CN118134986B - Sparse time sequence-based complex ice-shaped three-dimensional reconstruction method, system and medium - Google Patents
Sparse time sequence-based complex ice-shaped three-dimensional reconstruction method, system and medium Download PDFInfo
- Publication number
- CN118134986B CN118134986B CN202410558455.9A CN202410558455A CN118134986B CN 118134986 B CN118134986 B CN 118134986B CN 202410558455 A CN202410558455 A CN 202410558455A CN 118134986 B CN118134986 B CN 118134986B
- Authority
- CN
- China
- Prior art keywords
- point
- ice
- dimensional
- points
- edge
- 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
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000012545 processing Methods 0.000 claims abstract description 9
- 238000000605 extraction Methods 0.000 claims abstract description 5
- 230000000007 visual effect Effects 0.000 claims abstract description 3
- 238000005259 measurement Methods 0.000 abstract description 14
- 230000000903 blocking effect Effects 0.000 abstract 1
- 230000006870 function Effects 0.000 description 5
- 230000015572 biosynthetic process Effects 0.000 description 3
- 238000004590 computer program Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 241000238557 Decapoda Species 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 102100028717 Cytosolic 5'-nucleotidase 3A Human genes 0.000 description 1
- 241000282326 Felis catus Species 0.000 description 1
- 241000219745 Lupinus Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000011229 interlayer Substances 0.000 description 1
- 239000010410 layer Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Abstract
The invention relates to a complex ice-shaped three-dimensional reconstruction method, a system and a medium based on sparse time sequence, wherein the method comprises the following steps: carrying out image processing and three-dimensional reconstruction on the obtained ice-shaped image at any moment to obtain three-dimensional point cloud data; based on the three-dimensional point cloud data at any moment, carrying out edge extraction to obtain edge points; setting a vertical line passing through any edge point, wherein the vertical line is parallel to a central axis of a visual field of an image acquisition device for acquiring ice-shaped images, and identifying an intersection point of the vertical line and three-dimensional point cloud data; and identifying whether the any edge point and the intersection point corresponding to the edge point are layering points or not based on the any edge point and the intersection point corresponding to the edge point, and obtaining the reconstructed three-dimensional ice shape. The reconstructed three-dimensional ice shape comprises the blocked layered points, and the blocked area on the back of the icing unit can be obtained, so that the problem of poor measurement precision of the complex ice shape due to mutual blocking among the icing units under the condition of sparse time sequence three-dimensional point cloud is effectively solved.
Description
Technical Field
The invention relates to the field of complex ice-shape three-dimensional reconstruction, in particular to a complex ice-shape three-dimensional reconstruction method, system and medium based on sparse time sequence.
Background
In the growth and evolution process of complex icing (such as shrimp tail ice, bei Kebing and pinnate ice), complex space structures which are mutually shielded can be gradually formed among icing units. When the three-dimensional ice shape on-line measurement is performed, only the three-dimensional measurement of the appearance of the frozen outer surface can be realized due to the limitation of the imaging view angle, and the measurement cannot be performed on the back surface of the frozen unit with a complex space structure (please refer to the feathered ice in fig. 1, the back surface of the frozen unit is shielded (the area indicated by the dotted circle in fig. 1)), and the shielded frozen area (please refer to the back surface of the shell ice frozen unit in fig. 2 and the shielded area thereof (the area indicated by the dotted circle in fig. 2)).
Referring to fig. 2, it can be seen from the spatial structure of the shell ice that there are many inter-layer edge openings due to the complex spatial shielding of the shell cat ice.
However, high-fidelity three-dimensional ice shape is an important premise for developing research on ice formation growth evolution mechanism, so that how to obtain three-dimensional ice formation of complex ice shapes with mutual shielding based on online measurement is a problem to be solved urgently.
Disclosure of Invention
The application aims to solve the technical problem of providing a complex ice-shape three-dimensional reconstruction method, a system and a medium based on sparse time sequence, which are characterized in that the method, the system and the medium can be suitable for obtaining complex ice-shape three-dimensional ice with mutual shielding under the sparse time sequence condition through online measurement.
In a first aspect, in one embodiment, a method for reconstructing a complex ice shape three-dimensional based on sparse time sequence is provided, including:
Acquiring an ice-shaped image at any time;
Carrying out image processing and three-dimensional reconstruction on the obtained ice-shaped image at any moment to obtain three-dimensional point cloud data at any moment;
Based on the three-dimensional point cloud data at any moment, carrying out edge extraction to obtain edge points;
Setting a vertical line passing through any one edge point based on the obtained edge point, wherein the vertical line is parallel to a central axis of a view field of an image acquisition device for acquiring the ice-shaped image, and identifying an intersection point of the vertical line and three-dimensional point cloud data;
Identifying whether the arbitrary edge point and the intersection point corresponding to the arbitrary edge point are layering points or not based on the arbitrary edge point and the intersection point corresponding to the arbitrary edge point;
And obtaining the reconstructed three-dimensional ice shape based on the identified layering points.
In one embodiment, the setting a vertical line passing through any one of the obtained edge points, the vertical line being parallel to a central axis of a field of view of an image acquisition device for acquiring an ice image, and identifying an intersection point of the vertical line and three-dimensional point cloud data includes:
Based on any one obtained edge point p i, setting a vertical line L passing through any one edge point p i, wherein the vertical line L is parallel to a central axis of a view field of an image acquisition device for acquiring ice-shaped images, and identifying an intersection point Q of the vertical line L and three-dimensional point cloud data; wherein i represents the index of the edge points, i is more than or equal to 1 and less than or equal to n, and n represents the total number of the edge points; the method for identifying the intersection point Q of the perpendicular L and the three-dimensional point cloud data comprises the following steps:
Points with a distance from the perpendicular L smaller than or equal to a preset first distance threshold value in the three-dimensional point cloud data are identified, and the points are identified as intersection points.
In one embodiment, the identifying whether the arbitrary edge point and the intersection point corresponding to the arbitrary edge point are hierarchical points based on the arbitrary edge point and the intersection point corresponding to the arbitrary edge point includes:
And calculating the distance between any one edge point and the corresponding intersection point, and if the distance is greater than or equal to a preset second distance threshold value, identifying the any one edge point and the corresponding intersection point as a layering point.
In one embodiment, the three-dimensional point cloud data does not include ice-shaped surface point cloud data of an aircraft, and the identifying whether the arbitrary edge point and the intersection point corresponding to the arbitrary edge point are layered points based on the arbitrary edge point and the intersection point corresponding to the arbitrary edge point includes:
And if the number of the intersection points corresponding to any one edge point is 0, identifying the any one edge point as a layering point.
In one embodiment, the identifying whether the arbitrary edge point and the intersection point corresponding to the arbitrary edge point are hierarchical points based on the arbitrary edge point and the intersection point corresponding to the arbitrary edge point includes:
If the number of the intersection points corresponding to any one edge point is at least two, identifying the intersection point closest to the any one edge point, calculating the distance between the any one edge point and the closest intersection point, and if the distance is greater than or equal to a preset second distance threshold value, identifying the any one edge point and all the intersection points corresponding to the any one edge point as layering points.
In one embodiment, the obtaining the reconstructed three-dimensional ice shape based on the identified layering points includes:
and for the three-dimensional ice shape at any time, obtaining the reconstructed three-dimensional ice shape based on the three-dimensional point cloud data at any time and the layering points obtained by identifying all the times before any time.
In a second aspect, in one embodiment, there is provided a complex ice-shape three-dimensional reconstruction system based on sparse timing, including:
The image acquisition device is used for acquiring ice-shaped images at any moment;
the first processor is used for carrying out image processing and three-dimensional reconstruction on the obtained ice-shaped image at any moment to obtain three-dimensional point cloud data at any moment;
The second processor is used for setting a vertical line passing through any one of the obtained edge points based on the any one of the obtained edge points, wherein the vertical line is parallel to a central axis of a visual field of an image acquisition device for acquiring the ice-shaped image, and identifying an intersection point of the vertical line and three-dimensional point cloud data;
a third processor, configured to identify, based on the arbitrary edge point and the intersection point corresponding to the arbitrary edge point, whether the arbitrary edge point and the intersection point corresponding to the arbitrary edge point are hierarchical points;
and a fourth processor for obtaining a reconstructed three-dimensional ice shape based on the identified layered points.
In one embodiment, any two or more of the first processor, the second processor, the third processor, and the fourth processor are the same processor.
In one embodiment, any one or more of the first processor, the second processor, and the fourth processor is an image processor.
In a third aspect, an embodiment provides a computer readable storage medium, where a program is stored, where the program can be loaded by a processor and executed the complex ice-shape three-dimensional reconstruction method described in any one of the embodiments above.
The beneficial effects of the invention are as follows:
Because the reconstructed three-dimensional ice shape comprises the blocked layering points, the blocked area on the back of the icing unit can be obtained. Therefore, high-fidelity reconstruction of the complex ice shape can be realized, the problem of poor measurement precision of the complex ice shape due to mutual shielding among icing units under the condition of sparse time sequence three-dimensional point cloud is effectively solved, and the measurement precision of the complex icing ice shape with mutual shielding is improved.
Drawings
FIG. 1 is a schematic view of a feathered ice configuration of one embodiment;
FIG. 2 is a schematic illustration of a shell ice shape configuration of an embodiment;
FIG. 3 is a schematic flow diagram of a method for three-dimensional reconstruction of a complex ice shape according to an embodiment of the present application;
FIG. 4 is a schematic view of an edge point of an ice formation at any one time t in one embodiment of the present application;
FIG. 5 is a schematic diagram of an embodiment of the present application for obtaining an intersection based on any one edge point in the frozen ice shape at any one time t;
FIG. 6 is a block diagram of a complex ice-shape three-dimensional reconstruction system according to one embodiment of the present application.
In the figure, 01 denotes an image acquisition device, 02 denotes a first processor, 03 denotes a second processor, 04 denotes a third processor, 05 denotes a fourth processor, 06 denotes an icing ice shape at time t-1, 07 denotes an icing ice shape at time t, 08 denotes a cliff edge point, and 09 denotes an aircraft surface.
Detailed Description
The application will be described in further detail below with reference to the drawings by means of specific embodiments. Wherein like elements in different embodiments are numbered alike in association. In the following embodiments, numerous specific details are set forth in order to provide a better understanding of the present application. However, one skilled in the art will readily recognize that some of the features may be omitted, or replaced by other elements, materials, or methods in different situations. In some instances, related operations of the present application have not been shown or described in the specification in order to avoid obscuring the core portions of the present application, and may be unnecessary to persons skilled in the art from a detailed description of the related operations, which may be presented in the description and general knowledge of one skilled in the art.
Furthermore, the described features, operations, or characteristics of the description may be combined in any suitable manner in various embodiments. Also, various steps or acts in the method descriptions may be interchanged or modified in a manner apparent to those of ordinary skill in the art. Thus, the various orders in the description and drawings are for clarity of description of only certain embodiments, and are not meant to be required orders unless otherwise indicated.
The numbering of the components itself, e.g. "first", "second", etc., is used herein merely to distinguish between the described objects and does not have any sequential or technical meaning.
In order to facilitate the explanation of the inventive concept of the present application, a brief explanation of the three-dimensional ice-shape reconstruction technique is provided below.
At present, there are many methods for three-dimensional ice reconstruction, but how to realize high-fidelity three-dimensional reconstruction of complex ice shapes (such as shrimp tail ice, bei Kebing and lupin ice) is a problem to be solved urgently.
In the ice growth process, if the ice growth is slower, the online measurement time interval can be longer, for example, 3 minutes, 5 minutes and 10 minutes are used for collecting the growth data once, so that the situation that the time interval is greater than or equal to 1 minute can be used as a sparse time sequence.
However, the applicant found in the study that for a three-dimensional point cloud with sparse timing with low time resolution (longer on-line measurement time interval of ice shape), a dense timing point cloud stacking method cannot be used for three-dimensional ice shape reconstruction due to difficulty in determining radius and number threshold of filter balls.
In view of the above, the application provides a method, a system and a medium for three-dimensional reconstruction of a complex ice shape based on sparse time sequence, which are based on three-dimensional point clouds at different moments, and the method and the system identify whether the edge point and other points are layered points or not through extracting the edge points, so that the corresponding three-dimensional ice shape is obtained based on the layered points obtained by the three-dimensional point clouds at different moments. The problem of poor measurement accuracy of complex ice shapes caused by mutual shielding among icing units under the condition of sparse time sequence three-dimensional point cloud is effectively solved, and the measurement accuracy of complex icing of the mutual shielding is improved.
Referring to fig. 3, a method for reconstructing a complex ice shape based on sparse time sequence according to an embodiment of the present application includes:
step S10, acquiring an ice-shaped image at any time.
Based on the image acquisition device, acquiring a real-time ice image in the ice growth process. For three-dimensional ice shapes with slower ice shape growth, the three-dimensional ice shapes can be obtained every 3 minutes, 5 minutes or 10 minutes, and the three-dimensional ice shapes are specifically set according to actual requirements. To obtain a high definition image, in one embodiment, a high definition industrial CCD camera may be used for image acquisition to obtain a real-time ice image.
And step S20, performing image processing and three-dimensional reconstruction on the obtained ice-shaped image at any moment to obtain three-dimensional point cloud data at any moment.
As will be appreciated by those skilled in the art, for an ice-shaped image obtained at any one time, image processing and three-dimensional reconstruction may be performed based on methods of the prior art to obtain three-dimensional point cloud data of the ice shape in the ice-shaped image. And will not be described in detail herein.
Step S30, edge extraction is carried out based on the three-dimensional point cloud data at any time, and edge points are obtained.
Based on the three-dimensional point cloud data of any moment, the surface points of the moment can be obtained, and among the surface points, please refer to fig. 4, the frozen ice shape 07 grows on the basis of the frozen ice shape 06 of the moment t-1, and some cliff edge points 08 protruding outwards exist, and the cliff edge points 08 can not be recognized by the image acquisition device due to being blocked because of being positioned on a leeward surface in the later growth process, and the edge points are also very likely to be upper layered points of a gap space, so that we need to obtain the edge points first. As can be appreciated by those skilled in the art, edge extraction is performed based on the three-dimensional point cloud data at any time to obtain an edge point, which can be implemented by using a method in the prior art, and therefore, will not be described herein.
And step S40, setting a vertical line passing through any one of the obtained edge points based on the any one of the obtained edge points, wherein the vertical line is parallel to a central axis of a field of view of an image acquisition device for acquiring the ice-shaped image, and identifying an intersection point of the vertical line and three-dimensional point cloud data.
In one embodiment, referring to fig. 5, a perpendicular L passing through any one of the edge points p i is set based on any one of the obtained edge points p i, the perpendicular L is parallel to a central axis of a field of view of an image capturing device for capturing an ice image (i.e., a z-axis direction of a three-dimensional point cloud space), and an intersection point Q of the perpendicular L and the three-dimensional point cloud data is identified; wherein i represents the index of the edge points, i is more than or equal to 1 and n is more than or equal to n, and n represents the total number of the edge points.
In some cases, an intersection point directly intersecting with the perpendicular L does not exist in the three-dimensional point cloud data, and therefore, for the identification of the intersection point, it may be: and identifying points with a distance from the vertical line L smaller than or equal to a preset first distance threshold in the three-dimensional point cloud data, and identifying the points as intersection points, wherein the intersection points become potential layering points under the shielding of layering ice shapes. Therefore, we can identify these points as intersection points. The first distance threshold may be set according to timing requirements.
Step S50, based on any one edge point and the corresponding intersection point, identifying whether the any one edge point and the corresponding intersection point are layering points.
For the identification of the hierarchical points, in one embodiment, the distance between any one edge point and the intersection point corresponding to the edge point is calculated, and if the distance is greater than or equal to a preset distance threshold value, the any one edge point and the intersection point corresponding to the edge point are identified as the hierarchical points.
In one embodiment, if the three-dimensional point cloud data acquired at any one time includes the aircraft surface 09 point cloud data, then the intersection point may be an intersection point with the aircraft surface 09 point cloud.
In one embodiment, if the three-dimensional point cloud data does not include the ice-shaped attachment growth aircraft surface 09 point cloud data, it is possible that the number of intersection points is 0, and at this time, any one of the edge points may be directly identified as a layered point.
In one embodiment, in the case of multi-layer occlusion, the intersection point may have at least two multi-intersection points, and at this time, the intersection point closest to the arbitrary edge point is identified, the distance between the arbitrary edge point and the closest intersection point is calculated, and if the distance is greater than or equal to a preset second distance threshold, the arbitrary edge point and all the intersection points corresponding to the arbitrary edge point are identified as the layered points. When the nearest intersection points meet the second distance threshold, the intersection points are all layering points which are no longer grown as the intersection points are all located on the lee surface of the icing unit where the edge points are located.
In one embodiment, referring to fig. 5, a distance H between an intersection point Q corresponding to any one edge point p i and any one edge point p i in the three-dimensional point cloud at any one time t is calculated, and if H is greater than H, the any one edge point p i and the intersection point Q corresponding to the any one edge point p i are identified as layered points. Wherein H represents a preset second distance threshold, which can be set according to the time sequence requirement.
Thus, when the hierarchical point at any one time is identified, the hierarchical points at all times can be obtained.
And step S60, obtaining the reconstructed three-dimensional ice shape based on the identified layering points.
In one embodiment, for a three-dimensional ice shape at any time, a reconstructed three-dimensional ice shape is obtained based on three-dimensional point cloud data at the time and layering points identified at all times before the time.
Because the reconstructed three-dimensional ice shape comprises the blocked layering points, the blocked area on the back of the icing unit can be obtained. Therefore, high-fidelity reconstruction of the hybrid ice shape can be realized, the problem of poor measurement precision of the complex ice shape caused by mutual shielding among icing units under the condition of sparse time sequence three-dimensional point cloud is effectively solved, and the measurement precision of the complex icing three-dimensional ice shape which is mutually shielded is improved.
Referring to fig. 6, in one embodiment of the present application, a complex ice-shaped three-dimensional reconstruction system based on sparse time sequence is provided, which includes an image acquisition device 01, a first processor 02, a second processor 03, a third processor 04, and a fourth processor 05. The image acquisition device 01 is used for acquiring ice-shaped images at any moment. The first processor 02 is configured to perform image processing and three-dimensional reconstruction on the obtained ice-shaped image at any time, and obtain three-dimensional point cloud data at any time. The second processor 03 is configured to set a vertical line passing through any one of the obtained edge points, where the vertical line is parallel to a central axis of a field of view of an image capturing device for capturing an ice image, and identify an intersection point of the vertical line and three-dimensional point cloud data. The third processor 04 is configured to identify, based on the arbitrary edge point and the intersection point corresponding to the arbitrary edge point, whether the arbitrary edge point and the intersection point corresponding to the arbitrary edge point are hierarchical points. The fourth processor 05 is configured to obtain a reconstructed three-dimensional ice shape based on the identified layered dots.
Based on the three-dimensional reconstruction system, the complex ice-shaped three-dimensional reconstruction method of any one embodiment can be effectively realized.
It will be appreciated by those skilled in the art that the hardware configuration of the video image quality detection apparatus shown in fig. 6 does not constitute a limitation of the complex ice-shape three-dimensional reconstruction system, and may include more or fewer components than illustrated, or may combine certain components, or a different arrangement of components.
In one embodiment, any one of the first processor 02, the second processor 03, the third processor 04, and the fourth processor 05 may be a separate processor chip, or may be a certain computing module in the processor chip.
In one embodiment, any two, three, or four of the first processor 02, the second processor 03, the third processor 04, and the fourth processor 05 may be the same processor.
In one embodiment, any one, two, or three of the first processor 02, the second processor 03, and the fourth processor 05 may be image processors in order to achieve faster processing.
In one embodiment of the present application, a computer readable storage medium is provided, where a program is stored, where the stored program includes a complex ice-shape three-dimensional reconstruction method that can be loaded and processed by a processor in any of the above embodiments.
Those skilled in the art will appreciate that all or part of the functions of the various methods in the above embodiments may be implemented by hardware, or may be implemented by a computer program. When all or part of the functions in the above embodiments are implemented by means of a computer program, the program may be stored in a computer readable storage medium, and the storage medium may include: read-only memory, random access memory, magnetic disk, optical disk, hard disk, etc., and the program is executed by a computer to realize the above-mentioned functions. For example, the program is stored in the memory of the device, and when the program in the memory is executed by the processor, all or part of the functions described above can be realized. In addition, when all or part of the functions in the above embodiments are implemented by means of a computer program, the program may be stored in a storage medium such as a server, another computer, a magnetic disk, an optical disk, a flash disk, or a removable hard disk, and the program in the above embodiments may be implemented by downloading or copying the program into a memory of a local device or updating a version of a system of the local device, and when the program in the memory is executed by a processor.
The foregoing description of the invention has been presented for purposes of illustration and description, and is not intended to be limiting. Several simple deductions, modifications or substitutions may also be made by a person skilled in the art to which the invention pertains, based on the idea of the invention.
Claims (10)
1. The complex ice-shaped three-dimensional reconstruction method based on sparse time sequence is characterized by comprising the following steps of:
Acquiring an ice-shaped image at any time;
Carrying out image processing and three-dimensional reconstruction on the obtained ice-shaped image at any moment to obtain three-dimensional point cloud data at any moment;
Based on the three-dimensional point cloud data at any moment, carrying out edge extraction to obtain edge points;
Setting a vertical line passing through any one edge point based on the obtained edge point, wherein the vertical line is parallel to a central axis of a view field of an image acquisition device for acquiring the ice-shaped image, and identifying an intersection point of the vertical line and three-dimensional point cloud data;
Identifying whether the arbitrary edge point and the intersection point corresponding to the arbitrary edge point are layering points or not based on the arbitrary edge point and the intersection point corresponding to the arbitrary edge point;
And obtaining the reconstructed three-dimensional ice shape based on the identified layering points.
2. A method for three-dimensional reconstruction of a complex ice shape as defined in claim 1, wherein said step of setting a vertical line passing through any one of the obtained edge points based on the any one of the obtained edge points, the vertical line being parallel to a central axis of a field of view of an image capturing device for capturing the ice shape image, and identifying an intersection point of the vertical line and three-dimensional point cloud data comprises:
Based on any one obtained edge point p i, setting a vertical line L passing through any one edge point p i, wherein the vertical line L is parallel to a central axis of a view field of an image acquisition device for acquiring ice-shaped images, and identifying an intersection point Q of the vertical line L and three-dimensional point cloud data; wherein i represents the index of the edge points, i is more than or equal to 1 and less than or equal to n, and n represents the total number of the edge points; the method for identifying the intersection point Q of the perpendicular L and the three-dimensional point cloud data comprises the following steps:
Points with a distance from the perpendicular L smaller than or equal to a preset first distance threshold value in the three-dimensional point cloud data are identified, and the points are identified as intersection points.
3. A method for three-dimensional reconstruction of a complex ice shape as set forth in claim 1, wherein said identifying whether any one of the edge points and the intersection point corresponding thereto are hierarchical points based on the any one of the edge points and the intersection point corresponding thereto comprises:
And calculating the distance between any one edge point and the corresponding intersection point, and if the distance is greater than or equal to a preset second distance threshold value, identifying the any one edge point and the corresponding intersection point as a layering point.
4. The method of claim 1, wherein the three-dimensional point cloud data does not include ice-attached and grown aircraft surface point cloud data, and the identifying whether any edge point and the intersection point corresponding to the edge point are layered points based on the any edge point and the intersection point corresponding to the edge point comprises:
And if the number of the intersection points corresponding to any one edge point is 0, identifying the any one edge point as a layering point.
5. A method for three-dimensional reconstruction of a complex ice shape according to claim 1 or 2, wherein said identifying whether any one of the edge points and the intersection point corresponding thereto are hierarchical points based on the any one of the edge points and the intersection point corresponding thereto comprises:
If the number of the intersection points corresponding to any one edge point is at least two, identifying the intersection point closest to the any one edge point, calculating the distance between the any one edge point and the closest intersection point, and if the distance is greater than or equal to a preset second distance threshold value, identifying the any one edge point and all the intersection points corresponding to the any one edge point as layering points.
6. The method for three-dimensional reconstruction of a complex ice shape according to claim 1, wherein said obtaining a reconstructed three-dimensional ice shape based on the identified hierarchical points comprises:
and for the three-dimensional ice shape at any time, obtaining the reconstructed three-dimensional ice shape based on the three-dimensional point cloud data at any time and the layering points obtained by identifying all the times before any time.
7. A complex ice-shape three-dimensional reconstruction system based on sparse timing, comprising:
The image acquisition device is used for acquiring ice-shaped images at any moment;
the first processor is used for carrying out image processing and three-dimensional reconstruction on the obtained ice-shaped image at any moment to obtain three-dimensional point cloud data at any moment;
The second processor is used for setting a vertical line passing through any one of the obtained edge points based on the any one of the obtained edge points, wherein the vertical line is parallel to a central axis of a visual field of an image acquisition device for acquiring the ice-shaped image, and identifying an intersection point of the vertical line and three-dimensional point cloud data;
a third processor, configured to identify, based on the arbitrary edge point and the intersection point corresponding to the arbitrary edge point, whether the arbitrary edge point and the intersection point corresponding to the arbitrary edge point are hierarchical points;
and a fourth processor for obtaining a reconstructed three-dimensional ice shape based on the identified layered points.
8. The complex ice-shaped three-dimensional reconstruction system of claim 7, wherein any two or more of the first processor, the second processor, the third processor, and the fourth processor are the same processor.
9. A complex ice-shaped three-dimensional reconstruction system according to claim 7, wherein any one or more of the first processor, the second processor and the fourth processor is an image processor.
10. A computer readable storage medium, wherein a program is stored in the medium, the program being capable of being loaded by a processor and performing the complex ice-shape three-dimensional reconstruction method according to any one of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410558455.9A CN118134986B (en) | 2024-05-08 | Sparse time sequence-based complex ice-shaped three-dimensional reconstruction method, system and medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410558455.9A CN118134986B (en) | 2024-05-08 | Sparse time sequence-based complex ice-shaped three-dimensional reconstruction method, system and medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN118134986A CN118134986A (en) | 2024-06-04 |
CN118134986B true CN118134986B (en) | 2024-07-16 |
Family
ID=
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
AU2020103131A4 (en) * | 2020-10-30 | 2021-01-07 | Nanjing Forestry University | Leaf surface reconstruction and physically based deformation simulation based on the point cloud data |
CN113376953A (en) * | 2021-05-20 | 2021-09-10 | 达闼机器人有限公司 | Object projection reconstruction system |
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
AU2020103131A4 (en) * | 2020-10-30 | 2021-01-07 | Nanjing Forestry University | Leaf surface reconstruction and physically based deformation simulation based on the point cloud data |
CN113376953A (en) * | 2021-05-20 | 2021-09-10 | 达闼机器人有限公司 | Object projection reconstruction system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2020215985A1 (en) | Medical image segmentation method and device, electronic device and storage medium | |
Gao et al. | Salient object detection in the distributed cloud-edge intelligent network | |
Zhang et al. | A categorization of multiscale-decomposition-based image fusion schemes with a performance study for a digital camera application | |
WO2022000862A1 (en) | Method and apparatus for detecting object in fisheye image, and storage medium | |
EP2102675B1 (en) | Segmentation of magnetic resonance diffusion data | |
Cusicanqui et al. | Usability of aerial video footage for 3-D scene reconstruction and structural damage assessment | |
McKinnon et al. | Towards automated and in-situ, near-real time 3-D reconstruction of coral reef environments | |
CN113424222A (en) | System and method for providing stroke lesion segmentation using a conditional generation countermeasure network | |
CN110147837B (en) | Method, system and equipment for detecting dense target in any direction based on feature focusing | |
CN112785591B (en) | Method and device for detecting and segmenting rib fracture in CT image | |
CN110070610A (en) | The characteristic point matching method and device of characteristic point matching method, three-dimensionalreconstruction process | |
CN115601574A (en) | Unmanned aerial vehicle image matching method for improving AKAZE characteristics | |
CN115661459A (en) | 2D mean teacher model using difference information | |
US5428655A (en) | Method and apparatus for three-dimensional detection of particles | |
CN118134986B (en) | Sparse time sequence-based complex ice-shaped three-dimensional reconstruction method, system and medium | |
CN118134986A (en) | Sparse time sequence-based complex ice-shaped three-dimensional reconstruction method, system and medium | |
CN116433976A (en) | Image processing method, device, equipment and storage medium | |
CN111914766B (en) | Method for detecting business trip behavior of city management service | |
CN118134985B (en) | Complex ice-shaped three-dimensional reconstruction method and medium based on dense time sequence | |
CN115861531A (en) | Crop group three-dimensional reconstruction method based on aerial images | |
CN115131384A (en) | Bionic robot 3D printing method, device and medium based on edge preservation | |
CN114049608A (en) | Track monitoring method and device, computer equipment and storage medium | |
CN116597168B (en) | Matching method, device, equipment and medium of vehicle-mounted laser point cloud and panoramic image | |
Kassim et al. | A cell augmentation tool for blood smear analysis | |
CN116912767B (en) | Milk cow individual feed intake monitoring method based on machine vision and point cloud data |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant |