CN112859006A - Method for detecting metal curved cylindrical structure in multi-channel ground penetrating radar data - Google Patents
Method for detecting metal curved cylindrical structure in multi-channel ground penetrating radar data Download PDFInfo
- Publication number
- CN112859006A CN112859006A CN202110032021.1A CN202110032021A CN112859006A CN 112859006 A CN112859006 A CN 112859006A CN 202110032021 A CN202110032021 A CN 202110032021A CN 112859006 A CN112859006 A CN 112859006A
- Authority
- CN
- China
- Prior art keywords
- target
- cylindrical structure
- radar data
- metal
- bscan
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/30—Assessment of water resources
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses a method for detecting a metal curved cylindrical structure in multi-channel ground penetrating radar data, which comprises the following steps: acquiring m multiplied by c radar data bscan in an area to be detected; preprocessing any radar data bscan and performing visualization processing; arranging any radar data batch, and obtaining n bscan images according to the positions of the radar data bscan in the radar data batch; performing two-dimensional hyperbolic curve detection on any image img _ i, and obtaining k metal cylindrical structure targets; carrying out actual coordinate conversion on the metal cylindrical structure Target _ i _ u to obtain the position information of the metal cylindrical structure Target _ i _ u in the region; recording a target Set of a metal cylindrical structure in the image img _ i as Set _ i, and performing two-dimensional hyperbolic curve detection on the ith bscan image to obtain n sets; and traversing the metal cylindrical structure targets in sequence, and searching the two-dimensional target by adopting a target position projection and area mode to complete the three-dimensional target search.
Description
Technical Field
The invention relates to the technical field of radar data processing, in particular to a method for detecting a metal curved cylindrical structure in multi-channel ground penetrating radar data.
Background
The position corresponding to the metal cylindrical structure in the ground penetrating radar slice image presents an obvious hyperbolic structure, and whether a steel bar or a pipeline (hollow) is distinguished at the position. On multichannel ground penetrating radar equipment, multichannel shallow layer ground penetrating radar during operation hangs on carrying equipment, advances forward simultaneously by carrying equipment a plurality of passageways, assumes to the radar equipment of m passageway, and m can be more than or equal to 1 any integer, and when m was 1, is single channel ground penetrating radar.
In general, the ground penetrating radar works by performing full coverage detection on a region, and each detection is performed by generating m channel radar data bscan by a single travel, which is denoted as 1 group of batchs, and in general, in the multi-channel ground penetrating radar detection, the number of axial scan data ascans contained in all bscans in the same batch is the same, while in the full coverage detection, the number of ascans contained in radar data bscans in two different batches is different, which is the case shown in fig. 1. The multi-channel ground penetrating radar detects the area back and forth c times to generate c groups of batch data, namely c multiplied by m radar data bscan, namely radar data of a cube, wherein each bscan data is composed of a plurality of ascan data, each ascan is composed of a plurality of data sampled downwards, each sampled data comprises position information and strength information of radar echo, the radar echo represents the condition of an underground target, and the radar echo data of a single bscan is visualized as shown in figure 2.
At present, in the prior art, analysis of multi-channel shallow ground penetrating radar data is generally performed on each slice, and then slice analysis results are integrated to obtain a real three-dimensional geological target detection result, and a metal cylindrical structure target presents an obvious hyperbolic characteristic in a radar slice, as shown in fig. 3. Currently, the automatic detection of underground targets with metal cylindrical structures mainly focuses on the detection of a single bscan, such as mao xing peng "a fast detection method for hyperbolic targets of ground penetrating radar", which mainly performs visualization processing on ground penetrating radar data (with high probability, bscan data) to perform edge detection, performs visualization processing on radar signals to perform edge processing again, and searches for hyperbolic targets after combination, at this time, there is a cluster of hyperbolic results, it is necessary to combine dielectric constant information with the hyperbolic results, extracts from the cluster of hyperbolic results, hyperbolic fixed points and several hyperbolic curves are reflection images belonging to the same steel bar, and obtains n steel bars and fixed point positions thereof, the method is based on a classical image processing algorithm, extracts hyperbolic information in the bscan radar signals, and obtains a plurality of two-dimensional results, but the hyperbolic targets are not necessarily steel bar targets, a metal nut screw (one bit larger) in the ground penetrating radar scan address will also travel the hyperbolic result on the bscan image.
For another Chinese patent with the patent application number of '202010493228.4' and the name of 'an intelligent concrete reinforcing steel bar positioning method based on ground penetrating radar and deep learning', the situation is almost the same as that of 'a method for quickly detecting hyperbolic targets by ground penetrating radar', ssd which is a method for detecting targets based on deep learning is used, and finally, the positions (vertexes) of the hyperbolic targets are also determined, so that how deep the hyperbolic targets are in the ground is determined.
For example, Hatong, "overview of hyperbolic-oriented ground penetrating radar image recognition technology", which summarizes hyperbolic targets currently detected in a bscan image, includes a deep learning method (e.g., "202010493228.4"), and also includes a method based on image processing (e.g., a method for rapidly detecting hyperbolic targets by a ground penetrating radar), but this method is also based on results of the bscan image and is two-dimensional.
In the actual situation, whether the method of classical image processing or deep learning is used, the target detection is carried out on a single bscan image, and because the radar slice image represents the target through the strength of electromagnetic reflected waves, and the actual situation under the road is very complicated, a plurality of false targets exist, and a very obvious hyperbolic characteristic is presented in the single bscan slice image.
Therefore, a method for detecting a metal curved cylindrical structure in multi-channel ground penetrating radar data, which is simple in logic, accurate and reliable, is urgently needed.
Disclosure of Invention
Aiming at the problems, the invention aims to provide a method for detecting a metal curved cylindrical structure in multi-channel ground penetrating radar data, and the technical scheme adopted by the invention is as follows:
a method for detecting a metal curved cylindrical structure in multi-channel ground penetrating radar data comprises the following steps:
in an area to be detected, grid-shaped turning back detection is performed for c times along the parallel direction by adopting an m-channel ground penetrating radar, and m multiplied by c radar data bscan be obtained; the m radar data bscan form a radar data batch; the c radar data batch form radar data cscan of the area to be detected; the radar data cscan is equal to m × c radar data bscan; both m and c are integers greater than 1;
preprocessing any radar data bscan and performing visualization processing;
arranging any one of the radar data batch, and performing grid-shaped adjacent pairwise connection on the 2 nd radar data bscan to the (m-1) th radar data bscan in the radar data batch according to the position of the radar data bscan in the radar data batch to obtain n bscan images, wherein any one of the bscan images is img _ i, and i is more than 0 and less than or equal to n;
performing two-dimensional hyperbolic curve detection on any image img _ i, obtaining k metal cylindrical structure targets, and recording any metal cylindrical structure Target as Target _ i _ u, wherein u is more than 0 and is not more than k;
carrying out actual coordinate conversion on the metal cylindrical structure Target _ i _ u to obtain the position information of the metal cylindrical structure Target _ i _ u in the region; the position information comprises the center point coordinate, the height, the width and the vector information of a space plane of the Target i _ u with the metal cylindrical structure in the region;
recording a target Set of a metal cylindrical structure in the image img _ i as Set _ i, and performing two-dimensional hyperbolic curve detection on the ith bscan image to obtain n sets;
sequentially traversing the metal cylindrical structure targets from the metal cylindrical structure target Set _1, projecting the positions of the metal cylindrical structure targets which are Set _ (j-1) in the metal cylindrical structure target Set to the images of the Set _ j in the metal cylindrical structure target Set, and searching the two-dimensional targets in an area mode until any image img _ i finishes searching, finishing three-dimensional target searching, so as to obtain the three-dimensional structure of the metal cylindrical structure; j is an integer greater than 1, and less than or equal to mxc.
Further, the step of sequentially traversing the metal cylindrical structure targets from the Set _1 of the metal cylindrical structure target Set, projecting the positions of the metal cylindrical structure targets of the Set _ (j-1) of the metal cylindrical structure target Set to the image where the Set _ j of the metal cylindrical structure target Set is located, and searching for the two-dimensional target in an area manner includes the following steps:
sequentially traversing the metal cylindrical structure targets in any metal cylindrical structure target Set _ i from the metal cylindrical structure target Set _1,
marking the Target of the j-1 th metal cylindrical structure Target set as Target (j-1) p(j-1)；p(j-1)Is an integer which is more than 1 and less than the total number of targets of the j-1 th metal cylindrical structure target set; the Target (j-1) p(j-1)The corresponding position information in the area is Rect (j-1) p(j-1)；
Marking the Target of the jth metal cylindrical structure Target set as Target _ j _ pj；pjIs an integer which is more than 1 and less than the total number of targets of the jth metal-like cylindrical structure target set; the Target _ j _ pjThe corresponding position information in the region is Rect _ j _ pj；
If the Target (j-1) _ p(j-1)And Target _ j _ pjThe position information Rect _ j _ p is adjacent in a grid shapejProjected to position information Rect (j-1) p(j-1)The plane is located, and projection position information Rect _ j _ p is obtainedj_proj；
Obtaining position information Rect (j-1) p(j-1)And projection position information Rect _ j _ pjThe intersection area iSize of _ proj;
obtaining position information Rect (j-1) p(j-1)And projection position information Rect _ j _ pjA union area uSize of _ proj;
and obtaining the ratio of the intersection area iSize to the union area uSize, and if the ratio is greater than a preset threshold value thresh, determining that the ratio is a two-dimensional target detected at the same position by the adjacent radar data bscan in the same radar data batch.
Further, the three-dimensional target search comprises the following steps:
obtaining a direction vector included angle of a plane where the two-dimensional target is located, and normalizing to be 0-pi/2;
if the normalized direction vector included angle is smaller than a preset angle threshold angleThresh, the three-dimensional Target Pip3d is recorded as { Target _ (j-1) _ p }(j-1),Target_j_pj}；
Until the three-dimensional target search is completed.
Preferably, the threshold thresh is 0.2.
Preferably, the angle threshold angleThresh takes the value of
Preferably, any radar data bscan is preprocessed, and the preprocessing comprises zero offset adjustment, zero point adjustment, filtering and gain adjustment.
Preferably, two-dimensional hyperbolic curve detection is performed on any image img _ i using FRCNN.
Compared with the prior art, the invention has the following beneficial effects:
(1) the invention skillfully adopts the position projection and area ratio judgment of the metal cylindrical structure target to realize the search of the two-dimensional target, and has the advantages that whether the space positions of two-dimensional detection targets respectively belonging to adjacent bscan are adjacent or not is judged, namely the adjacent two-dimensional detection targets belong to the same three-dimensional target;
(2) the method adopts the direction vector included angle of the plane where the two-dimensional target is located to search the three-dimensional target, and has the advantages that whether the directions of the two-dimensional targets belonging to the adjacent bscan are consistent or not is judged, and the pipeline is considered to be continuous without violent turning;
in conclusion, the method has the advantages of simple logic, accuracy, reliability and the like, and has high practical value and popularization value in the technical field of radar data processing.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention, and therefore should not be considered as limiting the scope of protection, and it is obvious for those skilled in the art that other related drawings can be obtained according to these drawings without inventive efforts.
Fig. 1 is a diagram of prior art ground detection radar data.
FIG. 2 is a graph of prior art echo data.
Fig. 3 is a hyperbolic characteristic diagram in the prior art.
Fig. 4 is a diagram of target location information according to the present invention.
Fig. 5 is a projected image of the present invention.
FIG. 6 is a schematic diagram of two-dimensional object search according to the present invention.
Detailed Description
To further clarify the objects, technical solutions and advantages of the present application, the present invention will be further described with reference to the accompanying drawings and examples, and embodiments of the present invention include, but are not limited to, the following examples. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Examples
As shown in fig. 4 to 6, the present embodiment provides a method for detecting a metal-like curved cylindrical structure in multi-channel ground penetrating radar data, including the following steps:
firstly, in an area to be detected, performing grid-shaped turn-back detection for c times along the parallel direction by using an m-channel ground penetrating radar to obtain mxc radar data bscan; the m radar data bscan form a radar data batch; the c radar data batch form radar data cscan of the area to be detected; the radar data cscan is equal to m × c radar data bscan; both m and c are integers greater than 1; in this embodiment, m is 7.
And secondly, preprocessing (adjusting zero offset, adjusting zero point, filtering and adjusting gain) any radar data bscan, and performing visualization processing.
Thirdly, arranging any one of the radar data batch, and performing grid-shaped adjacent pairwise connection on the 2 nd radar data bscan to the (m-1) th radar data bscan in the radar data batch according to the position of the radar data bscan in the radar data batch to obtain n bscan images, wherein any one of the bscan images is img _ i, and i is more than 0 and less than or equal to n; in this case, it is not distinguished whether or not the bscan of the entire detection data participates in the raster-like adjacent arrangement.
Fourthly, performing two-dimensional hyperbolic curve detection on any image img _ i, obtaining k metal cylindrical structure targets, and recording any metal cylindrical structure Target as Target _ i _ u, wherein u is more than 0 and is not more than k; in this embodiment, the two-dimensional hyperbolic detection may adopt a classical image processing algorithm (e.g., "a method for rapidly detecting hyperbolic target of ground penetrating radar"), or may adopt a deep learning manner without limitation.
Fifthly, carrying out actual coordinate conversion on the Target _ i _ u with the metal cylindrical structure to obtain the position information of the Target _ i _ u with the metal cylindrical structure in the region; the position information comprises the center point coordinate, the height, the width and the vector information of a space plane of the metal cylindrical structure Target i _ u in the region. In the embodiment, the object is detected in the bscan image, only the position on the image is initially, namely a frame, the frame comprises a starting point and a width and a height, and since the bscan image is actually obtained by visualizing one bscan radar data, each image coordinate is the real coordinate of the multi-win bscan radar data, and the detection result is converted into a real coordinate system.
Sixthly, recording a target Set of the metal cylindrical structure in the image img _ i as Set _ i, and performing two-dimensional hyperbolic curve detection on the ith bscan image to obtain m sets;
step seven, sequentially traversing the metal cylindrical structure targets from the metal cylindrical structure target Set _1, projecting the positions of the metal cylindrical structure targets which are Set _ (j-1) to the images of the metal cylindrical structure target Set _, and searching the two-dimensional targets in an area mode until any image img _ i completes the search, completing the three-dimensional target search, so as to obtain the three-dimensional structure of the metal cylindrical structure; specifically, searching for a two-dimensional target comprises the following steps:
(11) sequentially traversing the metal cylindrical structure targets in any metal cylindrical structure target Set _ i from the metal cylindrical structure target Set _1,
(12) marking the Target of the j-1 th metal cylindrical structure Target set as Target (j-1) p(j-1)； p(j-1)Is an integer which is more than 1 and less than the total number of targets of the j-1 th metal cylindrical structure target set; the Target (j-1) p(j-1)The corresponding position information in the area is Rect (j-1) p(j-1)；
(13) Marking the Target of the jth metal cylindrical structure Target set as Target _ j _ pj；pjIs an integer which is more than 1 and less than the total number of targets of the jth metal-like cylindrical structure target set; the Target _ j \ujThe corresponding position information of p in the region is Rect _ j _ pj；
(14) Position information Rect _ j _ pjProjected to position information Rect (j-1) p(j-1)The plane is located, and projection position information Rect _ j _ p is obtainedj_proj；
(15) Obtaining position information Rect (j-1) p(j-1)And projection position information Rect _ j _ pjThe intersection area iSize of _ proj;
(16) obtaining position information Rect (j-1) p(j-1)And projection position information Rect _ j _ pjA union area uSize of _ proj;
(17) and obtaining the ratio of the intersection area iSize to the union area uSize, and if the ratio is greater than a preset threshold value thresh, determining that the ratio is a two-dimensional target detected at the same position by the adjacent radar data bscan in the same radar data batch. In this embodiment, the threshold thresh is 0.2 to adapt to a curve pipeline and a curve task, and the two-dimensional target overlapping area of adjacent bscans is small.
In addition, the three-dimensional target search comprises the following steps:
(21) obtaining a direction vector angle of a plane where the two-dimensional target is located (namely obtaining the direction vector angle according to vector information of a space plane), and normalizing to 0-pi/2;
(22) if the normalized direction vector included angle is smaller than a preset angle threshold angleThresh, the three-dimensional Target Pip3d is recorded as { Target _ (j-1) _ p }(j-1),Target_j_pj}; wherein the angle threshold angleThresh takes the value of
(23) Until the three-dimensional target search is completed.
The above-mentioned embodiments are only preferred embodiments of the present invention, and do not limit the scope of the present invention, but all the modifications made by the principles of the present invention and the non-inventive efforts based on the above-mentioned embodiments shall fall within the scope of the present invention.
Claims (7)
1. A method for detecting a metal curved cylindrical structure in multi-channel ground penetrating radar data is characterized by comprising the following steps:
in an area to be detected, grid-shaped turning back detection is performed for c times along the parallel direction by adopting an m-channel ground penetrating radar, and m multiplied by c radar data bscan be obtained; the m radar data bscan form a radar data batch; the c radar data batch form radar data cscan of the area to be detected; the radar data cscan is equal to m × c radar data bscan; both m and c are integers greater than 1;
preprocessing any radar data bscan and performing visualization processing;
arranging any one of the radar data batch, and performing grid-shaped adjacent pairwise connection on the 2 nd radar data bscan to the (m-1) th radar data bscan in the radar data batch according to the position of the radar data bscan in the radar data batch to obtain n bscan images, wherein any one of the bscan images is img _ i, and i is more than 0 and less than or equal to n;
performing two-dimensional hyperbolic curve detection on any image img _ i, obtaining k metal cylindrical structure targets, and recording any metal cylindrical structure Target as Target _ i _ u, wherein u is more than 0 and is not more than k;
carrying out actual coordinate conversion on the metal cylindrical structure Target _ i _ u to obtain the position information of the metal cylindrical structure Target _ i _ u in the region; the position information comprises the center point coordinate, the height, the width and the vector information of a space plane of the Target i _ u with the metal cylindrical structure in the region;
recording a target Set of a metal cylindrical structure in the image img _ i as Set _ i, and performing two-dimensional hyperbolic curve detection on the ith bscan image to obtain n sets;
sequentially traversing the metal cylindrical structure targets from the metal cylindrical structure target Set _1, projecting the positions of the metal cylindrical structure targets which are Set _ (j-1) in the metal cylindrical structure target Set to the images of the Set _ j in the metal cylindrical structure target Set, and searching the two-dimensional targets in an area mode until any image img _ i finishes searching, finishing three-dimensional target searching, so as to obtain the three-dimensional structure of the metal cylindrical structure; and j is an integer greater than 1 and less than or equal to mxc.
2. The method for detecting the metal-like curved cylindrical structure in the multi-channel ground penetrating radar data according to claim 1, wherein the steps of sequentially traversing the metal-like cylindrical structure targets from the Set _1 of metal-like cylindrical structure targets, projecting the positions of the metal-like cylindrical structure targets of the Set _ (j-1) of the Set _1 of metal-like cylindrical structure targets into the image where the Set _ j of metal-like cylindrical structure targets are located, and searching for the two-dimensional target in an area manner comprise:
sequentially traversing the metal cylindrical structure targets in any metal cylindrical structure target Set _ i from the metal cylindrical structure target Set _1,
marking the Target of the j-1 th metal cylindrical structure Target set as Target (j-1) p(j-1)；p(j-1)Is an integer which is more than 1 and less than the total number of targets of the j-1 th metal cylindrical structure target set; the Target (j-1) p(j-1)The corresponding position information in the area is Rect (j-1) p(j-1)；
Marking the Target of the jth metal cylindrical structure Target set as Target _ j _ pj；pjIs an integer which is more than 1 and less than the total number of targets of the jth metal-like cylindrical structure target set; the Target _ j _ pjThe corresponding position information in the region is Rect _ j _ pj；
If the Target (j-1) _ p(j-1)And Target _ j _ pjThe position information Rect _ j _ p is adjacent in a grid shapejProjected to position information Rect (j-1) p(j-1)The plane is located, and projection position information Rect _ j _ p is obtainedj_proj；
Obtaining position information Rect (j-1) p(j-1)And projection position information Rect _ j _ pjThe intersection area iSize of _ proj;
obtaining position information Rect (j-1) p(j-1)And projection position information Rect _ j _ pjA union area uSize of _ proj;
and obtaining the ratio of the intersection area iSize to the union area uSize, and if the ratio is greater than a preset threshold value thresh, determining that the ratio is a two-dimensional target detected at the same position by the adjacent radar data bscan in the same radar data batch.
3. The method for detecting the metal-like curved cylindrical structure in the multi-channel ground penetrating radar data as claimed in claim 2, wherein the three-dimensional target searching comprises the following steps:
obtaining a direction vector included angle of a plane where the two-dimensional target is located, and normalizing to be 0-pi/2;
if the normalized direction vector included angle is smaller than a preset angle threshold angleThresh, the three-dimensional Target Pip3d is recorded as { Target _ (j-1) _ p }(j-1),Target_j_pj}；
Until the three-dimensional target search is completed.
4. The method of claim 2, wherein the threshold thresh is 0.2.
5. The method as claimed in claim 3, wherein the angle threshold angleThresh is set to a value of
6. The method of claim 1, wherein any radar data bscan be preprocessed, and the preprocessing comprises zero offset adjustment, zero point adjustment, filtering and gain adjustment.
7. The method for detecting the metal-like curved cylindrical structure in the multi-channel ground penetrating radar data as claimed in claim 1, wherein two-dimensional hyperbolic curve detection is performed on any image img _ i by using FRCNN.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110032021.1A CN112859006B (en) | 2021-01-11 | 2021-01-11 | Method for detecting metal bending cylindrical structure in multichannel ground penetrating radar data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110032021.1A CN112859006B (en) | 2021-01-11 | 2021-01-11 | Method for detecting metal bending cylindrical structure in multichannel ground penetrating radar data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112859006A true CN112859006A (en) | 2021-05-28 |
| CN112859006B CN112859006B (en) | 2023-08-29 |
Family
ID=76002449
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110032021.1A Active CN112859006B (en) | 2021-01-11 | 2021-01-11 | Method for detecting metal bending cylindrical structure in multichannel ground penetrating radar data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112859006B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113655477A (en) * | 2021-06-11 | 2021-11-16 | 成都圭目机器人有限公司 | Method for automatically detecting geological diseases of land radar by adopting shallow layer |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012024133A2 (en) * | 2010-08-20 | 2012-02-23 | Niitek, Inc. | Metal detector and ground-penetrating radar hybrid head and manufacturing method thereof |
| CN106291494A (en) * | 2016-07-21 | 2017-01-04 | 深圳大学 | The SAR cheating interference target identification method and system strengthened based on differential characteristics |
| CN106446919A (en) * | 2016-11-04 | 2017-02-22 | 深圳市航天华拓科技有限公司 | Quick detection method for ground penetrating radar hyperbolic curve target |
| WO2017120897A1 (en) * | 2016-01-15 | 2017-07-20 | 武汉武大卓越科技有限责任公司 | Object surface deformation feature extraction method based on line scanning three-dimensional point cloud |
| CN107346023A (en) * | 2017-07-04 | 2017-11-14 | 山东工商学院 | A kind of GPR hyperbolic ripple conspicuousness mapping method based on moment characteristics |
| CN107358617A (en) * | 2017-08-07 | 2017-11-17 | 中南大学 | The detection method of representative points in a kind of GPR record section |
| CN107621626A (en) * | 2017-10-09 | 2018-01-23 | 中国矿业大学(北京) | Radar signal Railway Roadbed detection method based on depth convolutional neural networks |
| CN108037490A (en) * | 2017-11-30 | 2018-05-15 | 中煤航测遥感集团有限公司 | Ground Penetrating Radar Linear Positioning Accuracy Measurement Methods and system |
| CN108153306A (en) * | 2017-12-19 | 2018-06-12 | 成都圭目机器人有限公司 | A kind of autonomous road lossless detection method of robot system |
| CN108665530A (en) * | 2018-04-25 | 2018-10-16 | 厦门大学 | Three-dimensional modeling implementation method based on single picture |
| EP3525000A1 (en) * | 2018-02-09 | 2019-08-14 | Bayerische Motoren Werke Aktiengesellschaft | Methods and apparatuses for object detection in a scene based on lidar data and radar data of the scene |
| CN110866545A (en) * | 2019-10-30 | 2020-03-06 | 中国地质大学（武汉） | Method and system for automatically identifying pipeline target in ground penetrating radar data |
| CN111027401A (en) * | 2019-11-15 | 2020-04-17 | 电子科技大学 | End-to-end target detection method with integration of camera and laser radar |
| CN111551927A (en) * | 2020-05-19 | 2020-08-18 | 上海圭目机器人有限公司 | Underground pipeline diameter measuring method based on three-dimensional ground penetrating radar |
| CN111582256A (en) * | 2020-04-26 | 2020-08-25 | 智慧互通科技有限公司 | Parking management method and device based on radar and visual information |
| CN111932617A (en) * | 2020-07-15 | 2020-11-13 | 中国科学院上海微系统与信息技术研究所 | Method and system for realizing real-time detection and positioning of regular object |
| CN112130132A (en) * | 2020-09-11 | 2020-12-25 | 广州大学 | Underground pipeline detection method and system based on ground penetrating radar and deep learning |
-
2021
- 2021-01-11 CN CN202110032021.1A patent/CN112859006B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012024133A2 (en) * | 2010-08-20 | 2012-02-23 | Niitek, Inc. | Metal detector and ground-penetrating radar hybrid head and manufacturing method thereof |
| WO2017120897A1 (en) * | 2016-01-15 | 2017-07-20 | 武汉武大卓越科技有限责任公司 | Object surface deformation feature extraction method based on line scanning three-dimensional point cloud |
| CN106291494A (en) * | 2016-07-21 | 2017-01-04 | 深圳大学 | The SAR cheating interference target identification method and system strengthened based on differential characteristics |
| CN106446919A (en) * | 2016-11-04 | 2017-02-22 | 深圳市航天华拓科技有限公司 | Quick detection method for ground penetrating radar hyperbolic curve target |
| CN107346023A (en) * | 2017-07-04 | 2017-11-14 | 山东工商学院 | A kind of GPR hyperbolic ripple conspicuousness mapping method based on moment characteristics |
| CN107358617A (en) * | 2017-08-07 | 2017-11-17 | 中南大学 | The detection method of representative points in a kind of GPR record section |
| CN107621626A (en) * | 2017-10-09 | 2018-01-23 | 中国矿业大学(北京) | Radar signal Railway Roadbed detection method based on depth convolutional neural networks |
| CN108037490A (en) * | 2017-11-30 | 2018-05-15 | 中煤航测遥感集团有限公司 | Ground Penetrating Radar Linear Positioning Accuracy Measurement Methods and system |
| CN108153306A (en) * | 2017-12-19 | 2018-06-12 | 成都圭目机器人有限公司 | A kind of autonomous road lossless detection method of robot system |
| EP3525000A1 (en) * | 2018-02-09 | 2019-08-14 | Bayerische Motoren Werke Aktiengesellschaft | Methods and apparatuses for object detection in a scene based on lidar data and radar data of the scene |
| CN108665530A (en) * | 2018-04-25 | 2018-10-16 | 厦门大学 | Three-dimensional modeling implementation method based on single picture |
| CN110866545A (en) * | 2019-10-30 | 2020-03-06 | 中国地质大学（武汉） | Method and system for automatically identifying pipeline target in ground penetrating radar data |
| CN111027401A (en) * | 2019-11-15 | 2020-04-17 | 电子科技大学 | End-to-end target detection method with integration of camera and laser radar |
| CN111582256A (en) * | 2020-04-26 | 2020-08-25 | 智慧互通科技有限公司 | Parking management method and device based on radar and visual information |
| CN111551927A (en) * | 2020-05-19 | 2020-08-18 | 上海圭目机器人有限公司 | Underground pipeline diameter measuring method based on three-dimensional ground penetrating radar |
| CN111932617A (en) * | 2020-07-15 | 2020-11-13 | 中国科学院上海微系统与信息技术研究所 | Method and system for realizing real-time detection and positioning of regular object |
| CN112130132A (en) * | 2020-09-11 | 2020-12-25 | 广州大学 | Underground pipeline detection method and system based on ground penetrating radar and deep learning |
Non-Patent Citations (6)
| Title |
|---|
| 卢丹丹: "城市地下管线三维建模关键技术研究", 《测绘通报》, no. 5, pages 117 - 119 * |
| 杜坤升: "城市地下管线探测关键技术分析", 《中国优秀硕士学位论文全文数据库》, no. 1, pages 038 - 1132 * |
| 王海宁: "三维探地雷达在道路地下病害体探测中的应用", 《中国煤炭地质》, vol. 30, no. 8, pages 70 - 74 * |
| 秦存昌: "隧道病害的探地雷达图像检测方法研究", 《中国优秀硕士学位论文全文数据库》, no. 1, pages 136 - 681 * |
| 胡浩帮: "基于Faster_R-CNN算法的探地雷达管线目标智能识别", 《城市勘测》, no. 3, pages 203 - 208 * |
| 郝彤: "面向双曲线形态的探地雷达图像识别技术综述", 《电子学报》, vol. 47, no. 6, pages 1369 - 1373 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113655477A (en) * | 2021-06-11 | 2021-11-16 | 成都圭目机器人有限公司 | Method for automatically detecting geological diseases of land radar by adopting shallow layer |
| CN113655477B (en) * | 2021-06-11 | 2023-09-01 | 成都圭目机器人有限公司 | Method for automatically detecting geological diseases by adopting shallow layer ground radar |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112859006B (en) | 2023-08-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103345757B (en) | Optics under multilevel multi-feature constraint and SAR image autoegistration method | |
| CN116148808B (en) | Automatic driving laser repositioning method and system based on point cloud descriptor | |
| CN110297246B (en) | Networking X-waveband weather radar collaborative self-adaptive control method and system | |
| CN107563370B (en) | Visual attention mechanism-based marine infrared target detection method | |
| WO2023035119A1 (en) | Method and system for extracting hyperbolic wave from ground penetrating radar image | |
| CN113239953A (en) | SAR image rotating ship detection method based on directed Gaussian function | |
| CN116310837B (en) | SAR ship target rotation detection method and system | |
| CN111929687B (en) | Automatic recognition algorithm for characteristics of tornado vortex | |
| CN112859006A (en) | Method for detecting metal curved cylindrical structure in multi-channel ground penetrating radar data | |
| CN115240058A (en) | Side-scan sonar target detection method combining accurate image segmentation and target shadow information | |
| Zou et al. | Sonar Image Target Detection for Underwater Communication System Based on Deep Neural Network. | |
| Wang et al. | Improved SSD Framework for Automatic Subsurface Object Indentification for GPR Data Processing | |
| CN113848556B (en) | Rapid extraction method for water depth range based on multi-beam sounding sonar wave beam image | |
| CN112859005B (en) | Method for detecting metal straight cylinder structure in multichannel ground penetrating radar data | |
| CN114998567A (en) | Infrared point group target identification method based on multi-mode feature discrimination | |
| CN111896932B (en) | Method for extracting target to be attacked by using sweep missile-borne single-line laser radar | |
| CN113466819A (en) | High-resolution three-dimensional point trace agglomeration method based on prior data | |
| KR20140104245A (en) | Method for calculating feasible search area for seeker to improve lock-on-target performance | |
| CN113341963A (en) | Navigation method and system for robot to automatically return to base station based on laser radar | |
| CN113177969A (en) | Point cloud single-target tracking method of candidate seeds based on motion direction change | |
| Liu et al. | Synthetic aperture radar image target recognition based on improved fusion of R-FCN and SRC | |
| CN113589235B (en) | Radar radial flow data extraction method and system | |
| CN104715265B (en) | Radar scene classification method based on compression sampling Yu integrated coding grader | |
| CN117689536B (en) | Laser radar splicing registration method, system, device and computer storage medium | |
| CN117951599B (en) | Underground piping diagram generation method and device based on radar image |
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 |