CN111192310A - High-speed ground rapid extraction system and method based on laser point cloud - Google Patents
High-speed ground rapid extraction system and method based on laser point cloud Download PDFInfo
- Publication number
- CN111192310A CN111192310A CN201911401170.XA CN201911401170A CN111192310A CN 111192310 A CN111192310 A CN 111192310A CN 201911401170 A CN201911401170 A CN 201911401170A CN 111192310 A CN111192310 A CN 111192310A
- Authority
- CN
- China
- Prior art keywords
- grid
- point cloud
- ground
- track
- clustering
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000000605 extraction Methods 0.000 title claims abstract description 15
- 230000008569 process Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000750 progressive effect Effects 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000007787 solid Substances 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
- G06T7/50—Depth or shape recovery
- G06T7/521—Depth or shape recovery from laser ranging, e.g. using interferometry; from the projection of structured light
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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
- G06T17/20—Finite element generation, e.g. wire-frame surface description, tesselation
-
- 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
- G06T2207/10028—Range image; Depth image; 3D point clouds
Abstract
The invention discloses a high-speed ground rapid extraction system and method based on laser point cloud. Wherein the method is configured to: loading a track point cloud of a track file; selecting a ground reference track, and acquiring a ground point cloud set of the track point cloud contained in the ground reference track; establishing an index grid of the ground point cloud set; acquiring the index grid with the maximum elevation difference value smaller than or equal to a plane threshold value as a plane grid, and acquiring a grid set of the plane grid; and clustering the index grid of the grid set into a clustering area. The invention can rapidly and accurately segment ground point cloud and non-ground point cloud, and can be widely applied to engineering.
Description
Technical Field
The invention relates to the technical field of measurement and control, in particular to a high-speed ground rapid extraction system and method based on laser point cloud.
Background
Ground point clouds and non-ground point clouds are distinguished before ground object detection and identification, so that wheels, road barriers, road edge stones and the like are prevented from being identified, and more accurate ground point cloud identification is ensured.
In the prior art, a ground plane is mostly obtained through a plane fitting mode, but a road surface is not a standard plane in an actual scene, for example, in order to provide drainage road efficiency, two side edges of a road are sunken downwards, the middle of the road is raised upwards, for a non-standard plane road, the ground and the non-ground can not be well divided through the plane fitting mode, and the plane fitting can not be widely implemented in engineering due to the fact that the ground point cloud data volume acquired with high precision is too large.
Disclosure of Invention
The embodiment of the invention at least discloses a high-speed ground rapid extraction method based on laser point cloud. The method of the embodiment can rapidly and accurately segment the ground point cloud and the non-ground point cloud, and can be widely applied to engineering.
To achieve the above, the method is configured to: loading a track point cloud of a track file; selecting a ground reference track, and acquiring a ground point cloud set of the track point cloud contained in the ground reference track; establishing an index grid of the ground point cloud set; acquiring the index grid with the maximum elevation difference value smaller than or equal to a plane threshold value as a plane grid, and acquiring a grid set of the plane grid; and clustering the index grid of the grid set into a clustering area.
In some embodiments of the present disclosure, the track point cloud is loaded and configured to: loading the track file; splitting the track file into at least one track segment along the track direction; loading the track point cloud of the track segment.
In some embodiments of the present disclosure, the ground reference trajectory is selected to be configured to: and the collection of the track point clouds which extend along the track direction and obviously belong to the ground point clouds is the ground reference track.
In some embodiments of the present disclosure, the method is configured with: and expanding the clustering region into a clustering region in a region growing mode.
In some embodiments of the present disclosure, extending the clustering region into the clustering region is configured to: acquiring at least one index grid with the maximum elevation difference value larger than a plane threshold as an unknown grid; classifying at least one unknown grid into an effective ground grid in a region growing mode; merging the effective ground grid into the clustered region.
In some embodiments of the present disclosure, the method is configured with: acquiring at least one unknown grid which does not belong to the effective ground grid as an ineffective ground grid; acquiring at least one track point cloud in the clustering area adjacent to the invalid ground grid as an adjacent point cloud; judging whether the maximum elevation difference value between an effective point cloud and the adjacent point cloud exists in the ineffective ground grid or not; merging the invalid ground grids in which the valid point clouds exist into the clustering region.
The embodiment of the invention at least discloses a high-speed ground rapid extraction system based on laser point cloud. The system comprises a loading module, a reference module, an index grid module, a plane grid module and a clustering module: the loading module is configured to load a track point cloud of a track file; the reference module is configured to select a ground reference track and obtain a ground point cloud set of the track point cloud contained in the ground reference track; the index grid module is configured to establish an index grid for the ground point cloud collection; the planar grid module is configured to acquire the index grid with the maximum elevation difference value smaller than or equal to a planar threshold as a planar grid and acquire a grid set of the planar grid; the clustering module is configured to cluster the index grid of the grid set into a clustering region.
In view of the above, other features and advantages of the disclosed exemplary embodiments will become apparent from the following detailed description of the disclosed exemplary embodiments, which proceeds with reference to the accompanying drawings.
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, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
FIG. 1 is a partial flow chart of a method in an embodiment;
FIG. 2 is a partial flow chart of a method in an embodiment;
fig. 3 is a block diagram of the system in the embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
The embodiment discloses a high-speed ground rapid extraction method based on laser point cloud. The method of the present embodiment is performed at a server and/or a computing device, such as a computer. Where the server and/or computing device is implemented in this embodiment with at least a memory and a processor. The memory mainly comprises a program storage area and a data storage area; the storage program area may store an operating system, and an application program required by at least one function (such as a sound playing function, an image playing function, and the like). And, the storage data area may store data created according to the use of the electronic terminal, including related setting information or use condition information of the displayed application, etc., which are referred to in the embodiments of the present application. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, and other volatile solid state storage devices.
Before the server and/or the computing device executes the method disclosed by the embodiment, the laser point cloud of a track line segment on a collection road where a vehicle runs along a high-speed or urban road through a laser scanner is collected, and a track file with the track line segment is generated. When the server and/or the computing device executes the method disclosed in the present embodiment, the flow of the method executed is shown in fig. 1 and fig. 2.
S110, loading a track file of a track segment on the road.
S120, the track file is divided into a plurality of track segments with the same storage area size along the track direction of the track line segment.
S130, loading the track point cloud of the single track segment.
S210, a track point cloud set which extends along the track direction and obviously belongs to ground point cloud is inquired to be a ground reference track. Optionally, the track point cloud set obviously belonging to the ground point cloud is formed by manually and primarily indexing in combination with known road information such as length, width and the like.
S220, judging the inclusion relation between all the track point clouds and the ground reference track, and acquiring the track point clouds included in the ground reference track as a ground point cloud set.
S300, constructing an index grid without an elevation value according to the ground point cloud set; optionally, the index grid size is 20cmX20 cm.
S400, acquiring a maximum elevation difference value between any two track point clouds in the index grid, and judging whether the maximum elevation difference value is smaller than or equal to a plane threshold value. The plane threshold may be 1cm, that is, the maximum elevation difference between any two track point clouds in the index grid should not be greater than 1cm, and naturally the index grid is an area that is approximately a plane. Meanwhile, the index grids with the maximum elevation difference value smaller than or equal to the plane threshold value are defined as plane grids, and grid sets of all the plane grids are obtained.
S500 all the index grids in the set of clustering grids are a large and continuous clustering region.
S610, acquiring an index grid with the maximum elevation difference value larger than the plane threshold value as an unknown grid.
S620 classifies the at least one unknown mesh as a valid ground mesh by means of region growing. Region growing as referred to in this embodiment refers to the process of developing groups of pixels or regions into larger regions, as from a collection of seed point clouds by merging point clouds of neighboring elements with similar attributes like intensity, gray level, texture color, etc. to each seed point cloud into the region of the collection.
S630 merges the valid ground mesh into a clustered region of further region expansion.
S710 obtains at least one unknown mesh that does not belong to the valid terrestrial meshes as an invalid terrestrial mesh.
S720, acquiring a track point cloud in a clustering region adjacent to the invalid ground grid as an adjacent point cloud.
S730 determines whether a track point cloud exists in the invalid ground grid, that is, whether the maximum elevation difference between the valid point cloud defined in this embodiment and the adjacent point cloud is less than or equal to the plane threshold.
And S740, when judging that the invalid ground grid has at least one valid point cloud, combining the invalid ground grid to a clustering area. Alternatively, a valid threshold amount may be configured to merge the invalid ground grids into the clustered regions only if the number of valid point clouds present in the invalid ground grids is equal to or greater than the valid threshold amount.
When the server and/or the computing device executes the flow of the method, the first pre-judged preliminary point is considered as a first point cloud collection of the ground point cloud. And establishing an index grid by using the first point cloud set, and further analyzing the index grid meeting the requirements in the first point cloud set as a plane grid through the maximum elevation difference, wherein the plane grid is the most part of the ground point cloud. And then, the first point cloud collection is expanded into a larger and continuous clustering area through clustering and expansion, so that the ground point cloud data can be extracted quickly and accurately.
For further explanation on the implementation of the above method, fig. 3 shows a high-speed ground fast extraction system based on laser point cloud disclosed in this embodiment. The system comprises a loading module, a reference module, an index grid module, a plane grid module and a clustering module.
When the loading module executes, loading a track point cloud of a track file; the reference module selects a ground reference track during execution and acquires a ground point cloud set of track point clouds contained in the ground reference track; when the index grid module is executed, an index grid of a ground point cloud set is established; when the plane grid module is executed, acquiring an index grid with the maximum elevation difference value smaller than or equal to a plane threshold value as a plane grid, and acquiring a grid set of the plane grid; the clustering module executes to cluster an index grid of the grid set into a cluster region.
The present embodiment is described in detail above. The embodiments are described in a progressive manner in the specification, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is simple, and the related points can be referred to the method part for description. It should be noted that, for those skilled in the art, it is possible to make several improvements and modifications to the present application without departing from the principle of the present application, and such improvements and modifications also fall within the scope of the claims of the present application.
The embodiments are described in a progressive mode in the specification, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is simple, and the related points can be referred to the description of the method.
Those of skill would further appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It is further noted that, in the present specification, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Claims (7)
1. A high-speed ground rapid extraction method based on laser point cloud is characterized in that,
the method is configured to:
loading a track point cloud of a track file;
selecting a ground reference track, and acquiring a ground point cloud set of the track point cloud contained in the ground reference track;
establishing an index grid of the ground point cloud set;
acquiring the index grid with the maximum elevation difference value smaller than or equal to a plane threshold value as a plane grid, and acquiring a grid set of the plane grid;
and clustering the index grid of the grid set into a clustering area.
2. The high-speed ground rapid extraction method based on laser point cloud of claim 1,
loading the trajectory point cloud configured to:
loading the track file;
splitting the track file into at least one track segment along the track direction;
loading the track point cloud of the track segment.
3. The high-speed ground rapid extraction method based on laser point cloud of claim 1,
selecting the ground reference trajectory configured to:
and the collection of the track point clouds which extend along the track direction and obviously belong to the ground point clouds is the ground reference track.
4. The high-speed ground rapid extraction method based on laser point cloud of claim 1,
the method is configured with:
and expanding the clustering region into a clustering region in a region growing mode.
5. The high-speed ground rapid extraction method based on laser point cloud of claim 1,
expanding the clustering region to the clustering region, configured to:
acquiring at least one index grid with the maximum elevation difference value larger than a plane threshold as an unknown grid;
classifying at least one unknown grid into an effective ground grid in a region growing mode;
merging the effective ground grid into the clustered region.
6. The method for high-speed ground fast extraction based on laser point cloud of claim 5,
the method is configured with:
acquiring at least one unknown grid which does not belong to the effective ground grid as an ineffective ground grid;
acquiring at least one track point cloud in the clustering area adjacent to the invalid ground grid as an adjacent point cloud;
judging whether the maximum elevation difference value between an effective point cloud and the adjacent point cloud exists in the ineffective ground grid or not;
merging the invalid ground grids in which the valid point clouds exist into the clustering region.
7. The high-speed ground rapid extraction system based on the laser point cloud is characterized by comprising a loading module, a reference module, an index grid module, a plane grid module and a clustering module:
the loading module is configured to load a track point cloud of a track file;
the reference module is configured to select a ground reference track and obtain a ground point cloud set of the track point cloud contained in the ground reference track;
the index grid module is configured to establish an index grid for the ground point cloud collection;
the planar grid module is configured to acquire the index grid with the maximum elevation difference value smaller than or equal to a planar threshold as a planar grid and acquire a grid set of the planar grid;
the clustering module is configured to cluster the index grid of the grid set into a clustering region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911401170.XA CN111192310A (en) | 2019-12-31 | 2019-12-31 | High-speed ground rapid extraction system and method based on laser point cloud |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911401170.XA CN111192310A (en) | 2019-12-31 | 2019-12-31 | High-speed ground rapid extraction system and method based on laser point cloud |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111192310A true CN111192310A (en) | 2020-05-22 |
Family
ID=70710468
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911401170.XA Pending CN111192310A (en) | 2019-12-31 | 2019-12-31 | High-speed ground rapid extraction system and method based on laser point cloud |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111192310A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103679655A (en) * | 2013-12-02 | 2014-03-26 | 河海大学 | LiDAR point cloud filter method based on gradient and area growth |
| CN106204705A (en) * | 2016-07-05 | 2016-12-07 | 长安大学 | A kind of 3D point cloud segmentation method based on multi-line laser radar |
| CN108919295A (en) * | 2018-05-15 | 2018-11-30 | 国网通用航空有限公司 | Airborne LiDAR point cloud road information extracting method and device |
| CN108984599A (en) * | 2018-06-01 | 2018-12-11 | 青岛秀山移动测量有限公司 | A kind of vehicle-mounted laser point cloud road surface extracting method referred to using driving trace |
| US20190178989A1 (en) * | 2017-12-11 | 2019-06-13 | Automotive Research & Testing Center | Dynamic road surface detecting method based on three-dimensional sensor |
| CN110490888A (en) * | 2019-07-29 | 2019-11-22 | 武汉大学 | Freeway geometry Characteristic Vectors based on airborne laser point cloud quantify extracting method |
-
2019
- 2019-12-31 CN CN201911401170.XA patent/CN111192310A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103679655A (en) * | 2013-12-02 | 2014-03-26 | 河海大学 | LiDAR point cloud filter method based on gradient and area growth |
| CN106204705A (en) * | 2016-07-05 | 2016-12-07 | 长安大学 | A kind of 3D point cloud segmentation method based on multi-line laser radar |
| US20190178989A1 (en) * | 2017-12-11 | 2019-06-13 | Automotive Research & Testing Center | Dynamic road surface detecting method based on three-dimensional sensor |
| CN108919295A (en) * | 2018-05-15 | 2018-11-30 | 国网通用航空有限公司 | Airborne LiDAR point cloud road information extracting method and device |
| CN108984599A (en) * | 2018-06-01 | 2018-12-11 | 青岛秀山移动测量有限公司 | A kind of vehicle-mounted laser point cloud road surface extracting method referred to using driving trace |
| CN110490888A (en) * | 2019-07-29 | 2019-11-22 | 武汉大学 | Freeway geometry Characteristic Vectors based on airborne laser point cloud quantify extracting method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2620930B1 (en) | Track estimation device and program | |
| JP5223675B2 (en) | Vehicle detection device, vehicle detection method, and vehicle detection program | |
| CN108665466B (en) | Automatic extraction method for road surface diseases in road laser point cloud | |
| CN109741450B (en) | Automatic road surface point cloud extraction method and device based on scanning lines | |
| CN116129202B (en) | Method, apparatus and storage medium for stock land analysis | |
| CN114359866A (en) | Road boundary detection method and device based on laser radar | |
| CN115240149A (en) | Three-dimensional point cloud detection and identification method and device, electronic equipment and storage medium | |
| CN111323788A (en) | Building change monitoring method and device and computer equipment | |
| CN111340889B (en) | Method for automatically acquiring matched image block and point cloud ball based on vehicle-mounted laser scanning | |
| CN114722944A (en) | Point cloud precision determination method, electronic device and computer storage medium | |
| CN111523341B (en) | Binarization method and device for two-dimensional code image | |
| CN113963314A (en) | Rainfall monitoring method and device, computer equipment and storage medium | |
| CN111932477B (en) | Noise removal method and device based on single line laser radar point cloud | |
| CN111192310A (en) | High-speed ground rapid extraction system and method based on laser point cloud | |
| CN113793421A (en) | Three-dimensional point cloud data processing method and system for substation equipment and storage medium | |
| CN111199188A (en) | Pixel processing method and device for remote sensing image difference map, storage medium and equipment | |
| CN114820662A (en) | Road side visual angle ground segmentation method, system and medium based on point cloud two-dimensional density | |
| CN113763308B (en) | Ground detection method, device, server and medium | |
| CN115376106A (en) | Vehicle type identification method, device, equipment and medium based on radar map | |
| JP3006602B1 (en) | Road white line detection method and device | |
| CN114821978A (en) | Method, device and medium for eliminating false alarm | |
| CN114842166A (en) | Negative obstacle detection method, system, medium, and apparatus applied to structured road | |
| CN114266721A (en) | Fence detection method and device based on superpixel, storage medium and equipment | |
| CN112785550A (en) | Image quality value determination method, image quality value determination device, storage medium, and electronic device | |
| JP2924693B2 (en) | Extraction method of texture area in 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200522 |