CN113655477A - Method for automatically detecting geological diseases of land radar by adopting shallow layer - Google Patents
Method for automatically detecting geological diseases of land radar by adopting shallow layer Download PDFInfo
- Publication number
- CN113655477A CN113655477A CN202110651938.XA CN202110651938A CN113655477A CN 113655477 A CN113655477 A CN 113655477A CN 202110651938 A CN202110651938 A CN 202110651938A CN 113655477 A CN113655477 A CN 113655477A
- Authority
- CN
- China
- Prior art keywords
- target
- radar data
- radar
- type
- geological
- 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
- 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
- G01S13/885—Radar or analogous systems specially adapted for specific applications for ground probing
-
- 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
- G01S13/89—Radar or analogous systems specially adapted for specific applications for mapping or imaging
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Electromagnetism (AREA)
- Computer Networks & Wireless Communication (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Probability & Statistics with Applications (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses a method for automatically detecting geological diseases of a ground radar by adopting a shallow layer, which comprises the following steps: detecting the geological area by turning back for c times and in a grid shape, and obtaining cscan radar data of the geological area; sequentially carrying out signal preprocessing and visualization processing on bscan radar data in the cscan radar data to obtain a radar data image; carrying out disease identification on the radar data image lmg _ i by adopting an image identification algorithm, and obtaining a disease category set to obtain K detection targets; three-dimensional sampling is carried out on the radar data image lmg _ i, sampling points form a set PointCloud3D, and the set PointCloud3D is projected to a horizontal plane; and (4) performing PointCloud3D clustering on the set by adopting the spatial position and the type to obtain the geological disease. Through the scheme, the method has the advantages of rapidness, accuracy, reliability and the like, and has high practical value and popularization value in the technical field of geological disease detection.
Description
Technical Field
The invention relates to the technical field of geological disease detection, in particular to a method for automatically detecting geological diseases by adopting a shallow layer to a ground radar.
Background
When the multichannel shallow bottom detection radar works, the multichannel shallow bottom detection radar is hung on the carrying equipment, and a plurality of channels of the carrying equipment are simultaneously pushed forwards, so that the multichannel shallow bottom detection radar is assumed as a radar device with m channels. In practice, m can be any integer greater than or equal to 1, and when m is 1, the radar is a single-channel ground penetrating radar.
As shown in fig. 1, in general, a ground penetrating radar performs full coverage detection on an area by using a foldback method. In general, in the multi-channel georadar detection, the number of ascans contained in all bscans in the same batch is the same, while in the full coverage detection, the number of ascans contained in bscans in two different batches is different and the same.
For example, as shown by the straight line in fig. 2, 3 batchs data are detected c times back and forth, and c batchs, i.e., m × c bscan data, which are marked as n (n ═ c × m) bscan data, i.e., radar data of one cube, are generated, as shown in fig. 3. In fig. 3, each point represents an actual position, the value of each point is the intensity of a radar echo, the radar echo represents the condition of a subsurface target, and the visualization processing of radar echo data of a single bscan is shown in fig. 4.
At present, in the prior art, the analysis of the multichannel shallow ground penetrating radar data generally includes analyzing each slice image, and then synthesizing the slice image analysis results to obtain a real three-dimensional geological target detection result, wherein the effect of one geological disease on the slice image is shown in fig. 5. Currently, automatic detection of an underground disease target in the prior art is mainly focused on detection of a single bscan. In the actual situation, no matter 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, the actual situation under the road is very complicated, a plurality of false targets exist, and the disease image characteristics are very obvious in the single bscan slice image.
The disease analysis in the prior art has the following problems:
firstly, the prior art mostly focuses on detecting the disease category target of a single bscan slice, so that a false target is difficult to remove and is difficult to apply to the actual situation;
secondly, the way of manually analyzing the radar data is that the result completely depends on the technicians who analyze the data, the results obtained by different personnel are different, and the same technical analyst cannot necessarily obtain the same result at different moments, so that the analysis has great subjectivity and is not beneficial to establishing pavement full life cycle disease management.
Therefore, a method for automatically detecting geological diseases by using shallow layer to land radar is urgently needed to be provided.
Disclosure of Invention
Aiming at the problems, the invention aims to provide a method for automatically detecting geological diseases by adopting a shallow layer to a radar, and the technical scheme adopted by the invention is as follows:
a method for automatically detecting geological diseases by adopting a shallow layer to a ground radar, wherein the shallow layer to the ground radar adopts m radar channels, comprises the following steps:
detecting the geological area by turning back for c times and in a grid shape, and obtaining cscan radar data of the geological area; the cscan radar data comprises batch radar data of c reentry paths; any batch radar data contains bscan radar data of m radar channels; the cscan radar data is equal to m × c bscan radar data, and n is m × c; both m and c are natural numbers more than or equal to 1;
sequentially performing signal preprocessing and visualization processing on bscan radar data in the cscan radar data to obtain radar data images, and recording radar data images corresponding to ith bscan radar data as lmg _ i, wherein i is more than 0 and less than n;
constructing a disease category set, carrying out disease identification on the radar data image lmg _ i by combining an image identification algorithm to obtain K detection targets, and recording any detection Target as Target _ i _ u; wherein DT _ GAP represents void, DT _ SUBSIDENCE represents settlement, 0< u < ═ k;
three-dimensional sampling is carried out on the radar data image lmg _ i, sampling points form a set PointCloud3D, and the set PointCloud3D is projected to a horizontal plane;
and (4) performing PointCloud3D clustering on the set by adopting the spatial position and the type to obtain the geological disease.
Furthermore, the detection Target _ i _ u contains the area coordinate, width and height of the radar data image lmg _ i at the position rect; obtaining the actual Position of the target according to the Position rect of the radar data image lmg _ i; the detection Target _ i _ u contains the type of the currently detected disease Target.
Preferably, the detection Target _ i _ u adopts grid-shaped foldback full coverage detection, and any radar data image lmg _ i is at equal intervals.
Further, the clustering with the set PointCloud3D using the spatial positions and the types further includes:
and (3) judging the distance between every two targets according to the spatial position and the type of the Target _ i _ u:
if the Target point Target _ i _ u _ p1.type is not equal to the Target point Target _ i _ u _ p2.type, the distance is infinite inf;
if the depth of the Target point Target _ i _ u _ p1.type and the Target point Target _ i _ u _ p2.type is greater than the preset threshold value thresh _ z, the distance is infinite inf;
if the Target point Target _ i _ u _ p1.type is equal to the Target point Target _ i _ u _ p2.type, and the depth of the Target point Target _ i _ u _ p1.type and the Target point Target _ i _ u _ p2.type is less than or equal to the preset threshold value thresh _ z, the distance is sqrt ((p1. x-p 2.x) + (p1. y-p 2. y)); wherein, p1.x and p1.y represent the coordinates of the Target point Target _ i _ u _ p1. type; the p2.x and p2.y represent coordinates of the Target point Target _ i _ u _ p2. type.
Preferably, the threshold thresh _ z is 0.15 m.
Preferably, the bscan radar data is subjected to zero offset adjustment, zero point adjustment, filtering and gain adjustment.
Compared with the prior art, the invention has the following beneficial effects:
(1) the method skillfully samples the shallow layer to carry out multi-channel detection on the area to be detected by the ground radar, obtains radar data of any channel, forms a radar data image, judges the position and type of any target in the radar data image, and clusters on the basis of judgment to obtain the geological disease and the position information of the same type;
(2) any target point is obtained through three-dimensional adoption and is projected to a horizontal plane, so that the position distance of the target point can be conveniently judged at the later stage, and data support is provided for clustering;
in conclusion, the method has the advantages of being rapid, accurate and reliable in detection and the like, and has high practical value and popularization value in the technical field of geological disease detection.
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 schematic diagram of a detection operation path in the prior art.
Fig. 2 is a schematic diagram of a detection region in the prior art.
Fig. 3 is a diagram of radar data in the prior art.
Fig. 4 is an image corresponding to radar data in the prior art.
Fig. 5 is a schematic diagram of a geological disease detection result in the prior art.
FIG. 6 is a slice detection diagram of a radar datum in the present invention.
FIG. 7 is a schematic diagram of a radar detection path according to the present invention.
FIG. 8 is a schematic diagram of isometric detection in the present invention.
Fig. 9 is a schematic diagram of a three-dimensional sampling projection in the present invention.
Fig. 10 is a schematic diagram illustrating the division of the detection area in the present invention.
Fig. 11 is a schematic diagram of a clustering result in 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. 6 to 11, the present embodiment provides a method for automatically detecting a geological disease by using a shallow-layer radar, which includes the following specific steps:
in this embodiment, the whole cscan radar data obtained by detecting the radar by the sampling shallow layer is composed of c banks (i.e., rows and the number of turns back), and each bank has m bscan data (m channels), so that n ═ c × m bscan data in the whole cscan.
In this embodiment, each radar data back is subjected to signal processing on a basic signal, such as zero offset adjustment, zero point adjustment, filtering, gain adjustment, and the like, and the processed signal is subjected to visualization processing, and the signal processing and visualization are implemented as a general scheme, which will not be described herein.
After visual conversion, any radar data back corresponds to one radar data image, and the ith bscan image is recorded as Img _ i, wherein 0< i < ═ n. In this embodiment, a disease target is detected for the radar data image Img _ i, where a classical image processing algorithm may be used, or a deep learning manner may also be used, without limitation, in this embodiment, an SSD algorithm is used to train a type sample picture of an existing radar slice image, and then the trained model is used to identify Img _ i, where this identification is mainly directed to common disease types, such as void, loose, settlement, and the like, and the disease type SET is recorded as DIS _ SET ═ DT _ GAP, DT _ substience, … … }. The address disease type to be identified is determined according to a specific application scenario without limitation. Here, using a method of classical image processing or deep learning, K targets in the image Img _ i are obtained, and a single Target is denoted as Target _ i _ u, where i denotes a result of Img _ i, and 0< u < ═ K; each Target _ i _ u contains information of rect, position and type, where rect is the area (coordinates, width and height) of the object on the image Img _ i. When the ground penetrating radar works, each asan not only has data, but also has a corresponding Position and a real coordinate Position, the present embodiment uses a central point Position of the target to represent the actual Position of the target, the Position includes x, y, z, coordinate, longitude, and sheight, where x and y are positions in a coordinate system used in a detection task, the longitude and latitude of the point in a terrestrial coordinate system are height, z is the depth of the point, a detection depth corresponding to a sampling point of each asan can be calculated according to the acquisition radar emission frequency, the detection track dielectric constant and the light speed, and type is a type of a currently detected disease target and is any value in DIS _ SET ═ DT _ GAP, DT _ subsense, … ….
In this embodiment, the Target detection is performed on the radar data bscan slice, and the detected targets are put into a set Target, Target { Target _0_0, … …, Target _0_ k0, Target _1_0, … …, Target _1_ k1, … …, … …, Target _ i _ u, … … }, where i is the corresponding bscan slice image number and u is one of the detection targets in the slice.
As shown in fig. 7, the radar device performs detection in a grid-shaped foldback full coverage manner, and the intervals between bscans are equidistant and are denoted as l _ between _ bscan; each detected object is projected to XY (horizontal plane, ignoring each object depth related information at this time). Three-dimensional sampling is carried out on each target on the bscan, the sampling interval is l _ between _ bscan (9cm), so that the 3d targets which may exist really are uniformly sampled in the parallel detection direction and the vertical detection direction, the depth of each disease adopts the depth of a central line of the disease, and a plurality of sampling points of the same disease are consistent in the depth direction, namely z is the same. As shown in the following figure, each sampling point P contains two pieces of information, position and type, and the type of each point is the type of the sampled object.
As shown in fig. 8 and 9, in the present embodiment, uniform sampling of each detection Target in the detection Target set is completed, and all the sampling points P are put into the set PointCloud3D and projected to the horizontal plane. In this embodiment, all the points in the three-dimensional point cloud PointCloud3D obtained by sampling the detection target are clustered according to the spatial position and type information thereof, the clustering method may select a kmean algorithm or a dbscan rich, each obtained subclass is a detected address disease, and it is noted here that before clustering, there are several three-dimensional diseases in the set, so that the dbscan algorithm is adopted first, or a kmean algorithm capable of merging and splitting subclasses is selected, and the 3d point cloud clustering method is not limited to the above two methods, and is a known public technology, and no description is made here.
In clustering, the distance between two points is determined, for example: target point Target _ i _ u _ p1.type and Target point Target _ i _ u _ p2. type:
(1) if the Target point Target _ i _ u _ p1.type is not equal to the Target point Target _ i _ u _ p2.type, the distance is infinite inf;
(2) if the depth of the Target point Target _ i _ u _ p1.type and the Target point Target _ i _ u _ p2.type is greater than the preset threshold value thresh _ z, the distance is infinite inf; the threshold thresh _ z is preferably 0.15 m.
(3) If the Target point Target _ i _ u _ p1.type is equal to the Target point Target _ i _ u _ p2.type, and the depth of the Target point Target _ i _ u _ p1.type and the Target point Target _ i _ u _ p2.type is less than or equal to the preset threshold value thresh _ z, the distance is sqrt ((p1. x-p 2.x) + (p1. y-p 2. y)); wherein, p1.x and p1.y represent the horizontal width and height of the Target point Target _ i _ u _ p1. type; the p2.x and p2.y represent the horizontal width and height of the Target point Target _ i _ u _ p2. type.
As shown in fig. 10, in the present embodiment, since the sampling distance in two directions that are horizontal and perpendicular to each other is l _ between _ bscan, which is different according to different multi-channel radar devices, but generally, the value is small, l _ between _ bscan in the embodiment is 9cm, each detection task is basically ten thousand square meters, and the detection accuracy of general geological internal diseases does not require 1 square decimeter, Point3d is a very large data set, and in the present embodiment, Point3d preprocessing is generally required for clustering, where the preprocessing is an optional step and is determined according to actual situations. Generally, there are two pretreatment methods, one or more of which are selected according to the need, or no pretreatment is required.
The whole Point3d is down-sampled, and the down-sampling method of the three-dimensional Point cloud is a known method and is not described again. The whole detection range is divided into a plurality of detection areas, point3d is also divided into a plurality of detection areas according to the detection areas, and the division rule is determined according to the detection items.
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 (6)
1. A method for automatically detecting geological diseases by adopting a shallow layer to a ground radar, wherein the shallow layer to the ground radar adopts m radar channels, is characterized by comprising the following steps:
detecting the geological area by turning back for c times and in a grid shape, and obtaining cscan radar data of the geological area; the cscan radar data comprises batch radar data of c reentry paths; any batch radar data contains bscan radar data of m radar channels; the cscan radar data is equal to m × c bscan radar data, and n is m × c; both m and c are natural numbers more than or equal to 1;
sequentially performing signal preprocessing and visualization processing on bscan radar data in the cscan radar data to obtain radar data images, and recording radar data images corresponding to ith bscan radar data as lmg _ i, wherein i is more than 0 and less than n;
constructing a disease category set, carrying out disease identification on the radar data image lmg _ i by combining an image identification algorithm to obtain K detection targets, and recording any detection Target as Target _ i _ u; wherein DT _ GAP represents void, DT _ SUBSIDENCE represents settlement, 0< u < ═ k;
three-dimensional sampling is carried out on the radar data image lmg _ i, sampling points form a set PointCloud3D, and the set PointCloud3D is projected to a horizontal plane;
and (4) performing PointCloud3D clustering on the set by adopting the spatial position and the type to obtain the geological disease.
2. The method for automatically detecting geological diseases by using the shallow layer to the ground radar as claimed in claim 1, characterized in that the detection Target _ i _ u contains the area coordinates, width and height of the radar data image lmg _ i in the position rect; obtaining the actual Position of the target according to the Position rect of the radar data image lmg _ i; the detection Target _ i _ u contains the type of the currently detected disease Target.
3. The method for automatically detecting the geological diseases by adopting the shallow-layer pair land radar as claimed in claim 1, wherein the Target _ i _ u is detected by adopting grid-shaped reentry full coverage detection, and any radar data image lmg _ i is at equal intervals.
4. The method for automatically detecting geological diseases of the shallow pair of land radar according to claim 1, wherein said clustering with the set PointCloud3D using spatial location and type further comprises:
and (3) judging the distance between every two targets according to the spatial position and the type of the Target _ i _ u:
if the Target point Target _ i _ u _ p1.type is not equal to the Target point Target _ i _ u _ p2.type, the distance is infinite inf;
if the depth of the Target point Target _ i _ u _ p1.type and the Target point Target _ i _ u _ p2.type is greater than the preset threshold value thresh _ z, the distance is infinite inf;
if the Target point Target _ i _ u _ p1.type is equal to the Target point Target _ i _ u _ p2.type, and the depth of the Target point Target _ i _ u _ p1.type and the Target point Target _ i _ u _ p2.type is less than or equal to the preset threshold value thresh _ z, the distance is sqrt ((p1. x-p 2.x) + (p1. y-p 2. y)); wherein, p1.x and p1.y represent the coordinates of the Target point Target _ i _ u _ p1. type; the p2.x and p2.y represent coordinates of the Target point Target _ i _ u _ p2. type.
5. The method for automatically detecting geological diseases by using shallow-layer landradar as claimed in claim 4, wherein the threshold thresh _ z is 0.15 m.
6. The method for automatically detecting the geological diseases by the shallow layer to the radar as claimed in claim 1, wherein the bscan radar data is subjected to zero offset adjustment, zero point adjustment, filtering and gain adjustment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110651938.XA CN113655477B (en) | 2021-06-11 | 2021-06-11 | Method for automatically detecting geological diseases by adopting shallow layer ground radar |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110651938.XA CN113655477B (en) | 2021-06-11 | 2021-06-11 | Method for automatically detecting geological diseases by adopting shallow layer ground radar |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113655477A true CN113655477A (en) | 2021-11-16 |
| CN113655477B CN113655477B (en) | 2023-09-01 |
Family
ID=78488958
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110651938.XA Active CN113655477B (en) | 2021-06-11 | 2021-06-11 | Method for automatically detecting geological diseases by adopting shallow layer ground radar |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113655477B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117409329A (en) * | 2023-12-15 | 2024-01-16 | 深圳安德空间技术有限公司 | Method and system for reducing false alarm rate of underground cavity detection by three-dimensional ground penetrating radar |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5592170A (en) * | 1995-04-11 | 1997-01-07 | Jaycor | Radar system and method for detecting and discriminating targets from a safe distance |
| US20180232947A1 (en) * | 2017-02-11 | 2018-08-16 | Vayavision, Ltd. | Method and system for generating multidimensional maps of a scene using a plurality of sensors of various types |
| CN108665466A (en) * | 2018-05-21 | 2018-10-16 | 山东科技大学 | Pavement disease extraction method in a kind of road laser point cloud |
| CN108733053A (en) * | 2018-04-23 | 2018-11-02 | 上海圭目机器人有限公司 | A kind of Intelligent road detection method based on robot |
| CN110097047A (en) * | 2019-03-19 | 2019-08-06 | 同济大学 | A vehicle detection method using single-line lidar based on deep learning |
| CN110363158A (en) * | 2019-07-17 | 2019-10-22 | 浙江大学 | A Neural Network-Based Collaborative Target Detection and Recognition Method of Millimeter-Wave Radar and Vision |
| CN110456363A (en) * | 2019-06-17 | 2019-11-15 | 北京理工大学 | Target detection and localization method based on fusion of 3D lidar point cloud and infrared image |
| CN110736985A (en) * | 2019-09-27 | 2020-01-31 | 山西省交通科技研发有限公司 | Pole characteristic clustering road hidden disease identification system and implementation method thereof |
| CN110988912A (en) * | 2019-12-06 | 2020-04-10 | 中国科学院自动化研究所 | Road target and distance detection method, system and device for automatic driving vehicle |
| CN111553236A (en) * | 2020-04-23 | 2020-08-18 | 福建农林大学 | Road foreground image-based pavement disease target detection and example segmentation method |
| CN111833449A (en) * | 2020-06-30 | 2020-10-27 | 南京航空航天大学 | Three-dimensional reconstruction of subway tunnel interior environment and intelligent identification method of disease |
| CN112462346A (en) * | 2020-11-26 | 2021-03-09 | 西安交通大学 | Ground penetrating radar roadbed defect target detection method based on convolutional neural network |
| EP3796210A1 (en) * | 2019-09-19 | 2021-03-24 | Siemens Healthcare GmbH | Spatial distribution of pathological image patterns in 3d image data |
| CN112700429A (en) * | 2021-01-08 | 2021-04-23 | 中国民航大学 | Airport pavement underground structure disease automatic detection method based on deep learning |
| CN112800524A (en) * | 2021-02-05 | 2021-05-14 | 河北工业大学 | Pavement disease three-dimensional reconstruction method based on deep learning |
| CN112859006A (en) * | 2021-01-11 | 2021-05-28 | 成都圭目机器人有限公司 | Method for detecting metal curved cylindrical structure in multi-channel ground penetrating radar data |
| CN112883820A (en) * | 2021-01-26 | 2021-06-01 | 上海应用技术大学 | Road target 3D detection method and system based on laser radar point cloud |
-
2021
- 2021-06-11 CN CN202110651938.XA patent/CN113655477B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5592170A (en) * | 1995-04-11 | 1997-01-07 | Jaycor | Radar system and method for detecting and discriminating targets from a safe distance |
| US20180232947A1 (en) * | 2017-02-11 | 2018-08-16 | Vayavision, Ltd. | Method and system for generating multidimensional maps of a scene using a plurality of sensors of various types |
| CN108733053A (en) * | 2018-04-23 | 2018-11-02 | 上海圭目机器人有限公司 | A kind of Intelligent road detection method based on robot |
| CN108665466A (en) * | 2018-05-21 | 2018-10-16 | 山东科技大学 | Pavement disease extraction method in a kind of road laser point cloud |
| CN110097047A (en) * | 2019-03-19 | 2019-08-06 | 同济大学 | A vehicle detection method using single-line lidar based on deep learning |
| CN110456363A (en) * | 2019-06-17 | 2019-11-15 | 北京理工大学 | Target detection and localization method based on fusion of 3D lidar point cloud and infrared image |
| CN110363158A (en) * | 2019-07-17 | 2019-10-22 | 浙江大学 | A Neural Network-Based Collaborative Target Detection and Recognition Method of Millimeter-Wave Radar and Vision |
| EP3796210A1 (en) * | 2019-09-19 | 2021-03-24 | Siemens Healthcare GmbH | Spatial distribution of pathological image patterns in 3d image data |
| CN110736985A (en) * | 2019-09-27 | 2020-01-31 | 山西省交通科技研发有限公司 | Pole characteristic clustering road hidden disease identification system and implementation method thereof |
| CN110988912A (en) * | 2019-12-06 | 2020-04-10 | 中国科学院自动化研究所 | Road target and distance detection method, system and device for automatic driving vehicle |
| CN111553236A (en) * | 2020-04-23 | 2020-08-18 | 福建农林大学 | Road foreground image-based pavement disease target detection and example segmentation method |
| CN111833449A (en) * | 2020-06-30 | 2020-10-27 | 南京航空航天大学 | Three-dimensional reconstruction of subway tunnel interior environment and intelligent identification method of disease |
| CN112462346A (en) * | 2020-11-26 | 2021-03-09 | 西安交通大学 | Ground penetrating radar roadbed defect target detection method based on convolutional neural network |
| CN112700429A (en) * | 2021-01-08 | 2021-04-23 | 中国民航大学 | Airport pavement underground structure disease automatic detection method based on deep learning |
| CN112859006A (en) * | 2021-01-11 | 2021-05-28 | 成都圭目机器人有限公司 | Method for detecting metal curved cylindrical structure in multi-channel ground penetrating radar data |
| CN112883820A (en) * | 2021-01-26 | 2021-06-01 | 上海应用技术大学 | Road target 3D detection method and system based on laser radar point cloud |
| CN112800524A (en) * | 2021-02-05 | 2021-05-14 | 河北工业大学 | Pavement disease three-dimensional reconstruction method based on deep learning |
Non-Patent Citations (4)
| Title |
|---|
| 朱少辉: "探地雷达在高等级公路质量检测中的应用研究", 《中国优秀硕士学位论文全文库》, no. 10, pages 034 - 6 * |
| 李姝凡: "基于探地雷达的混凝土内钢筋下病害识别方法研究", 《中国优秀硕士学位论文全文库》, no. 11, pages 038 - 86 * |
| 李海丰 等: "基于多传感器信息融合的机场道面裂缝检测算法", 《现代电子技术》, vol. 43, no. 24, pages 17 - 25 * |
| 童峥: "基于深度学习和探地雷达技术的路面结构病害检测研究", 《全国优秀硕士学位论文全文库》, no. 1, pages 034 - 419 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117409329A (en) * | 2023-12-15 | 2024-01-16 | 深圳安德空间技术有限公司 | Method and system for reducing false alarm rate of underground cavity detection by three-dimensional ground penetrating radar |
| CN117409329B (en) * | 2023-12-15 | 2024-04-05 | 深圳安德空间技术有限公司 | Method and system for reducing false alarm rate of underground cavity detection by three-dimensional ground penetrating radar |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113655477B (en) | 2023-09-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wenner et al. | Near real-time automated classification of seismic signals of slope failures with continuous random forests | |
| Dietze et al. | Seismic monitoring of small alpine rockfalls–validity, precision and limitations | |
| Drews et al. | Validation of fracture data recognition in rock masses by automated plane detection in 3D point clouds | |
| EP1839074B1 (en) | Method of seismic signal processing | |
| CN108254784B (en) | Fault identification method, device and system based on two-dimensional seismic data | |
| CN113762090B (en) | Disaster monitoring and early warning method for ultra-high voltage dense transmission channel | |
| CN114252884B (en) | Roadside radar positioning monitoring method, device, computer equipment and storage medium | |
| CN114239379B (en) | A method and system for analyzing geological hazards of power transmission lines based on deformation detection | |
| Karantanellis et al. | 3D hazard analysis and object-based characterization of landslide motion mechanism using UAV imagery | |
| CN115690081A (en) | Tree counting method, system, storage medium, computer equipment and terminal | |
| CN113360587B (en) | Land surveying and mapping equipment and method based on GIS technology | |
| CN116778329A (en) | Urban road underground shallow disease detection method, device, equipment and medium | |
| Brighenti et al. | UAV survey method to monitor and analyze geological hazards: the case study of the mud volcano of Villaggio Santa Barbara, Caltanissetta (Sicily) | |
| CN113655477A (en) | Method for automatically detecting geological diseases of land radar by adopting shallow layer | |
| US11754704B2 (en) | Synthetic-aperture-radar image processing device and image processing method | |
| Chen et al. | Flying bird detection and hazard assessment for avian radar system | |
| Calvo et al. | Unlocking the correlation in fluvial outcrops by using a DOM-derived virtual datum: Method description and field tests in the Huesca fluvial fan, Ebro Basin (Spain) | |
| Julge et al. | Performance analysis of freeware filtering algorithms for determining ground surface from airborne laser scanning data | |
| CN109886142B (en) | Crop interpretation method based on SAR technology | |
| CN118566908A (en) | Monitoring data transmission method, electronic equipment and storage medium | |
| Cappellazzo et al. | Integrated Airborne LiDAR-UAV Methods for Archaeological Mapping in Vegetation-Covered Areas | |
| Wezyk | The integration of the terrestrial and airborne laser scanning technologies in the semi-automated process of retrieving selected trees and forest stand parameters Integração das tecnologias terrestre e aerotransportada de scanner laser no processo semi | |
| CN115951404B (en) | An earthquake source location method and system based on historical data | |
| RU2596610C1 (en) | Method of search and detection of object | |
| Purohit et al. | ConeQuest: A Benchmark for Cone Segmentation on Mars |
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 |