage medium | |
| CN116152697A (en) | Three-dimensional model measuring method and related device for concrete structure cracks | |
| CN102865814A (en) | Plant population three-dimensional reconstruction error measurement method | |
| CN117036944B (en) | Tree carbon sink amount calculating method and system based on point cloud data and image recognition | |
| CN110517323A (en) | 3 D positioning system and method based on manipulator one camera multi-vision visual | |
| CN111354080A (en) | Content-based three-dimensional reconstruction data supplementary acquisition method | |
| CN112687005A (en) | Coal pile volume measurement method based on three-dimensional reconstruction | |
| CN110728747A (en) | Vehicle three-dimensional outline drawing method based on laser point cloud data and OpenGL | |
| CN110363703A (en) | Shelf monitor method based on depth camera | |
| CN116051980A (en) | Building identification method, system, electronic equipment and medium based on oblique photography | |
| CN115100443A (en) | Cable defect identification method based on high-speed template matching calculation | |
| CN114898100A (en) | Point cloud data extraction method, device, system, equipment and storage medium | |
| CN107358655B (en) | Identification method of hemispherical surface and conical surface models based on discrete stationary wavelet transform | |
| CN114078186A (en) | Three-dimensional shape reconstruction simulation method based on infinite focus scanning | |
| CN115294181B (en) | Cow body type assessment index measurement method based on two-stage key point positioning | |
| CN111461029B (en) | Human body joint point data optimization system and method based on multi-view Kinect |
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 |