CN106204547A - The method automatically extracting shaft-like atural object locus from Vehicle-borne Laser Scanning point cloud - Google Patents
The method automatically extracting shaft-like atural object locus from Vehicle-borne Laser Scanning point cloud Download PDFInfo
- Publication number
- CN106204547A CN106204547A CN201610504709.4A CN201610504709A CN106204547A CN 106204547 A CN106204547 A CN 106204547A CN 201610504709 A CN201610504709 A CN 201610504709A CN 106204547 A CN106204547 A CN 106204547A
- Authority
- CN
- China
- Prior art keywords
- shaft
- cloud
- atural object
- point cloud
- point
- 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
Classifications
-
- 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
Landscapes
- Image Processing (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a kind of method automatically extracting shaft-like atural object locus from Vehicle-borne Laser Scanning point cloud, it is first from Vehicle-borne Laser Scanning point cloud, optimal spatial demixing point cloud plane projection image;The optimal spatial demixing point cloud plane projection image generated is carried out Threshold segmentation, removes the point that brightness is low;Plane projection image after Threshold segmentation is carried out straight-line detection, removes the data with line feature;Image is extracted further, removes the data division not meeting shaft-like atural object characteristics of diameters, obtain shaft-like atural object projection picture;Last from shaft-like atural object projection picture, take the geometric center of each shaft-like ground object area, as the locus anchor point of shaft-like atural object, and by its relative position recovering to three-dimensional point cloud.The inventive method is susceptible to the impact of data noise point, and automaticity is high, takes full advantage of the morphological characteristic of cloud data to a greater extent, has reached preferable extraction effect.
Description
Technical field
The invention belongs to Vehicle-borne Laser Scanning Point Cloud Processing technical field.
Background technology
Vehicle-mounted mobile laser measurement system is as the measurement means of a kind of advanced person, the application in the three dimensional data collection of city
Increasingly wider, system acquisition to three-dimensional information include the building of road both sides, trees, electric light bar, electric lines of force, bridge and
Pavement of road etc..Shaft-like atural object is facility the most universal in Municipal Component, along with the fast development of smart city, is badly in need of obtaining
The most shaft-like atural object spatial positional information.Currently for the research of Objects extraction shaft-like in laser point cloud, main
Clustering procedure to be had and projected density method, both approaches is all based on the cloud data of entirety, easily by noise spot in cloud data
Impact, method applicability is the highest.The most preferably excavate the morphological characteristic of cloud data, improve shaft-like atural object locus and extract
Precision and efficiency, remain one of current Research Challenges.
Summary of the invention
For above-mentioned technical problem, the present invention by research point Vehicle-borne Laser Scanning data genaration based on the plane counted
Projection picture, uses the mode of image procossing, in conjunction with geometric shape and the feature of shaft-like atural object, it is proposed that a kind of vehicle-mounted laser is swept
The method that in described point cloud, shaft-like atural object spatial positional information automatically extracts, extracts shaft-like atural object, it is possible to from massive point cloud
Data are extracted shaft-like atural object spatial positional information fast and automatically.
To achieve these goals, the present invention adopts the following technical scheme that
A kind of method automatically extracting shaft-like atural object locus from Vehicle-borne Laser Scanning point cloud, comprises the steps:
The first step, from Vehicle-borne Laser Scanning point cloud, the space of shaft-like atural object in the vertical direction in acquisition subrange
Layering cloud data, carries out plane projection to space delamination point cloud, according to scope and the plane coordinates of space delamination point cloud, and will be from
The laser point cloud dissipated projects in plane, with the brightness value of unit picture element point cloud quantity definition pixel, is converted into the figure of two dimension
As data, and automatically obtain optimal spatial demixing point cloud plane projection image;
Second step, carries out Threshold segmentation to the optimal spatial demixing point cloud plane projection image generated, removes brightness low
Point, the less laser spots of sustained height number of ranges will remove in cloud data;
3rd step, carries out straight-line detection to the plane projection image after Threshold segmentation, removes the data with line feature, i.e.
The wall data of building in cloud data is removed;
4th step, extracts further to image, removes the data division not meeting shaft-like atural object characteristics of diameters, obtains
Shaft-like atural object projection picture;
5th step, from shaft-like atural object projection picture, takes the geometric center of each shaft-like ground object area, as shaft-like atural object
Locus anchor point, and by its relative position recovering to three-dimensional point cloud.
The invention have the advantage that
The present invention, according to laser point cloud data, automatically obtains space delamination data, and automatically chooses optimal spatial hierarchy number
According to carrying out plane projection, by analyzing the feature of shaft-like atural object, carry out shaft-like atural object to based on the plane projection image counted
Extracting, be susceptible to the impact of data noise point, automaticity is high, and the form taking full advantage of cloud data to a greater extent is special
Levy, reached preferable extraction effect.
Accompanying drawing explanation
Fig. 1 is the flow chart that the present invention implements;
Fig. 2 is automatically to obtain optimal spatial demixing point cloud projection picture;
Fig. 3 is the demixing point cloud projection picture having more different high-rise point;
Fig. 4 is demixing point cloud projection picture after filtering;
Fig. 5 is the locus projection picture of shaft-like atural object.
The projection of Fig. 2-Fig. 5 seems to be inverted, by white with black dot image, the white with black dot image obtained.
Detailed description of the invention
The present invention, according to the flow chart accompanying drawing 1 of summary of the invention and enforcement, can be implemented by those skilled in the art.For
Convenient to carry out, below each step in summary of the invention is described in further detail, during detailed description, gives Fig. 2-Fig. 5
Instantiation, example is only as a example by the extraction of other two the shaft-like object coordinates locus of building.
One, the detailed description to summary of the invention first step:
1, vertical direction space delamination point cloud automatically extracts
Being distributed according to actual building space height, be first layered a cloud according to vertical direction entirety, every 2m divides one
Point cloud layer, in acquisition subrange, a series of space delamination cloud datas of in the vertical direction, are set to l1, l2, l3……lN;
2, successively each some cloud layer is carried out plane projection
With x/y plane as perspective plane, the negative direction in z direction is projecting direction, projects laser point cloud, by building,
Road, shaft-like atural object etc. project under projected coordinate system;
3, generate based on the plane projection image counted
According to current some cloud scope, the cloud coordinate that sets up an office is (X, Y, Z), and some cloud scope is { Xmin, Ymin,Zmin, Xmax, Ymax,
Zmax, the pixel coordinate of image is that (x, y), scaling precision is s, then (x, y) difference of some cloud coordinate (X, Y, Z) correspondence image
It is: x=(X-Xmin) × s, y=(Y-Ymin)×s;
In unit picture element, the brightness of point is the brightness superposition falling and putting cloud number in unit picture element, if often there being a some cloud to turn
Change into (x, y), this brightness value increase by 30%;
Travel through all cloud datas, calculate the plane projection image coordinate of its correspondence, and carry out brightness superposition, obtain optimum
There is a cloud layer in space based on the plane projection image counted, thus generates N number of plane projection image:
4, optimal spatial demixing point cloud is automatically obtained
The N number of plane projection image generated is carried out rough boxed area circumscribed circle detection, calculates circumscribed circle diameter, choosing
Take the more diameter plane projection image close to actual shaft-like atural object diameter, as optimal spatial demixing point cloud projection picture,
Carry out next step shaft-like Objects extraction.
Fig. 2 is shown in which an optimal spatial demixing point cloud projection picture, containing multiple shaft-like culture point clouds in image
Projection picture, wherein has P1 and P2 from the shaft-like atural object pixel that top building is nearest.
In order to prove the accuracy of the present invention, project to P1 and P2 learn under projected coordinate system, P1 coordinate
(509170.2306,3985536.5028,75.0464), P2 coordinate (509173.3905,3985537.3584,74.6881),
Being converted into plane projection image recoil and being designated as P1 ' coordinate is (293,161), and P2 ' coordinate is (354,181).
Two, the detailed description to summary of the invention second step:
By the method for existing adaptive threshold, optimal spatial demixing point cloud projection picture as shown in Figure 2 is carried out threshold value to divide
Cut, i.e. by calculating the weighted average of pixel peripheral region, then deduct a constant to obtain adaptive threshold, to obtaining
Plane projection image carry out Threshold segmentation, obtain the region that brightness is bigger.
As it is shown on figure 3, P1 ' and the brightness of P2 ' position are relatively big, therefore it is effectively maintained.This subregion
There are the data of more different high-rise point in i.e. corresponding point cloud being perpendicular to the unit range of x/y plane, meet shaft-like atural object Vertical Square
Upwards there is the feature of relatively multiple spot.
Three, the detailed description to summary of the invention third step:
Image after Threshold segmentation is carried out straight-line detection, removes the part of obvious wired characteristic in image, by these portions
Split as background colour, the impact on shaft-like Objects extraction result such as building walls in actual three dimensional point cloud.
As shown in Figure 4, after the image shown in Fig. 3 is excluded building walls impact, so that it may obtain figure as shown in Figure 4
Picture.
Four, the detailed description to summary of the invention the 4th step:
The part that brightness in image after excluding building walls impact is big is carried out regional area growth, extracts every
These regions are filtered by the region that one Block Brightness is big: first extract monolithic zone boundary, if this zone boundary circularity
Less than 0.2, then the inclined linear in this region, do not meet the feature of shaft-like atural object, get rid of;Extract monolithic region again, calculate outside minimum
Connecing diameter of a circle, the distance being converted in cloud data, if these data are much smaller than or are much larger than actual shaft-like atural object diameter, then
Do not meet the feature of shaft-like atural object, got rid of;Judge whether the distance of n adjacent rod atural object meets actual shaft-like atural object again
Spacing, meet, retain, otherwise delete.
As it is shown in figure 5, by after image filtering as shown in Figure 4, finally give shaft-like atural object projection picture shown in Fig. 5.
Five, the detailed description to summary of the invention the 5th step:
1, shaft-like atural object central point is calculated
For shaft-like atural object projection as remaining region, extract the border in region, ask the center of circle of its minimum circumscribed circle, make
Central point for shaft-like atural object;
2, shaft-like atural object center point coordinate is converted into a cloud coordinate
Shaft-like culture point coordinate is set to that (x, y), then corresponding some cloud coordinate (X, Y, Z) is: X=x/s+Xmin, Y=y/s+
Ymin, Z-direction coordinate takes the intermediate value of Z-direction when a cloud carries out space delamination;(X, Y, the Z) that obtain is shaft-like atural object
Locus.
As it is shown in figure 5, by P1 and P2 center point coordinate P1 ' (293,162) in image shown in Fig. 4 and P2 ' (354,179),
It is converted into a cloud coordinate as follows:
P1’(509170.2535,3985536.5059,75.0235);
P2’(509173.2149,3985537.4218,75.0235)。
The above-mentioned some cloud coordinate being converted into and the coordinate projecting in projected coordinate system, both are basically identical, it was demonstrated that this
Bright method may apply to the extraction of actual shaft-like atural object.
Claims (6)
1. the method automatically extracting shaft-like atural object locus from Vehicle-borne Laser Scanning point cloud, it is characterised in that include
Following steps:
The first step, from Vehicle-borne Laser Scanning point cloud, the space delamination of shaft-like atural object in the vertical direction in acquisition subrange
Cloud data, carries out plane projection to space delamination point cloud, according to scope and the plane coordinates of space delamination point cloud, by discrete
Laser point cloud projects in plane, with the brightness value of unit picture element point cloud quantity definition pixel, is converted into the picture number of two dimension
According to, and automatically obtain optimal spatial demixing point cloud plane projection image;
Second step, carries out Threshold segmentation to the optimal spatial demixing point cloud plane projection image generated, removes the point that brightness is low, i.e.
The less laser spots of sustained height number of ranges in cloud data is removed;
3rd step, carries out straight-line detection to the plane projection image after Threshold segmentation, removes the data with line feature, Ji Jiangdian
In cloud data, the wall data of building removes;
4th step, extracts further to image, removes the data division not meeting shaft-like atural object characteristics of diameters, obtains shaft-like
Atural object projection picture;
5th step, from shaft-like atural object projection picture, takes the geometric center of each shaft-like ground object area, as the sky of shaft-like atural object
Between position anchor point, and by its relative position recovering to three-dimensional point cloud.
2. the method for claim 1, it is characterised in that the detailed step of the described first step is:
1.1, vertical direction space delamination point cloud automatically extracts
Being distributed according to actual building space height, be first layered a cloud according to vertical direction entirety, every 2m divides a some cloud
Layer, in acquisition subrange, a series of space delamination cloud datas of in the vertical direction, are set to l1, l2, l3……lN;
1.2, successively each some cloud layer is carried out plane projection
With x/y plane as perspective plane, the negative direction in z direction is projecting direction, projects laser point cloud, by building, road
Road, shaft-like atural object project under projected coordinate system;
1.3, generate based on the plane projection image counted
According to current some cloud scope, the cloud coordinate that sets up an office is (X, Y, Z), and some cloud scope is { Xmin, Ymin,Zmin, Xmax, Ymax, Zmax,
The pixel coordinate of image be (x, y), scaling precision is s, then some cloud coordinate (X, Y, Z) correspondence image (x, y) respectively: x=
(X-Xmin) × s, y=(Y-Ymin)×s;
In unit picture element, the brightness of point is the brightness superposition falling and putting cloud number in unit picture element, if often there being a some cloud to be converted into
(x, y), this brightness value increases by 30% to pixel;
Travel through all cloud datas, calculate the plane projection image coordinate of its correspondence, and carry out brightness superposition, obtain optimal spatial
There is a cloud layer based on the plane projection image counted, thus generated N number of plane projection image;
1.4, optimal spatial demixing point cloud is automatically obtained
The N number of plane projection image generated is carried out rough boxed area circumscribed circle detection, calculates circumscribed circle diameter, chosen
More diameter, close to the plane projection image of actual shaft-like atural object diameter, as optimal spatial demixing point cloud projection picture, is carried out
Next step shaft-like Objects extraction.
3. the method for claim 1, it is characterised in that the detailed step of described second step is:
During Threshold segmentation, by the method for adaptive threshold, optimal spatial demixing point cloud projection picture is carried out image segmentation, the most logical
Cross the weighted average calculating pixel peripheral region, then deduct a constant to obtain adaptive threshold, to the plane obtained
Projection picture carries out Threshold segmentation, obtains the region that brightness is bigger;This subregion i.e. corresponding point cloud is perpendicular to x/y plane
There are the data of more different high-rise point in unit range, meet the feature having relatively multiple spot in shaft-like atural object vertical direction.
4. method as claimed in claim 1, it is characterised in that the detailed step of described 3rd step is:
Image after Threshold segmentation is carried out straight-line detection, removes the part of obvious wired characteristic in image, these parts are put
For background colour, the impact on shaft-like Objects extraction result of the building walls in actual three dimensional point cloud can be excluded.
5. the method for claim 1, it is characterised in that the detailed step of described 4th step is:
The part that brightness in image is big is carried out regional area growth, extracts the region that each Block Brightness is big, to these regions
It is filtered: first extract monolithic zone boundary, if < 0.2, then the inclined linear in this region, is not inconsistent this zone boundary circularity
Close the feature of shaft-like atural object, get rid of;Extract monolithic region again, calculate the diameter of minimum circumscribed circle, be converted in cloud data
Distance, if these data are much smaller than or much larger than actual shaft-like atural object diameter, then do not meet the feature of shaft-like atural object, arranged
Remove;Obtain shaft-like atural object projection picture.
6. the method for claim 1, it is characterised in that the detailed step of described 5th step is:
5.1, shaft-like atural object central point is calculated
For remaining region, extract monolithic zone boundary, ask the center of circle of its minimum circumscribed circle, as the center of shaft-like atural object
Point;
5.2, shaft-like atural object center point coordinate is converted into a cloud coordinate
Shaft-like atural object center point coordinate is set to that (x, y), then corresponding some cloud coordinate (X, Y, Z) is: X=x/s+Xmin, Y=y/s+
Ymin, Z-direction takes the intermediate value of Z-direction when a cloud carries out space delamination;
(X, Y, the Z) that obtain is the locus of shaft-like atural object.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610504709.4A CN106204547B (en) | 2016-06-29 | 2016-06-29 | The method that rod-shaped atural object spatial position is automatically extracted from Vehicle-borne Laser Scanning point cloud |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610504709.4A CN106204547B (en) | 2016-06-29 | 2016-06-29 | The method that rod-shaped atural object spatial position is automatically extracted from Vehicle-borne Laser Scanning point cloud |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106204547A true CN106204547A (en) | 2016-12-07 |
CN106204547B CN106204547B (en) | 2018-08-14 |
Family
ID=57462737
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610504709.4A Active CN106204547B (en) | 2016-06-29 | 2016-06-29 | The method that rod-shaped atural object spatial position is automatically extracted from Vehicle-borne Laser Scanning point cloud |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106204547B (en) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108376416A (en) * | 2018-01-16 | 2018-08-07 | 天津大学 | A kind of image generating method and device |
CN108447126A (en) * | 2018-01-29 | 2018-08-24 | 山东科技大学 | Traverse measurement system laser point cloud precision assessment method based on reference planes |
CN109410282A (en) * | 2018-11-08 | 2019-03-01 | 上海木木聚枞机器人科技有限公司 | A kind of detecting and tracking method and apparatus of transfusion pole |
CN110619663A (en) * | 2019-08-28 | 2019-12-27 | 山东科技大学 | Video image target positioning method based on three-dimensional laser point cloud |
CN110866948A (en) * | 2019-11-26 | 2020-03-06 | 湖南农业大学 | Novel method for estimating grain volume morphological parameters by using three-dimensional scanning point cloud |
CN110928301A (en) * | 2019-11-19 | 2020-03-27 | 北京小米智能科技有限公司 | Method, device and medium for detecting tiny obstacles |
CN111127530A (en) * | 2019-12-24 | 2020-05-08 | 山东科技大学 | Accurate registration method for three-dimensional laser point clouds of multi-phase roads |
CN111291662A (en) * | 2020-01-21 | 2020-06-16 | 武汉大学 | Vehicle-mounted point cloud rod-shaped object extraction method based on plane selection |
CN111928782A (en) * | 2017-07-21 | 2020-11-13 | 株式会社多田野 | Method for estimating upper surface of object to be measured, guidance information display device, and crane |
CN111932574A (en) * | 2020-09-01 | 2020-11-13 | 重庆市勘测院 | Building facade point cloud extraction system and method based on multi-level semantic features |
CN112446314A (en) * | 2020-11-19 | 2021-03-05 | 武汉中海庭数据技术有限公司 | Method and system for extracting guardrail elevation based on projection drawing |
CN112595258A (en) * | 2020-11-23 | 2021-04-02 | 扆亮海 | Ground object contour extraction method based on ground laser point cloud |
CN112836681A (en) * | 2021-03-03 | 2021-05-25 | 上海高仙自动化科技发展有限公司 | Obstacle marking method and device and readable non-transitory storage medium |
CN113487746A (en) * | 2021-05-25 | 2021-10-08 | 武汉海达数云技术有限公司 | Optimal associated image selection method and system in vehicle-mounted point cloud coloring |
CN115564673A (en) * | 2022-09-26 | 2023-01-03 | 浙江省测绘科学技术研究院 | Method and system for extracting three-dimensional point cloud underground garage column and automatically generating vector |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070024620A1 (en) * | 2005-08-01 | 2007-02-01 | Muller-Fischer Matthias H | Method of generating surface defined by boundary of three-dimensional point cloud |
CN103473734A (en) * | 2013-09-16 | 2013-12-25 | 南京大学 | Power line extracting and fitting method based on in-vehicle LiDAR data |
-
2016
- 2016-06-29 CN CN201610504709.4A patent/CN106204547B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070024620A1 (en) * | 2005-08-01 | 2007-02-01 | Muller-Fischer Matthias H | Method of generating surface defined by boundary of three-dimensional point cloud |
CN103473734A (en) * | 2013-09-16 | 2013-12-25 | 南京大学 | Power line extracting and fitting method based on in-vehicle LiDAR data |
Non-Patent Citations (3)
Title |
---|
MATTI LEHTOMÄKI ET AL: "Detection of vertical pole-like objects in a road environment using vehicle-based laser scanning data", 《REMOTE SENSING》 * |
吴宾 等: "一种基于车载激光扫描点云数据的单株行道树信息提取方法", 《华东师范大学学报(自然科学版)》 * |
李永强 等: "车载激光扫描数据中杆状地物提取", 《测绘科学》 * |
Cited By (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111928782A (en) * | 2017-07-21 | 2020-11-13 | 株式会社多田野 | Method for estimating upper surface of object to be measured, guidance information display device, and crane |
CN108376416A (en) * | 2018-01-16 | 2018-08-07 | 天津大学 | A kind of image generating method and device |
CN108447126A (en) * | 2018-01-29 | 2018-08-24 | 山东科技大学 | Traverse measurement system laser point cloud precision assessment method based on reference planes |
CN108447126B (en) * | 2018-01-29 | 2021-08-17 | 山东科技大学 | Laser point cloud precision evaluation method of mobile measurement system based on reference plane |
CN109410282A (en) * | 2018-11-08 | 2019-03-01 | 上海木木聚枞机器人科技有限公司 | A kind of detecting and tracking method and apparatus of transfusion pole |
CN110619663A (en) * | 2019-08-28 | 2019-12-27 | 山东科技大学 | Video image target positioning method based on three-dimensional laser point cloud |
CN110928301A (en) * | 2019-11-19 | 2020-03-27 | 北京小米智能科技有限公司 | Method, device and medium for detecting tiny obstacles |
CN110928301B (en) * | 2019-11-19 | 2023-06-30 | 北京小米智能科技有限公司 | Method, device and medium for detecting tiny obstacle |
CN110866948A (en) * | 2019-11-26 | 2020-03-06 | 湖南农业大学 | Novel method for estimating grain volume morphological parameters by using three-dimensional scanning point cloud |
CN110866948B (en) * | 2019-11-26 | 2023-11-24 | 湖南农业大学 | New method for estimating volume morphological parameters of grains by utilizing three-dimensional scanning point cloud |
CN111127530B (en) * | 2019-12-24 | 2023-06-20 | 山东科技大学 | Multi-period road three-dimensional laser point cloud accurate registration method |
CN111127530A (en) * | 2019-12-24 | 2020-05-08 | 山东科技大学 | Accurate registration method for three-dimensional laser point clouds of multi-phase roads |
CN111291662B (en) * | 2020-01-21 | 2022-06-07 | 武汉大学 | Vehicle-mounted point cloud rod-shaped object extraction method based on plane selection |
CN111291662A (en) * | 2020-01-21 | 2020-06-16 | 武汉大学 | Vehicle-mounted point cloud rod-shaped object extraction method based on plane selection |
CN111932574B (en) * | 2020-09-01 | 2023-05-23 | 重庆市勘测院 | Building vertical point cloud extraction system and method based on multi-level semantic features |
CN111932574A (en) * | 2020-09-01 | 2020-11-13 | 重庆市勘测院 | Building facade point cloud extraction system and method based on multi-level semantic features |
CN112446314A (en) * | 2020-11-19 | 2021-03-05 | 武汉中海庭数据技术有限公司 | Method and system for extracting guardrail elevation based on projection drawing |
CN112446314B (en) * | 2020-11-19 | 2022-07-29 | 武汉中海庭数据技术有限公司 | Method and system for extracting guardrail elevation based on projection drawing |
CN112595258B (en) * | 2020-11-23 | 2022-04-22 | 湖南航天智远科技有限公司 | Ground object contour extraction method based on ground laser point cloud |
CN112595258A (en) * | 2020-11-23 | 2021-04-02 | 扆亮海 | Ground object contour extraction method based on ground laser point cloud |
CN112836681A (en) * | 2021-03-03 | 2021-05-25 | 上海高仙自动化科技发展有限公司 | Obstacle marking method and device and readable non-transitory storage medium |
CN112836681B (en) * | 2021-03-03 | 2024-01-26 | 上海高仙自动化科技发展有限公司 | Obstacle marking method and device and readable non-transitory storage medium |
CN113487746B (en) * | 2021-05-25 | 2023-02-24 | 武汉海达数云技术有限公司 | Optimal associated image selection method and system in vehicle-mounted point cloud coloring |
CN113487746A (en) * | 2021-05-25 | 2021-10-08 | 武汉海达数云技术有限公司 | Optimal associated image selection method and system in vehicle-mounted point cloud coloring |
CN115564673A (en) * | 2022-09-26 | 2023-01-03 | 浙江省测绘科学技术研究院 | Method and system for extracting three-dimensional point cloud underground garage column and automatically generating vector |
CN115564673B (en) * | 2022-09-26 | 2024-03-15 | 浙江省测绘科学技术研究院 | Three-dimensional point cloud underground garage column extraction and vector automatic generation method and system |
Also Published As
Publication number | Publication date |
---|---|
CN106204547B (en) | 2018-08-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106204547A (en) | The method automatically extracting shaft-like atural object locus from Vehicle-borne Laser Scanning point cloud | |
CN106650640B (en) | Negative obstacle detection method based on laser radar point cloud local structure characteristics | |
CN111291708B (en) | Transformer substation inspection robot obstacle detection and identification method integrated with depth camera | |
CN105513127B (en) | Shaft regularization three-dimensional modeling method and system based on density peaks cluster | |
CN106067003B (en) | Automatic extraction method for road vector identification line in vehicle-mounted laser scanning point cloud | |
CN105184852B (en) | A kind of urban road recognition methods and device based on laser point cloud | |
CN111079611B (en) | Automatic extraction method for road surface and marking line thereof | |
Wu et al. | Rapid localization and extraction of street light poles in mobile LiDAR point clouds: A supervoxel-based approach | |
CN102103202B (en) | Semi-supervised classification method for airborne laser radar data fusing images | |
CN102930509B (en) | Intelligent filtering method for airborne laser point cloud data | |
CN106199558A (en) | Barrier method for quick | |
CN111325138B (en) | Road boundary real-time detection method based on point cloud local concave-convex characteristics | |
CN109118500A (en) | A kind of dividing method of the Point Cloud Data from Three Dimension Laser Scanning based on image | |
CN108845569A (en) | Generate semi-automatic cloud method of the horizontal bend lane of three-dimensional high-definition mileage chart | |
CN105551082A (en) | Method and device of pavement identification on the basis of laser-point cloud | |
CN112070769A (en) | Layered point cloud segmentation method based on DBSCAN | |
CN112633092B (en) | Road information extraction method based on vehicle-mounted laser scanning point cloud | |
CN103679655A (en) | LiDAR point cloud filter method based on gradient and area growth | |
CN110349260A (en) | A kind of pavement strip extraction method and device | |
CN106525000A (en) | A road marking line automatic extracting method based on laser scanning discrete point strength gradients | |
CN110532963B (en) | Vehicle-mounted laser radar point cloud driven road marking accurate extraction method | |
CN114359876B (en) | Vehicle target identification method and storage medium | |
EP4174792A1 (en) | Method for scene understanding and semantic analysis of objects | |
KR101549155B1 (en) | Method of automatic extraction of building boundary from lidar data | |
CN114359866A (en) | Road boundary detection method and device based on laser radar |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |