Core recording method, device, system and equipment based on visual identification technology

Abstract

The invention discloses a core logging method, device, system and equipment based on a visual identification technology, and relates to the technical field of core logging. The method comprises the following steps: firstly, acquiring a plurality of multispectral images and a plurality of laser point cloud ranging data of a target rock core in a rock core box from different angles, then determining the lithology of the target rock core according to the multispectral images, and automatically calculating the rock core length and the rock core recovery rate of the target rock core according to a three-dimensional laser point cloud model constructed according to the laser point cloud ranging data. And finally recording the lithology, the core length and the core recovery rate of the target core. According to the invention, automatic calculation of the core catalog data is realized, the defect of low accuracy caused by experience measurement and experience estimation of workers in the prior art is overcome, and the accuracy of the core catalog data is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of core logging, and particularly to a core logging method, device, system and equipment based on visual recognition technology. Background Art

[0002] Core logging refers to the original geological logging carried out during core drilling. During the core logging process, it is necessary for staff to preliminarily judge the color, lithology, structural characteristics and composition of the rock in the core based on experience, and use a tape measure to measure the core length. However, due to the presence of different degrees of joint structure, crack damage, weathering, etc. in the rock, the length of the core taken out is often less than the actual core length that should be taken. Currently, in actual operation, it is first necessary to determine a certain position, read the accurate core meters at that position, and perform empirical estimation based on the position data of the core run marks of the upper and lower 4 runs in the core storage box, with relatively low accuracy. Summary of the Invention

[0003] The purpose of the present invention is to provide a core logging method, device, system and equipment based on visual recognition technology, which can automatically calculate core logging data and improve the accuracy of core logging data at the same time.

[0004] To achieve the above object, the present invention provides the following solutions:

[0005] A core logging method based on visual recognition technology includes:

[0006] Collecting multiple multispectral images and multiple laser point cloud ranging data of the target core in the core box from different angles;

[0007] Fusing the multiple multispectral images to obtain a multispectral fusion image of the target core;

[0008] Extracting spectral feature data of the target core from the multispectral fusion image, and matching it with the spectral feature data of different lithologies of the core stored in the database to determine the lithology of the target core;

[0009] Using the multiple laser point cloud ranging data to perform three-dimensional modeling of the target core to obtain a three-dimensional laser point cloud model of the target core;

[0010] Determining the core length and core recovery rate of the target core according to the three-dimensional laser point cloud model of the target core;

[0011] Logging the lithology, core length and core recovery rate of the target core.

[0012] A core logging device based on visual recognition technology includes: a circular rail-shaped three-axis pan-tilt stabilization module, a multispectral camera, a laser point cloud rangefinder and a computer;

[0013] The circular-rail-shaped three-axis gimbal stabilization module is fixed above the core box;

[0014] The multispectral camera and the laser point cloud rangefinder are both movably arranged on the circular-rail-shaped three-axis gimbal stabilization module, and the lens of the multispectral camera and the measuring end of the laser point cloud rangefinder are both aligned with the core box;

[0015] The signal output ends of the multispectral camera and the laser point cloud rangefinder are both connected to the computer;

[0016] The multispectral camera is used to collect multispectral images of the target core in the core box from different angles while operating on the circular-rail-shaped three-axis gimbal stabilization module;

[0017] The laser point cloud rangefinder is used to collect laser point cloud ranging data of the target core in the core box from different angles while operating on the circular-rail-shaped three-axis gimbal stabilization module;

[0018] The computer is used to catalog the lithology, core length, and core recovery rate of the target core according to the multispectral images and laser point cloud ranging data of the target core, using the above-mentioned core cataloging method based on vision recognition technology.

[0019] A core cataloging system based on vision recognition technology, comprising:

[0020] A data acquisition module, which is used to collect multiple multispectral images and multiple laser point cloud ranging data of the target core in the core box from different angles;

[0021] A fusion module, which is used to fuse the multiple multispectral images to obtain a single multispectral fusion image of the target core;

[0022] A lithology determination module, which is used to extract the spectral feature data of the target core from the multispectral fusion image and match it with the spectral feature data of different lithologies of the core stored in the database to determine the lithology of the target core;

[0023] A 3D modeling module, which is used to perform 3D modeling of the target core using multiple laser point cloud ranging data to obtain a 3D laser point cloud model of the target core;

[0024] A length and recovery rate determination module, which is used to determine the core length and core recovery rate of the target core according to the 3D laser point cloud model of the target core;

[0025] A cataloging module, which is used to catalog the lithology, core length, and core recovery rate of the target core.

[0026] A computer device includes: a memory, a processor, and a computer program stored on the memory and executable on the processor. The processor executes the computer program to implement the steps of the above method.

[0027] According to the specific embodiments provided by the present invention, the following technical effects are disclosed:

[0028] A core cataloging method, device, system, and equipment based on visual recognition technology according to an embodiment of the present invention determine the lithology of a target core based on a multispectral image, and automatically calculate the core length and core recovery rate of the target core according to a three-dimensional laser point cloud model of the target core constructed from laser point cloud ranging data, realizing the automatic calculation of core cataloging data. At the same time, it overcomes the defect of low accuracy caused by relying on the experience measurement and estimation of staff, and improves the accuracy of core cataloging data. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0030] Figure 1 It is a flowchart of a core cataloging method based on visual recognition technology provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0031] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0032] To make the above objects, features, and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below with reference to the drawings and specific embodiments.

[0033] Embodiment 1

[0034] As Figure 1 shown, an embodiment of the present invention provides a core cataloging method based on visual recognition technology, including:

[0035] Step 1: Collect multiple multispectral images and multiple laser point cloud ranging data of the target core in the core box from different angles.

[0036] Take pictures and measurements of the target core placed in the core box, and collect multi-spectral images and laser point cloud ranging data around the target core.

[0037] Step 2: Merge multiple of the multi-spectral images to obtain a multi-spectral merged image of the target core.

[0038] Before merging multiple multi-spectral images, first perform denoising processing on each multi-spectral image. After the denoising processing, fuse all the obtained multi-spectral images to form a multi-spectral merged image of the target core.

[0039] Step 3: Extract the spectral feature data of the target core from the multi-spectral merged image, and match it with the spectral feature data of different lithologies of cores stored in the database to determine the lithology of the target core.

[0040] Step 4: Use multiple laser point cloud ranging data to perform 3D modeling of the target core to obtain a 3D laser point cloud model of the target core.

[0041] The process of 3D modeling is as follows:

[0042] S4.1: According to multiple laser point cloud ranging data, construct a partial 3D laser point cloud model of the target core corresponding to the laser point cloud ranging data.

[0043] S4.2: Based on the partial 3D laser point cloud model, determine the initial 3D laser point cloud model of the whole target core according to the cylindrical shape of the target core; that is, construct a connection degree model according to the laser point cloud spatial distance data collected at different positions.

[0044] S4.3: Extract the shape function of the initial 3D laser point cloud model. That is, generate a function according to the constructed model features.

[0045] S4.4: Perform denoising processing on the shape function.

[0046] Remove the outliers in the function model and correct the function to remove the spikes in the model.

[0047] S4.5: Generate the final 3D laser point cloud model of the whole target core according to the denoised shape function.

[0048] Step 5: Determine the core length and core recovery rate of the target core according to the 3D laser point cloud model of the target core.

[0049] After determining the core length and core recovery rate of the target core, it is also possible to fuse the 3D laser point cloud model and the multi-spectral merged image of the target core to generate a 3D rendering of the target core. The 3D rendering includes the lithology, core length, and core recovery rate of the target core.

[0050] Step 6: Catalog the lithology, core length, and core recovery rate of the target core.

[0051] When the target core includes multiple cores drilled in a core hole, the core length of the target core is equal to the sum of the lengths of all core segments; the core recovery rate of the target core is equal to the ratio of the core length of the target core to the core hole depth.

[0052] The present invention can distinguish cores, debris, and core boxes, and is mainly applied to the error calculation and processing methods generated during core cataloging.

[0053] The beneficial effects of the method of the present invention are as follows:

[0054] 1. Generate a three-dimensional rendered core file, facilitating digital geological cataloging and post-stage result integration.

[0055] 2. Improve work efficiency and accurately read core meter data.

[0056] 3. Accurately calculate the core recovery rate data of any segment, which can reach the millimeter level.

[0057] 4. Provide database support for core judgment.

[0058] Embodiment 2

[0059] In order to execute the method corresponding to the above Embodiment 1 to achieve the corresponding functions and technical effects, a core cataloging device based on visual recognition technology is provided below, including: a circular rail-shaped three-axis gimbal stabilization module, a multispectral camera, a laser point cloud range finder, and a computer.

[0060] The circular rail-shaped three-axis gimbal stabilization module is fixed above the core box; the multispectral camera and the laser point cloud range finder are both movably arranged on the circular rail-shaped three-axis gimbal stabilization module, and the lens of the multispectral camera and the measurement end of the laser point cloud range finder are both aligned with the core box; the signal output ends of the multispectral camera and the laser point cloud range finder are both connected to the computer. The multispectral camera is used to collect multispectral images of the target core in the core box from different angles while running on the circular rail-shaped three-axis gimbal stabilization module. The laser point cloud range finder is used to collect laser point cloud range measurement data of the target core in the core box from different angles while running on the circular rail-shaped three-axis gimbal stabilization module.

[0061] The computer is used to catalog the lithology, core length, and core recovery rate of the target core according to the multispectral images and laser point cloud range measurement data of the target core by using the core cataloging method based on visual recognition technology in Embodiment 1.

[0062] In one example, the circular-rail-shaped three-axis gimbal stabilization module includes: a circular track, a moving module, and a motor module. The moving module is movably arranged on the circular track; both the multispectral camera and the laser point cloud range finder are fixed on the moving module. The driving end of the motor module is connected to the control end of the moving module. The motor module is used to make the moving module drive the multispectral camera and the laser point cloud range finder to move on the circular track.

[0063] In another example, the circular-rail-shaped three-axis gimbal stabilization module includes: a three-axis gyro stabilization module. The core box is arranged on the three-axis gyro stabilization module to keep the core box horizontally placed.

[0064] Embodiment III

[0065] An embodiment of the present invention provides a core cataloging system based on visual recognition technology, including:

[0066] A data acquisition module, configured to acquire multiple multispectral images and multiple laser point cloud range measurement data of a target core in a core box from different angles.

[0067] A fusion module, configured to fuse the multiple multispectral images to obtain a single multispectral fusion image of the target core.

[0068] A lithology determination module, configured to extract spectral feature data of the target core from the multispectral fusion image, and match it with the spectral feature data of different lithologies of cores stored in the database to determine the lithology of the target core.

[0069] A three-dimensional modeling module, configured to perform three-dimensional modeling of the target core using multiple laser point cloud range measurement data to obtain a three-dimensional laser point cloud model of the target core.

[0070] A length and recovery rate determination module, configured to determine the core length and core recovery rate of the target core according to the three-dimensional laser point cloud model of the target core.

[0071] A cataloging module, configured to catalog the lithology, core length, and core recovery rate of the target core.

[0072] The core cataloging system based on visual recognition technology provided by the embodiment of the present invention and the core cataloging method based on visual recognition technology described in the above embodiment have similar working principles and beneficial effects, so they will not be elaborated here. For specific content, please refer to the introduction of the above method embodiment.

[0073] Embodiment IV

[0074] An embodiment of the present invention provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor. The processor executes the computer program to implement the steps of the method described in Embodiment I.

[0075] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. For the same or similar parts among the various embodiments, reference may be made to each other.

[0076] Specific examples are used in this article to elaborate on the principles and implementation manners of the present invention. The descriptions of the above embodiments are only used to help understand the method of the present invention and its core idea; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A core cataloging method based on visual recognition technology, characterized in that, Including: Collecting multiple multispectral images and multiple laser point cloud ranging data of the target core in the core box from different angles; Fusing the multiple multispectral images to obtain a single multispectral fused image of the target core; Extracting spectral feature data of the target core from the multispectral fused image and matching it with the spectral feature data of different lithologies of cores stored in the database to determine the lithology of the target core; Performing three-dimensional modeling of the target core using multiple laser point cloud ranging data to obtain a three-dimensional laser point cloud model of the target core; Determining the core length and core recovery rate of the target core based on the three-dimensional laser point cloud model of the target core; Cataloging the lithology, core length, and core recovery rate of the target core.

2. The core cataloging method based on visual recognition technology according to claim 1, wherein Before fusing the multiple multispectral images to obtain a single multispectral fused image of the target core, it further includes: Performing denoising processing on each of the multispectral images.

3. The core cataloging method based on visual recognition technology according to claim 1, characterized in that Performing three-dimensional modeling of the target core using multiple laser point cloud ranging data to obtain a three-dimensional laser point cloud model of the target core, specifically including: Based on multiple laser point cloud ranging data, constructing a partial three-dimensional laser point cloud model of the target core corresponding to the laser point cloud ranging data; Based on the partial three-dimensional laser point cloud model and the cylindrical shape of the target core, determining an initial three-dimensional laser point cloud model of the whole target core; Extracting the shape function of the initial three-dimensional laser point cloud model; Performing denoising processing on the shape function; Generating a final three-dimensional laser point cloud model of the whole target core based on the denoised shape function.

4. The core cataloging method based on visual recognition technology according to claim 1, wherein When the target core includes multiple cores drilled in a core hole: The core length of the target core is equal to the sum of the lengths of all core segments; The core recovery rate of the target core is equal to the ratio of the core length of the target core to the depth of the core hole.

5. The core cataloging method based on visual recognition technology according to claim 1, characterized in that Before cataloging the lithology, core length, and core recovery rate of the target core, it further includes: Fusing the three-dimensional laser point cloud model and the multispectral fused image of the target core to generate a three-dimensional rendering drawing of the target core; the three-dimensional rendering drawing includes the lithology, core length, and core recovery rate of the target core.

6. A core cataloging device based on visual recognition technology, characterized in that Including: A circular rail-shaped three-axis gimbal stabilization module, a multispectral camera, a laser point cloud range finder, and a computer; The circular rail-shaped three-axis gimbal stabilization module is fixed above the core box; The multispectral camera and the laser point cloud range finder are both movably arranged on the circular rail-shaped three-axis gimbal stabilization module, and the lens of the multispectral camera and the measuring end of the laser point cloud range finder are both aligned with the core box; The signal output ends of the multispectral camera and the laser point cloud range finder are both connected to the computer; The multispectral camera is used to collect multispectral images of the target core in the core box from different angles while running on the circular rail-shaped three-axis gimbal stabilization module; The laser point cloud range finder is used to collect laser point cloud ranging data of the target core in the core box from different angles while running on the circular rail-shaped three-axis gimbal stabilization module; The computer is used to catalog the lithology, core length, and core recovery rate of the target core according to the multispectral images and laser point cloud ranging data of the target core by using the core cataloging method based on visual recognition technology according to any one of claims 1-5.

7. The core cataloging device based on visual recognition technology according to claim 6, characterized in that, The circular-rail three-axis gimbal stabilization module includes: a circular orbit, a moving module, and a motor module; The moving module is movably arranged on the circular orbit; both the multi-spectral camera and the laser point cloud rangefinder are fixed on the moving module; The driving end of the motor module is connected to the control end of the moving module; The motor module is used to make the moving module drive the multi-spectral camera and the laser point cloud rangefinder to move on the circular orbit.

8. The core cataloging device based on visual recognition technology according to claim 7, characterized in that, The circular-rail three-axis gimbal stabilization module includes: a three-axis gyro stabilization module; The core box is arranged on the three-axis gyro stabilization module to keep the core box horizontally placed.

9. A core cataloging system based on visual recognition technology, characterized in that, Including: A data acquisition module, configured to acquire multiple multi-spectral images and multiple laser point cloud ranging data of a target core in the core box from different angles; A fusion module, configured to fuse the multiple multi-spectral images to obtain a multi-spectral fusion image of the target core; A lithology determination module, configured to extract spectral feature data of the target core from the multi-spectral fusion image and match it with the spectral feature data of different lithologies of cores stored in the database to determine the lithology of the target core; A 3D modeling module, configured to perform 3D modeling of the target core using multiple laser point cloud ranging data to obtain a 3D laser point cloud model of the target core; A length and recovery rate determination module, configured to determine the core length and core recovery rate of the target core according to the 3D laser point cloud model of the target core; A cataloging module, configured to catalog the lithology, core length, and core recovery rate of the target core.

10. A computer device, comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method according to any one of claims 1-5.

Images