CN109035224B - Submarine pipeline detection and three-dimensional reconstruction method based on multi-beam point cloud - Google Patents
Submarine pipeline detection and three-dimensional reconstruction method based on multi-beam point cloud Download PDFInfo
- Publication number
- CN109035224B CN109035224B CN201810758534.9A CN201810758534A CN109035224B CN 109035224 B CN109035224 B CN 109035224B CN 201810758534 A CN201810758534 A CN 201810758534A CN 109035224 B CN109035224 B CN 109035224B
- Authority
- CN
- China
- Prior art keywords
- pipeline
- point cloud
- sonar
- fitting
- cloud 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
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000001514 detection method Methods 0.000 title claims abstract description 28
- 238000001914 filtration Methods 0.000 claims abstract description 16
- 238000004458 analytical method Methods 0.000 claims abstract description 8
- 238000003708 edge detection Methods 0.000 claims description 9
- 238000007619 statistical method Methods 0.000 claims description 7
- 239000000284 extract Substances 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/0006—Industrial image inspection using a design-rule based approach
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
- G06T2207/10012—Stereo images
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Computer Graphics (AREA)
- Software Systems (AREA)
- Measurement Of Velocity Or Position Using Acoustic Or Ultrasonic Waves (AREA)
Abstract
The invention relates to the field of multi-beam sonar underwater target detection and point cloud data modeling, in particular to a multi-beam point cloud-based submarine pipeline detection and three-dimensional reconstruction method. Classifying and extracting image pixel points by using a threshold method according to an underwater sonar image obtained by a multi-beam sounding sonar detection pipeline to obtain three-dimensional point cloud data; then, a point cloud denoising and filtering method based on density analysis is adopted to obtain three-dimensional point cloud data of the filtered and denoised pipeline; performing circle fitting on the point cloud data of each section of the pipeline by adopting a linear fitting method, and performing three-dimensional reconstruction on the radius of the obtained fitting circle and the center point of the linear change to obtain a three-dimensional image of the pipeline; compared with the point cloud data obtained through the sounding points, the method provided by the invention can be used for directly extracting the point cloud data from the sonar image, still obtaining a relatively accurate point cloud model, and is small in calculation amount and suitable for detection and three-dimensional reconstruction of various underwater pipelines.
Description
Technical Field
The invention relates to the field of multi-beam sonar underwater target detection and point cloud data modeling, in particular to a multi-beam point cloud-based submarine pipeline detection and three-dimensional reconstruction method.
Background
In recent decades, the development of global marine oil and gas resources has been rapid, and in the development of oil and gas resources, a submarine oil and gas pipeline is the most rapid, safe and economic way for conveying oil and gas resources, and is called as a 'life line' of marine oil and gas engineering. With the continuous deep development of ocean oil and gas resources, the laying scale of submarine pipelines is larger and larger, but under the influence of the abnormal complex environment of the seabed and human construction operation, the submarine oil and gas pipelines are easy to be damaged and damaged, oil and gas leakage can occur when the damage is accumulated to a certain degree, resource waste and ecological environment damage can be caused, even explosion can be caused by oil and gas leakage, personnel casualties and larger property loss can be caused, and therefore, the daily routing inspection of the submarine pipelines is particularly important. The operation condition of the submarine pipeline is checked regularly, the safety state of the submarine pipeline is mastered in time, and the method becomes an important guarantee measure for offshore oil and gas production, so that the pipeline corrosion can be prevented, the safe operation of the pipeline can be guaranteed, and the service life of the pipeline is prolonged.
Because the detection of the submarine pipeline mostly adopts internal detection and external detection, and in the existing submarine oil pipeline external detection technology, the mode that the underwater robot carries the multi-beam system is more and more widely applied. In order to better observe the state of the pipeline, three-dimensional information of the pipeline needs to be further extracted, the point cloud technology is widely applied to the extraction of the three-dimensional information of the target surface at present, and the point cloud technology is applied to the detection and three-dimensional reconstruction of the submarine pipeline, so that the three-dimensional information of the submarine pipeline can be accurately extracted.
The existing multi-beam sounding system can give water depth values of dozens or even hundreds of seabed measured points perpendicular to a track direction at one time, accurately and quickly obtain the size, shape and height change of an underwater target in a certain width along the track direction, and further obtain good point cloud data, so that the system has the characteristics of large measurement range, high measurement speed, high accuracy and high efficiency. However, for a pipeline with a smaller radius, the number of point clouds on the surface of the pipeline obtained by the multi-beam sounding system is very small, and the detection and three-dimensional reconstruction of the pipeline cannot be met.
Disclosure of Invention
The invention aims to provide a submarine pipeline detection and three-dimensional reconstruction method based on multi-beam point cloud so as to improve the three-dimensional reconstruction efficiency of underwater pipeline point cloud data.
The embodiment of the invention provides a submarine pipeline detection and three-dimensional reconstruction method based on multi-beam point cloud, which comprises the following steps:
the method comprises the following steps: classifying and extracting image pixel points by adopting a threshold value method and a canny edge detection method according to an underwater sonar image obtained by detecting a pipeline by using a multi-beam sounding sonar to obtain three-dimensional point cloud data of the pipeline;
step two: setting different initial radiuses R and minimum neighborhood number k by adopting a point cloud denoising and filtering method based on density analysis according to the three-dimensional point cloud data of the pipeline to obtain the three-dimensional point cloud data of the pipeline after filtering and denoising;
step three: performing circle fitting on the point cloud data of each section of the pipeline by adopting a histogram-based statistical method and a spatial linear fitting method according to the three-dimensional point cloud data of the filtered and denoised pipeline to obtain the radius of a fitting circle and a linearly-changed central point;
step four: performing three-dimensional reconstruction on the pipeline by adopting an alpha Shape algorithm according to the radius of the fitting circle and the center point of the linear change to obtain a three-dimensional image of the pipeline;
the first step comprises the following steps:
classifying and extracting image pixel points by adopting a threshold value method and a canny edge detection method according to an underwater sonar image obtained by a multi-beam sounding sonar detection pipeline; the underwater sonar image obtained by the multi-beam sounding sonar detection pipeline does not use methods such as bottom detection and the like, but directly extracts pixel points; the threshold value method carries out binarization processing on the pixel points to obtain two types of pixel points with different setting values; the canny edge detection method carries out edge detection processing on all pixel points and extracts the boundary points of the pipeline in the sonar image; converting the boundary points of the pipeline into space coordinates to obtain three-dimensional point cloud data of the pipeline;
among the space coordinates, the positive direction of the X axis is the multi-beam sonar advancing direction:
x＝t*v
wherein, x is the abscissa of the point cloud, v is the sonar moving speed, and t represents the interval time of acquiring an image by the multi-beam sonar;
the Y-axis and Z-axis coordinates of the point cloud space rectangular coordinate system correspond to the horizontal and vertical coordinates of a single sonar image, the Y-axis represents the vertical direction of a sonar track, and the Z-axis represents the normal vector direction of the ground;
the second step comprises the following steps:
setting different initial radiuses R and minimum neighborhood numbers k by adopting a point cloud denoising and filtering method based on density analysis according to the three-dimensional point cloud data of the pipeline; the density analysis method comprises the steps of defining a spherical area with the radius of R by taking a certain point in point clouds as the center of a sphere, inquiring the number of point clouds contained in the spherical area, defining a point cloud neighbor number k, and deleting the point clouds with the number of point clouds in the spherical area smaller than k as noise, otherwise, keeping the point clouds; the point cloud denoising and filtering method is carried out twice, the initial radius R and the minimum neighborhood number k are adjusted, and a noise cluster far away from a pipeline and a sparse noise point close to the pipeline are filtered respectively;
the third step comprises the following steps:
performing circle fitting on the point cloud data of each section of the pipeline by adopting a histogram-based statistical method and a spatial linear fitting method according to the three-dimensional point cloud data of the filtered and denoised pipeline; wherein, the form of each section of the pipeline is prior knowledge; the method comprises the steps of solving the average value of the radius of a fitting circle obtained after fitting a point cloud data circle of each section based on a histogram statistical method to obtain the average radius of the fitting circle; the space linear fitting method is used for fitting a circle center point set of a fitting circle obtained after the point cloud data circle of each section is fitted to obtain a linearly-changed circle center point and the direction information of the pipeline;
the invention has the beneficial effects that:
1. for a pipeline with a smaller radius, the number of point clouds on the surface of the pipeline obtained by the multi-beam sounding system is extremely small, and the detection and three-dimensional reconstruction of the pipeline cannot be met. Compared with the depth measurement point, the method has the advantages that the pipeline pixel points are directly extracted from the sonar image to be processed and the point cloud data are extracted, so that more point cloud data can be obtained, and sufficient data bases are provided for next accurate fitting of the pipeline;
2. by classifying noise into two categories: the method comprises the following steps of firstly carrying out filtering with different scales twice on all point clouds of a marine pipe, wherein the large-scale filtering mainly removes outlier noise, the small-scale filtering mainly removes noise on the surface of the near pipe, and then carrying out circle fitting on the point clouds corresponding to each section of the pipe, so that the influence of the noise on the pipe fitting can be effectively reduced, the pipe can be more accurately subjected to the circle fitting, and more accurate pipe fitting radius and circle center positions can be obtained;
3. the mean value of the fitting radius is obtained through a histogram statistical method, the radius value with low occurrence frequency is ignored, the influence of the radius extreme value on the mean radius is effectively avoided, and the submarine pipeline is generally not easy to bend, so that the center point set is fitted by linear fitting, the fitting result meeting the practical situation can be achieved, and the pipeline three-dimensional reconstruction in the next step is facilitated.
Drawings
FIG. 1 is an overall flow chart of a submarine pipeline detection and three-dimensional reconstruction method based on multi-beam point cloud;
FIG. 2 is a schematic diagram of the multi-beam sonar for submarine pipeline detection according to the present invention;
FIG. 3 is a pipeline point cloud image after denoising an original point cloud according to the present invention;
FIG. 4 is a pipeline point cloud image after the invention performs circle fitting on the denoised point cloud;
FIG. 5 is a schematic diagram of the present invention for linearly fitting the center of a fitting circle;
FIG. 6 is a cloud point view of the pipeline resulting from the final processing of the present invention;
FIG. 7(a) is a side view of the three-dimensional reconstruction of the pipeline according to the present invention;
FIG. 7(b) is a cross-sectional view of the result of three-dimensional reconstruction of the pipeline according to the present invention;
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, the present invention is further described with reference to the accompanying drawings:
fig. 1 is an overall flow chart of a submarine pipeline detection and three-dimensional reconstruction method based on multi-beam point cloud.
The technical scheme of the invention is realized as follows:
step (1): obtain underwater sonar image through multi-beam sonar collection processing, adopt the threshold value method to carry out binarization processing to the image, adopt canny edge detection method to extract the boundary point of pipeline in the sonar image, turn into space coordinate with the boundary point, obtain the three-dimensional point cloud data of pipeline, in the space rectangular coordinate system that the normal vector that uses ground is the Z axle, X axle positive direction is multi-beam sonar advancing direction:
x＝t*v
wherein x is the abscissa of the point cloud, v is the sonar moving speed, and t represents the interval time of acquiring an image by the multi-beam sonar;
the Y-axis and Z-axis coordinates of the point cloud space rectangular coordinate system correspond to horizontal and vertical coordinates of a sonar image, the Y-axis represents the vertical direction of a sonar track, and the Z-axis represents the normal vector direction of the ground;
step (2): filtering the pipeline point cloud data by adopting a density analysis method, defining a spherical area with the radius of R by taking a certain point in the point cloud as a sphere center, inquiring the number of the point clouds contained in the spherical area, defining a point cloud neighbor number k, if the number of the point clouds contained in the spherical area is less than k, regarding the point cloud as noise and deleting the point cloud, otherwise, keeping the point cloud, and performing the operation on each point in the point cloud to finish primary filtering processing. The method adopts a twice filtering mode, adjusts the initial radius and the minimum neighbor number, and respectively filters a noise cluster far away from a pipeline and a sparse noise point close to the pipeline, and FIG. 3 is point cloud data after filtering processing;
and (3): and (3) performing circle fitting on the point cloud data of each section by taking the circular section of the pipeline as a prior condition, and calculating the radius and the center of a circle of the fitting circle, wherein the point cloud of the pipeline obtained after fitting is shown in FIG. 4, and the radius of each fitting circle is different from the radius of each fitting circle seen from the diagram, and the center of the circle is not on one axis, which is not in accordance with the actual existence condition of the submarine pipeline, so that the processing of the step (4) needs to be performed on the point cloud data.
And (4): calculating the average radius of the fitting circle by using a histogram statistical method, fitting the circle center point set by using a spatial linear fitting method to obtain linearly changing circle center points, wherein the figure 5 is a fitting result of the circle center, and the figure 6 is a result graph of the pipeline point cloud obtained after processing, wherein the fitting result can meet the actual fitting result by using linear fitting because the submarine pipeline is generally not easy to bend.
And (5): referring to fig. 7, according to the average radius and the circle center obtained by calculation, the pipeline is three-dimensionally reconstructed by using the alphaShape algorithm to the point cloud, so as to obtain a three-dimensional image of the submarine pipeline. Fig. 7 is a result of three-dimensional reconstruction of a pipeline, in which fig. 7(a) is a side view of the pipeline and fig. 7(b) is a cross-sectional view of the pipeline. From the results, the treatment method of the invention can obtain good pipeline reconstruction effect.
Claims (2)
1. A submarine pipeline detection and three-dimensional reconstruction method based on multi-beam point cloud is characterized by comprising the following steps:
the method comprises the following steps: classifying and extracting image pixel points by adopting a threshold value method and a canny edge detection method according to an underwater sonar image obtained by detecting a pipeline by using a multi-beam sounding sonar to obtain three-dimensional point cloud data of the pipeline;
step two: setting different initial radiuses R and minimum neighborhood number k by adopting a point cloud denoising and filtering method based on density analysis according to the three-dimensional point cloud data of the pipeline to obtain the three-dimensional point cloud data of the pipeline after filtering and denoising;
the point cloud denoising and filtering method based on density analysis specifically comprises the following steps:
defining a spherical area with the radius of R by taking a certain point in the point clouds as the center of sphere, inquiring the number of the point clouds in the spherical area, defining a point cloud neighbor number k, and deleting the point clouds of which the number is less than k in the spherical area as noise, otherwise, keeping the point clouds; the point cloud denoising and filtering method based on density analysis is carried out twice, the initial radius R and the minimum neighborhood number k are adjusted, and a noise cluster far away from a pipeline and a sparse noise point close to the pipeline are filtered respectively;
step three: performing circle fitting on the point cloud data of each section of the pipeline by adopting a histogram-based statistical method and a spatial linear fitting method according to the three-dimensional point cloud data of the filtered and denoised pipeline to obtain the radius of a fitting circle and a linearly-changed central point;
the form of each section of the pipeline is priori knowledge; the method comprises the steps of solving the average value of the radius of a fitting circle obtained after fitting a point cloud data circle of each section based on a histogram statistical method to obtain the average radius of the fitting circle; the space linear fitting method is used for fitting a circle center point set of a fitting circle obtained after the point cloud data circle of each section is fitted to obtain a linearly-changed circle center point and the direction information of the pipeline;
step four: and performing three-dimensional reconstruction on the pipeline by adopting an alphaShape algorithm according to the radius of the fitting circle and the linearly changed central point to obtain a three-dimensional image of the pipeline.
2. The method for submarine pipeline detection and three-dimensional reconstruction based on multi-beam point cloud according to claim 1, wherein the first step comprises:
classifying and extracting image pixel points by adopting a threshold value method and a canny edge detection method according to an underwater sonar image obtained by a multi-beam sounding sonar detection pipeline; the underwater sonar image obtained by the multi-beam sounding sonar detection pipeline does not use a through-bottom detection method but directly extracts pixel points; the threshold value method carries out binarization processing on the pixel points to obtain two types of pixel points with different setting values; the canny edge detection method carries out edge detection processing on all pixel points and extracts the boundary points of the pipeline in the sonar image; converting the boundary points of the pipeline into space coordinates to obtain three-dimensional point cloud data of the pipeline;
among the space coordinates, the positive direction of the X axis is the multi-beam sonar advancing direction:
x＝t*v
wherein, x is the abscissa of the point cloud, v is the sonar moving speed, and t represents the interval time of acquiring an image by the multi-beam sonar;
the Y-axis and Z-axis coordinates of the point cloud space rectangular coordinate system correspond to the horizontal and vertical coordinates of a single sonar image, the Y-axis represents the vertical direction of a sonar track, and the Z-axis represents the normal vector direction of the ground.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810758534.9A CN109035224B (en) | 2018-07-11 | 2018-07-11 | Submarine pipeline detection and three-dimensional reconstruction method based on multi-beam point cloud |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810758534.9A CN109035224B (en) | 2018-07-11 | 2018-07-11 | Submarine pipeline detection and three-dimensional reconstruction method based on multi-beam point cloud |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109035224A CN109035224A (en) | 2018-12-18 |
| CN109035224B true CN109035224B (en) | 2021-11-09 |
Family
ID=64640869
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810758534.9A Active CN109035224B (en) | 2018-07-11 | 2018-07-11 | Submarine pipeline detection and three-dimensional reconstruction method based on multi-beam point cloud |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109035224B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110109142B (en) * | 2019-04-04 | 2021-04-02 | 深圳市速腾聚创科技有限公司 | Point cloud filtering method and device, computer equipment and storage medium |
| CN110533650B (en) * | 2019-08-28 | 2022-12-13 | 哈尔滨工程大学 | AUV underwater pipeline detection tracking method based on vision |
| CN111238386B (en) * | 2019-11-26 | 2021-09-21 | 中国航空工业集团公司北京长城计量测试技术研究所 | Method for measuring minimum spacing of engine pipelines |
| CN111144318B (en) * | 2019-12-27 | 2023-08-29 | 苏州联视泰电子信息技术有限公司 | Noise reduction method for point cloud data of underwater sonar system |
| CN111429563B (en) * | 2020-03-10 | 2021-08-13 | 山东大学 | Pipeline three-dimensional reconstruction method, system, medium and equipment based on deep learning |
| CN111899326A (en) * | 2020-06-18 | 2020-11-06 | 苏州小优智能科技有限公司 | Three-dimensional reconstruction method based on GPU parallel acceleration |
| CN112529841B (en) * | 2020-11-16 | 2023-01-31 | 中国海洋大学 | Method and system for processing seabed gas plume in multi-beam water column data and application |
| CN113256697B (en) * | 2021-04-27 | 2023-07-18 | 武汉理工大学 | Three-dimensional reconstruction method, system, device and storage medium for underwater scene |
| CN113567968B (en) * | 2021-05-25 | 2024-04-16 | 自然资源部第一海洋研究所 | Underwater target real-time segmentation method based on shallow water multi-beam water depth data and application thereof |
| CN114800520B (en) * | 2022-05-23 | 2024-01-23 | 北京迁移科技有限公司 | High-precision hand-eye calibration method |
| JP2023179840A (en) * | 2022-06-08 | 2023-12-20 | 川崎重工業株式会社 | Image generation system, object discrimination system, and image generation method |
| CN115880189B (en) * | 2023-02-22 | 2023-05-30 | 山东科技大学 | Multi-beam point cloud filtering method for submarine topography |
| CN115932864B (en) * | 2023-02-24 | 2023-08-01 | 深圳市博铭维技术股份有限公司 | Pipeline defect detection method and pipeline defect detection device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001094827A3 (en) * | 2000-06-07 | 2002-04-18 | Coflexip | Subsea pipeline touchdown monitoring |
| CN102915561A (en) * | 2012-09-27 | 2013-02-06 | 清华大学 | Method of three-dimensional reconstruction for pipeline structures |
| CN104075072A (en) * | 2014-07-17 | 2014-10-01 | 国家海洋技术中心 | Submarine pipeline detection device based on ROV platform |
| CN105096268A (en) * | 2015-07-13 | 2015-11-25 | 西北农林科技大学 | Denoising smoothing method of point cloud |
| CN105182350A (en) * | 2015-09-26 | 2015-12-23 | 哈尔滨工程大学 | Multi-beam sonar target detection method by applying feature tracking |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8958911B2 (en) * | 2012-02-29 | 2015-02-17 | Irobot Corporation | Mobile robot |
-
2018
- 2018-07-11 CN CN201810758534.9A patent/CN109035224B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001094827A3 (en) * | 2000-06-07 | 2002-04-18 | Coflexip | Subsea pipeline touchdown monitoring |
| CN102915561A (en) * | 2012-09-27 | 2013-02-06 | 清华大学 | Method of three-dimensional reconstruction for pipeline structures |
| CN104075072A (en) * | 2014-07-17 | 2014-10-01 | 国家海洋技术中心 | Submarine pipeline detection device based on ROV platform |
| CN105096268A (en) * | 2015-07-13 | 2015-11-25 | 西北农林科技大学 | Denoising smoothing method of point cloud |
| CN105182350A (en) * | 2015-09-26 | 2015-12-23 | 哈尔滨工程大学 | Multi-beam sonar target detection method by applying feature tracking |
Non-Patent Citations (5)
| Title |
|---|
| AUTONOMOUS MODELING OF PIPES WITHIN POINT CLOUDS;Mahmoud Ahmed et al.;《ISARC 2013》;20131231;第3-5页 * |
| Three-dimensional reconstruction of underwater objects using wide-aperture imaging SONAR;Thomas Guerneve et al.;《J Field Robotics》;20180331;第892-902页 * |
| 双光斑中心识别算法比较;冯驰等;《应用科技》;20090831;第36卷(第8期);第21-24页 * |
| 多尺度点云噪声检测的密度分析法;朱俊锋等;《测绘学报》;20150331;第44卷(第3期);第283-286页 * |
| 水中气体目标的多波束声呐成像与检测算法;蒲定等;《应用科技》;20171031;第44卷(第 5 期);第13-15页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109035224A (en) | 2018-12-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109035224B (en) | Submarine pipeline detection and three-dimensional reconstruction method based on multi-beam point cloud | |
| CN109903327B (en) | Target size measurement method of sparse point cloud | |
| CN107145874B (en) | Ship target detection and identification method in complex background SAR image | |
| CN108986048B (en) | Three-dimensional point cloud rapid composite filtering processing method based on line laser scanning | |
| CN109816664B (en) | Three-dimensional point cloud segmentation method and device | |
| CN103870845A (en) | Novel K value optimization method in point cloud clustering denoising process | |
| CN103292792B (en) | Actual measurement SVP reconstruction method suitable for submarine detection and pseudo-landform processing | |
| CN101832470A (en) | Method and device for polling underwater lines based on light vision sensing | |
| CN201680157U (en) | Apparatus for checking underwater pipeline based on light vision | |
| CN111723821A (en) | Detection and identification method and device for power plant instrument image | |
| CN110533650B (en) | AUV underwater pipeline detection tracking method based on vision | |
| CN113034569A (en) | Point cloud data-based ship overrun early warning method and system | |
| CN111340834B (en) | Lining plate assembly system and method based on laser radar and binocular camera data fusion | |
| CN115482211A (en) | Tunnel overbreak and underexcavation detection method and device, electronic equipment and storage medium | |
| CN113899349B (en) | Sea wave parameter detection method, equipment and storage medium | |
| CN108734731B (en) | Machine vision-based quasi-circular particle target counting method | |
| CN108320291A (en) | Submarine geomorphy boundary extraction method based on Otsu algorithm | |
| CN113848209B (en) | Dam crack detection method based on unmanned aerial vehicle and laser ranging | |
| CN117291942A (en) | Coastline extraction method for satellite remote sensing land surface water body data | |
| CN116579949A (en) | Airborne point cloud ground point filtering method suitable for urban multi-noise environment | |
| CN116416589A (en) | Rail point cloud extraction method based on rail data and geometric properties | |
| CN113591740B (en) | Deep learning-based sediment particle identification method and device in complex river environment | |
| CN113567968B (en) | Underwater target real-time segmentation method based on shallow water multi-beam water depth data and application thereof | |
| CN111598901B (en) | Method for estimating processing progress of dental restoration product based on depth image | |
| Wang et al. | Deep Learning-Based Semantic Segmentation and Surface Reconstruction for Point Clouds of Offshore Oil Production Equipment |
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 |