CN111325834B - Modeling method and system based on digital image processing - Google Patents
Modeling method and system based on digital image processing Download PDFInfo
- Publication number
- CN111325834B CN111325834B CN202010212308.8A CN202010212308A CN111325834B CN 111325834 B CN111325834 B CN 111325834B CN 202010212308 A CN202010212308 A CN 202010212308A CN 111325834 B CN111325834 B CN 111325834B
- Authority
- CN
- China
- Prior art keywords
- processing
- color mapping
- value
- image
- data
- 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
- 238000012545 processing Methods 0.000 title claims abstract description 68
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000013507 mapping Methods 0.000 claims abstract description 48
- 238000005516 engineering process Methods 0.000 claims abstract description 15
- 230000000877 morphologic effect Effects 0.000 claims abstract description 7
- 230000002159 abnormal effect Effects 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 14
- 238000009499 grossing Methods 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 238000003708 edge detection Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 abstract description 5
- 239000011435 rock Substances 0.000 description 6
- 230000009466 transformation Effects 0.000 description 4
- 230000001131 transforming effect Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 239000003086 colorant Substances 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 239000004215 Carbon black (E152) Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000011796 hollow space material Substances 0.000 description 1
- 229930195733 hydrocarbon Natural products 0.000 description 1
- 125000001183 hydrocarbyl group Chemical group 0.000 description 1
- 230000003993 interaction Effects 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
- 238000010422 painting Methods 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/28—Processing seismic data, e.g. analysis, for interpretation, for correction
- G01V1/32—Transforming one recording into another or one representation into another
- G01V1/325—Transforming one representation into another
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/28—Processing seismic data, e.g. analysis, for interpretation, for correction
- G01V1/34—Displaying seismic recordings or visualisation of seismic data or attributes
- G01V1/345—Visualisation of seismic data or attributes, e.g. in 3D cubes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/40—Filling a planar surface by adding surface attributes, e.g. colour or texture
-
- G06T3/04—
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V2210/00—Details of seismic processing or analysis
- G01V2210/40—Transforming data representation
- G01V2210/48—Other transforms
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V2210/00—Details of seismic processing or analysis
- G01V2210/60—Analysis
- G01V2210/66—Subsurface modeling
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V2210/00—Details of seismic processing or analysis
- G01V2210/70—Other details related to processing
- G01V2210/74—Visualisation of seismic data
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Remote Sensing (AREA)
- Acoustics & Sound (AREA)
- Theoretical Computer Science (AREA)
- Environmental & Geological Engineering (AREA)
- Geology (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geophysics (AREA)
- Software Systems (AREA)
- Geometry (AREA)
- Computer Graphics (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a modeling method and a modeling system based on image processing, wherein the method comprises the following steps of S1, converting data to be processed in a time-space domain into a digital image domain through numerical value-color mapping pairs; s2, processing the image converted into the digital image domain by using an image morphological processing technology; s3, reversely converting the processed image into a time-space domain through numerical value-color mapping, and completing modeling. The modeling method provided by the invention is simple, visual and clear in operation, high in precision and capable of efficiently and simply completing complex modeling work.
Description
Technical Field
The invention relates to a modeling method and system based on digital image processing, and relates to the technical field of seismic exploration.
Background
As seismic exploration targets are shifted from conventionally constructed reservoirs to unconventional lithologic reservoirs, simultaneous hydrocarbon-bearing prediction and reservoir recovery scheme design requires geophysical expertise to provide more accurate quantitative prediction parameters: porosity, saturation, permeability, brittleness index, etc., and therefore, place higher demands on modeling techniques. The three links of seismic data acquisition, processing and inversion are all closely related to modeling. The method comprises the steps of acquiring information of an underground medium, acquiring the information of the underground medium, and acquiring the information of the underground medium, wherein the aim of seismic data acquisition is to acquire the information of the underground medium, and the design of an acquisition and observation system is an important task of seismic data acquisition, so that the seismic data with the maximum information amount is acquired by adopting an economic and efficient observation system. The main relying means of the design of the acquisition and observation system is forward modeling, the forward modeling depends on a model, the higher the accuracy of a prediction model is, the closer the prediction data is to the actual situation, the higher the rationality of the designed observation system is, and the acquisition quality and the cost are reasonably balanced. In the seismic data processing process, the speed is a key parameter, a high-precision speed model is obtained, the imaging quality of the seismic data can be greatly improved, and the method is also a key for realizing the fidelity and the fidelity of the seismic data. The seismic data inversion process is the inverse process from data to medium parameters, which is an underdetermined problem in principle, and a low-frequency model is an indispensable factor in order to reduce the multi-solution and obtain a solution closer to the real underground condition. How to build an accurate low frequency model is one of the core problems of seismic data inversion. Therefore, in order to adapt to the transformation of the seismic exploration targets and the requirement of high-precision quantitative prediction of the oil and gas reservoirs, searching for a modeling method with high precision and convenient operation is still one of important research contents in the field of seismic exploration.
The existing modeling work is mainly divided into two stages, namely, the acquisition of modeling elements, namely, a horizon, a velocity body, a fault interpretation result and other direct or indirect results obtained by seismic data. And secondly, combining modeling elements together according to a certain rule in a time-space domain by utilizing a computer technology. The combination of modeling elements mainly depends on computer technology, and the modeling result is firstly a visual effect, so that modeling staff can obtain visual images through vision, and further modeling quality is judged. While the most challenging task in conventional modeling is man-machine interaction, modeling often becomes extremely difficult when an operator attempts to modify an element or local feature of an element in a model. The reason for this is that the interconversion between data and visual images requires too much rules and expertise in the computer domain, making it difficult for geophysical personnel to handle. Therefore, modeling work in the oil and gas exploration field is often focused on simple combinations of few modeling elements, and the requirements of production practice are difficult to meet.
In recent years, with the development of computer vision technology, particularly deep learning technology, image-based processing of oil and gas exploration data has become possible. Based on conventional wisdom, seismic data is often transformed, for example, from the time-space domain to the frequency domain by fourier transformation, and then subjected to some processing and then transformed to the time-space domain by inverse fourier transformation. The conventional modeling technique has the following drawbacks: the operation is complex, and the computer imaging technology needs to be mastered; abnormal points and boundaries in the modeling element are difficult to control; interoperation requires higher configuration computer hardware (especially memory).
Disclosure of Invention
Aiming at the problems, the invention aims to provide a modeling method and a modeling system based on digital image processing, which are used for transforming modeling elements into an image domain, processing by using an image processing technology, and then inversely transforming the processed image into a data domain, so that the precision is high, and complex modeling work can be efficiently and simply completed.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
in a first aspect, the present embodiment provides a modeling method based on digital image processing, including:
s1, converting data to be processed in a time-space domain into a digital image domain through a numerical value-color mapping pair;
s2, processing the image converted into the digital image domain by using an image morphological processing technology;
s3, reversely converting the processed image into a time-space domain through numerical value-color mapping to complete modeling.
Further, the method also comprises the step of preprocessing the data to be processed in the time-space domain:
performing outlier processing on the obtained data S to enable the data value after outlier processing to be in a set range, wherein the outlier processing is specifically as follows:
wherein Y is new data obtained after processing, S up And S is down An upper limit value and a lower limit value set for the data S, respectively.
Further, the value-color mapping pair includes two types of value-color mapping pairs: firstly, a gray value-color mapping pair is constructed, and secondly, a color value-color mapping pair is constructed.
Further, the step S2 of processing the image converted into the digital image domain by using an image morphological processing technique includes an open operation, a closed operation, and/or an edge detection smoothing process.
In a second aspect, the present embodiment further provides a modeling system based on digital image processing, the system including:
the domain conversion module is used for converting the data to be processed in the time-space domain into a digital image domain through a numerical value-color mapping pair;
an image processing module for processing the image converted into the digital image domain by using an image morphological processing technology;
and the inverse conversion module is used for inversely converting the processed image into a time-space domain through numerical value-color mapping.
Further, the system also comprises an outlier processing module, which is used for carrying out outlier processing on the obtained data, so that the value of the data after outlier processing is in a set range.
Due to the adoption of the technical scheme, the invention has the following advantages:
1. the modeling method provided by the invention has the advantages that the modeling work is completed by utilizing image processing, the operation is simple, a complex computer technology is not needed to be used as a support, especially, the abnormal points and boundary problems in the model are more convenient to process, the computer resources with higher configuration are not needed, the operation is simple, visual and clear, the precision is high, and the complex modeling work can be efficiently and simply completed.
2. Because of the complex operation in the conventional modeling means, the abnormal points and boundaries in the modeling elements are difficult to process, and the requirement on computer hardware is high, the invention provides a method for solving the modeling problem in the digital image field based on the fact that the computer vision research field and the deep learning technology are rapidly developed in the image field, and the modeling elements are converted into the digital image field, the problems of local abnormal points, smooth boundaries and the like in the modeling process are solved by utilizing the conventional image processing technology, and then the modeling elements are converted into the data field;
in conclusion, the invention can be widely applied to seismic exploration.
Detailed Description
Exemplary embodiments of the present invention are described in more detail below, however, it should be understood that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
It is to be understood that the terminology used herein is for the purpose of describing particular example embodiments only, and is not intended to be limiting. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. The terms "comprises," "comprising," and "having" are inclusive and therefore specify the presence of stated features, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, elements, components, and/or groups thereof. The method steps, processes, and operations described herein are not to be construed as necessarily requiring their performance in the particular order described or illustrated, unless an order of performance is explicitly stated. It should also be appreciated that additional or alternative steps may be used.
Example 1
The embodiment provides a modeling method based on digital image processing, which comprises the following steps:
s1, acquiring related data such as earthquake and the like, and removing outliers from the seismic data
In this embodiment, the seismic data or the related attribute data is denoted as S. Preprocessing the obtained seismic data S, for example, so that the data exceeding the set range falls into the corresponding data range:
wherein S is up And S is down And (3) respectively obtaining a reasonable upper limit value and a reasonable lower limit value of S, carrying out outlier removal processing on the seismic data through the formula, and obtaining new data Y after processing.
S2, constructing a conversion value-color mapping pair of the data to the image:
the present embodiment can construct two types of value-color mapping pairs according to actual needs: firstly, a gray value-color mapping pair is constructed, and secondly, a color value-color mapping pair is constructed.
Specifically, colors may be represented in three colors of red, green and blue (RGB), each of which varies from 0 to 255. The gray scale value-color mapping pair is 255, namely, red, green and blue are equal, and the gray scale value-color mapping pair ranges from 000, 1 1, 2 2 … … to 255 255 255. The color number-color mapping pairs can be 16777216 (24 th power of 2) mapping pairs at most, and the number-color mapping pairs can be utilized to convert the data volume of the time-space domain into pictures of the digital image domain, wherein the number of the mapping pairs is not more than 1000 in the general oil and gas exploration field.
S3, processing the converted image according to the need, wherein the processing comprises open operation, closed operation, edge detection smoothing processing and the like:
the open operation is the process of sequentially corroding and expanding the image, and after the image is corroded, abnormal points are removed, but the image is compressed. And then expanding the corroded image to remove abnormal points and retain the original image.
The closed operation is the process of sequentially expanding and corroding the image. The image expands and then erodes, which helps to remove outliers within a connected region, or outliers on the boundary of the region.
Edge smoothing processing, which can be performed by alternating open operation and close operation.
The above operation essentially traverses the image with a convolution kernel of n×n, the size of n depending on the size of the outlier and the degree of edge smoothing.
S4, inversely transforming the processed image into a space-time data domain through numerical value-color mapping, namely: the processed picture is converted to the original data field using the constructed value-color mapping pairs.
Example 2
The present embodiment provides a modeling system based on digital image processing, the system including:
the abnormal value processing module is used for carrying out abnormal value processing on the obtained data so that the data value after the abnormal value processing is in a set range.
The domain conversion module is used for converting the data to be processed in the time-space domain into a digital image domain through a numerical value-color mapping pair;
an image processing module for processing the image converted into the digital image domain by using an image morphological processing technology;
and the inverse conversion module is used for inversely converting the processed image into a time-space domain through numerical value-color mapping.
Example 3
The embodiment provides a modeling process for engraving igneous rock on a three-dimensional seismic data volume based on digital image processing, the modeling process comprising the following steps:
s1: removing abnormal values from the seismic data, so that the value of the processed seismic data is in a set range;
s2: defining a numerical value-color mapping pair, wherein the more the number of the numerical value-color mapping pairs is, the higher the accuracy of converting the seismic data into an image is;
s3: the seismic data can be converted into images along the direction of the main line or the direction of the connecting line by utilizing the numerical value-color mapping pair in the S2;
s4: editing igneous rock positions by using an image editing tool, such as a painting brush, a rubber and a color filling function in a drawing program of a windows system, editing igneous rock into a single color, such as RGB (red, green and blue) of 244 126 120, wherein the color is not contained in the numerical value-color mapping pair defined in the step S2, and a numerical value-color mapping pair is independently defined for the color and supplemented to the numerical value-color mapping pair defined in the step S2 to form a new numerical value-color mapping pair;
s5: the igneous rock boundary in S4 is processed by using an image boundary processing tool, and the open operation, the close operation and the edge detection smoothing processing of the image are mainly carried out, so that the igneous rock boundary is smoother and accords with geological recognition;
s6: and (5) performing inverse transformation on the image processed in the S5 by using the numerical value-color mapping in the S4 to obtain processed model data, thereby completing the engraving of igneous rocks.
Example 4
The embodiment provides a process for modeling a three-dimensional velocity body based on a digital image processing method, wherein the velocity body is an intermediate result of seismic data processing, and the modeling method comprises the following steps of:
s1: removing abnormal values from the seismic data, so that the processed velocity values are in a reasonable range;
s2: defining speed value-color mapping pairs, wherein the more the number of the speed value-color mapping pairs is, the higher the accuracy of converting the speed body into an image is;
s3: converting the velocity body along the inline or crossline direction into an image (the Z direction is typically the depth or time direction) using the velocity value-color mapping pair in S2;
s4: eliminating small anomalies in the velocity body by utilizing image division operation, separating two velocity anomalies at a slim point, and smoothing the boundary of a larger velocity body without changing the area of the velocity body;
s5: the image closing operation is utilized to fill a tiny hollow space in the speed body, connect the boundary of the adjacent speed abnormal body and smooth the speed abnormal body without changing the area;
s6: processing the generated speed body boundary by using an image boundary processing tool S5;
s7: and (3) inversely transforming the image processed in the S6 by using the speed value-color mapping pair in the S2 to generate a processed speed model.
Finally, it should be noted that: the above embodiments are only for illustrating the technical aspects of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those of ordinary skill in the art that: modifications and equivalents may be made to the specific embodiments of the invention without departing from the spirit and scope of the invention, which is intended to be covered by the claims.
Claims (2)
1. A modeling method based on digital image processing, characterized by comprising:
s1, converting data to be processed of a time-space domain into a digital image domain along a main line direction or a tie line direction through a numerical value-color mapping pair, wherein the numerical value-color mapping pair comprises two types of numerical value-color mapping pairs: firstly, constructing a gray value-color mapping pair, and secondly, constructing a color value-color mapping pair; the step of preprocessing the data to be processed in the time-space domain:
performing outlier processing on the obtained data S to enable the data value after outlier processing to be in a set range, wherein the outlier processing is specifically as follows:
wherein Y is new data obtained after processing, S up And S is down An upper limit value and a lower limit value set for the data S, respectively;
s2, processing the image converted into the digital image domain by using an image morphological processing technology, wherein the processing comprises open operation, closed operation and/or edge detection smoothing processing;
s3, reversely converting the processed image into a time-space domain through numerical value-color mapping to complete modeling.
2. A modeling system based on digital image processing, the system comprising:
the abnormal value processing module is used for performing abnormal value processing on the obtained data so that the data value after the abnormal value processing is in a set range, and specifically comprises the following steps:
wherein Y is new data obtained after processing, S up And S is down An upper limit value and a lower limit value set for the data S, respectively;
the domain conversion module is used for converting the data to be processed of the time-space domain into the digital image domain along the direction of the main line or the direction of the connecting line through a numerical value-color mapping pair, wherein the numerical value-color mapping pair comprises two types of numerical value-color mapping pairs: firstly, constructing a gray value-color mapping pair, and secondly, constructing a color value-color mapping pair;
an image processing module for processing the image converted into the digital image domain by using an image morphological processing technology, including an open operation, a close operation and/or an edge detection smoothing process;
and the inverse conversion module is used for inversely converting the processed image into a time-space domain through numerical value-color mapping.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010212308.8A CN111325834B (en) | 2020-03-24 | 2020-03-24 | Modeling method and system based on digital image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010212308.8A CN111325834B (en) | 2020-03-24 | 2020-03-24 | Modeling method and system based on digital image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111325834A CN111325834A (en) | 2020-06-23 |
| CN111325834B true CN111325834B (en) | 2023-12-26 |
Family
ID=71169961
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010212308.8A Active CN111325834B (en) | 2020-03-24 | 2020-03-24 | Modeling method and system based on digital image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111325834B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105425301A (en) * | 2016-01-08 | 2016-03-23 | 东华理工大学 | Frequency domain three-dimensional irregular earthquake data reconstruction method |
| WO2017166187A1 (en) * | 2016-03-31 | 2017-10-05 | Shanghai United Imaging Healthcare Co., Ltd. | System and method for image reconstruction |
| EP3429180A1 (en) * | 2017-07-14 | 2019-01-16 | Universitat Pompeu Fabra | Method and system for color gamut mapping |
| CN109254320A (en) * | 2018-10-18 | 2019-01-22 | 中国海洋石油集团有限公司 | Seismic properties optimization and sand body Overlay District prediction technique based on image processing method |
| CN110308484A (en) * | 2019-06-11 | 2019-10-08 | 中国石油大学(北京) | A kind of chromatography conversion method and system based on deep learning intelligent screening first arrival |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8422103B2 (en) * | 2008-12-23 | 2013-04-16 | Ricoh Production Print Solutions LLC | Optimization of gray component replacement |
| US8411106B2 (en) * | 2008-12-30 | 2013-04-02 | Canon Kabushiki Kaisha | Converting digital values corresponding to colors of an image from a source color space to a destination color space |
| US8379947B2 (en) * | 2010-05-28 | 2013-02-19 | International Business Machines Corporation | Spatio-temporal image reconstruction using sparse regression and secondary information |
| US9036885B2 (en) * | 2012-10-28 | 2015-05-19 | Technion Research & Development Foundation Limited | Image reconstruction in computed tomography |
| US20190277989A1 (en) * | 2018-03-08 | 2019-09-12 | Chevron U.S.A. Inc. | System and method for improving resolution of digital seismic images |
-
2020
- 2020-03-24 CN CN202010212308.8A patent/CN111325834B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105425301A (en) * | 2016-01-08 | 2016-03-23 | 东华理工大学 | Frequency domain three-dimensional irregular earthquake data reconstruction method |
| WO2017166187A1 (en) * | 2016-03-31 | 2017-10-05 | Shanghai United Imaging Healthcare Co., Ltd. | System and method for image reconstruction |
| EP3429180A1 (en) * | 2017-07-14 | 2019-01-16 | Universitat Pompeu Fabra | Method and system for color gamut mapping |
| CN109254320A (en) * | 2018-10-18 | 2019-01-22 | 中国海洋石油集团有限公司 | Seismic properties optimization and sand body Overlay District prediction technique based on image processing method |
| CN110308484A (en) * | 2019-06-11 | 2019-10-08 | 中国石油大学(北京) | A kind of chromatography conversion method and system based on deep learning intelligent screening first arrival |
Non-Patent Citations (3)
| Title |
|---|
| Data and Image Prior Intergration for Image Reconstruction Using Consensus Equilibrium;Muhammad Usman Ghani等;arXiv;第1-15页 * |
| 基于RGB原理的地震多属性显示技术研究与应用;靳涛;《中国优秀硕士学位论文全文数据库（信息科技辑）》;第12-22页 * |
| 数学形态学在地震信号处理中的应用研究;陈辉等;地球物理学进展;第24卷(第6期);第1995-2002页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111325834A (en) | 2020-06-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110210551B (en) | Visual target tracking method based on adaptive subject sensitivity | |
| CN111179187B (en) | Single image rain removing method based on cyclic generation countermeasure network | |
| CN108364278B (en) | Rock core fracture extraction method and system | |
| CN106295613A (en) | A kind of unmanned plane target localization method and system | |
| CN107564078B (en) | Automatic vectorization method for grid partition map with interference pixels | |
| CN111950046B (en) | Drilling data model construction method based on BIM | |
| CN106815594A (en) | Solid matching method and device | |
| CN103743750B (en) | A kind of generation method of distribution diagram of surface damage of heavy calibre optical element | |
| CN105093289A (en) | Seismic horizon identification method based on image processing | |
| CN113780345A (en) | Small sample classification method and system facing small and medium-sized enterprises and based on tensor attention | |
| CN107729291A (en) | A kind of Identification of Bilinear Model Parameters method based on decomposition technique | |
| CN105894513A (en) | Remote sensing image change detection method and remote sensing image change detection system taking into consideration spatial and temporal variations of image objects | |
| Weber et al. | Detecting critical regions in scalar fields | |
| CN111325834B (en) | Modeling method and system based on digital image processing | |
| Wang et al. | Color matching simulation of ocean landscape decoration pattern based on visual communication | |
| Heipke et al. | Semiautomatic extraction of roads from aerial images | |
| CN112785707B (en) | BIM-based three-dimensional geological automatic modeling method | |
| CN110174109A (en) | A kind of polynary joint air navigation aid of unmanned boat based on air-sea collaboration | |
| CN112686830A (en) | Super-resolution method of single depth map based on image decomposition | |
| CN107239779B (en) | Improved method for scanning paper chart water depth points and automatically vectorizing and extracting information | |
| CN115631489A (en) | Three-dimensional semantic scene completion method, device, equipment and medium | |
| CN113421334B (en) | Multi-focus image three-dimensional reconstruction method based on deep learning | |
| CN111462014B (en) | Single-image rain removing method based on deep learning and model driving | |
| CN115544811A (en) | Data management method applied to digital twin model | |
| CN110441821B (en) | Fault fast interpretation method based on variable interpretation net density |
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 |