CN105447855A - Terrestrial 3D laser scanning point cloud spherical target automatic identification method - Google Patents
Terrestrial 3D laser scanning point cloud spherical target automatic identification method Download PDFInfo
- Publication number
- CN105447855A CN105447855A CN201510780431.9A CN201510780431A CN105447855A CN 105447855 A CN105447855 A CN 105447855A CN 201510780431 A CN201510780431 A CN 201510780431A CN 105447855 A CN105447855 A CN 105447855A
- Authority
- CN
- China
- Prior art keywords
- target
- sphere
- point cloud
- laser
- information
- 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
- Length Measuring Devices By Optical Means (AREA)
Abstract
A terrestrial 3D laser scanning point cloud spherical target automatic identification method comprises the following steps: retaining distance and angle information in the polar coordinate information in the process in which original data scanned by a laser scanner is transformed from 3D polar coordinate information into 3D right-angle coordinate information; quickly and roughly identifying a spherical target according to the angle, distance and gray information; fitting the data of the spherical target according to the 3D right-angle coordinates thereof; and judging whether the target is a real sphere based on the tolerance after point cloud fitting as well as the standard deviation, sphere radius and center-of-sphere information. According to the spherical target identification method provided by the invention, a target is identified preliminarily based on the measurement principle of the laser scanner and according to distance, gray and other information, the speed and accuracy of spherical target identification are improved, the rate of mistaken target identification is low, and the target information can be automatically identified for users to use after the scanner completes scanning.
Description
Technical field
The present invention relates to a kind of Motion parameters method, particularly a kind of Three Dimensional Ground laser scanning point cloud sphere Motion parameters method, belongs to Motion parameters field.
Background technology
Since two thousand; Three Dimensional Ground laser scanner technique (Terrestriallaserscanning; TLS) since achievement obtains substantive application; along with the progress of spatial digitizer hardware; become survey field another revolutionary achievement after GPS technology at present, in conservation of historic buildings, urban digital, deformation monitoring, archaeology, traffic etc., each gets the application that bears fruit in succession.
In the application process of three-dimensional laser scanner, often run into the automatic abstraction function of some feature dough sheets, particularly the automatic abstraction function of sphere sheet is particularly important, as when scanner works, in order to all data whole scene scanned are stitched together, usually need to lay many artificial targets or orientation mark between scanning movement and station, as plane target drone, centre of sphere target etc., wherein to have decipherment distance far away due to it for centre of sphere mark, no matter from what scanning direction, the center of ball is all same, also has the factor such as easy to make to become main flow gradually.
In the processing procedure of big data quantity, usually the means adopted at present adopt the mode of manual extraction sphere target to process, utilize the mode of man-machine interactively, the Data Segmentation of sphere data and surrounding is opened, and then the mode of matching processes, can only searching one by one, compare and take time and effort.
In the automatic identification sphere computing method of present stage, be mostly that to have normal direction according to umbilical point cloud feature not identical, point to all directions of surrounding.Its Gaussian mapping be projected as one centered by initial point, take unit as the unit ball of radius.According on umbilical point cloud dough sheet maximum principal curvatures a little equal with minimum principal curvatures, and its principal curvaturess of some cloud all on sphere is all equal.By judging to treat that whether the principal curvatures of judging point cloud dough sheet levels off to a constant, determines whether umbilical point cloud.But the shortcoming of this method needs to carry out a large amount of data to calculate, because the data volume of cloud data itself is just very large, then carry out a large amount of curvature method arrow calculating, cause data processing slow, actual use cannot be obtained in engineering.
Summary of the invention
Technology of the present invention is dealt with problems and is: overcome the deficiencies in the prior art, provide a kind of Three Dimensional Ground laser scanning point cloud sphere Motion parameters method, achieve the quick identification and extraction of ball object, there is recognition accuracy high, the advantages such as occupying system resources is low, and speed is fast.
Technical solution of the present invention is: a kind of Three Dimensional Ground laser scanning point cloud sphere Motion parameters method, comprises the following steps:
(1) utilize three-dimensional laser scanner to scan target, obtain the laser point cloud origin pole coordinate information of target, described origin pole coordinate information comprises horizontal angle, vertical angle, impact point Distance geometry gray scale; Described impact point distance is the coordinate at certain some distance three-dimensional laser scanner center in target laser point cloud;
(2) target laser point cloud origin pole coordinate information step (1) obtained is transformed into rectangular coordinate system;
(3) under rectangular coordinate system, by the target laser point cloud horizontal angle interval that presets and vertical angle interval, according to the horizontal angle step-length preset and vertical angle step-length grid division, each grid cell is a feed search region;
(4) for a thread is set up in each feed search region, target laser point in each feed search region is traveled through, obtain the range information of each point in every bit and same seed region of search, in in same seed region of search, the range information met between this point is all greater than the impact point distance of this point, and meet from this point more away from, the region that the larger each point of its impact point distance is formed is classified as target area;
(5) gray scale of target area is judged, if the gray scale of target area weakens outward gradually from central point, then enter step (6); Otherwise, give up this target area;
(6) least square sphere surface fitting is carried out to the some cloud in target area, calculate the standard deviation of sphere information and fitting data, if the standard deviation of fitting data is less than or equal to predetermined threshold value, then sphere information is exported, and this target area is labeled as sphere target, otherwise, give up this target area.
Described laser scanner is ground three-dimensional laser scanner.
Described ground three-dimensional laser scanner comprises: pulsed three-dimensional laser scanner and phase type three-dimensional laser scanner.
Described horizontal angle is obtained by laser scanner horizontal revolving stage, and vertical angle is obtained by the vertical tilting mirror of laser scanner, and impact point Distance geometry gray scale is obtained by laser ranging.
Described predetermined threshold value equals the cloud data precision that presets or sphere obtains precision.
Described horizontal angle interval is: 0 ~ 360 °; Vertical angle interval is: 0 ~ 360 °.
Described horizontal angle step-length and vertical angle step-length are determined according to allocation of computer, and the setting of horizontal angle step-length and vertical angle step-length is less than the arithmetic capability equaling to exceed computing machine.
The present invention's beneficial effect is compared with prior art:
(1) the present invention utilizes Three Dimensional Ground laser scanner directly to obtain the polar coordinates information of sphere target, and the automatic identification of sphere target is carried out based on this polar coordinates information, avoid the artificial extraction huge workload of feature and the big data quantity of curvature computing in prior art, improve the efficiency of sphere Motion parameters, occupying system resources is low;
(2) the present invention utilizes range information in raw data and half-tone information as Rule of judgment, only need during computing in software to compare calculating, just can judge whether it is the data of spherical class object scan, then the artificial setting of sphere surface fitting threshold value is utilized, accurately determine whether real sphere target, effectively improve sphere target is other efficiency and precision automatically;
(3) the present invention utilizes multithreading to process data, substantially increases the arithmetic speed of algorithm.
Accompanying drawing explanation
Fig. 1 is data processing method process flow diagram of the present invention.
Embodiment
Below in conjunction with accompanying drawing, the specific embodiment of the present invention is further described in detail.
Be illustrated in figure 1 process flow diagram of the present invention, as can be seen from Figure 1, a kind of Three Dimensional Ground laser scanning point cloud sphere Motion parameters method that the present invention proposes, step is as follows:
(1) utilize three-dimensional laser scanner to scan target, obtain the laser point cloud origin pole coordinate information of target, described origin pole coordinate information comprises horizontal angle, vertical angle, impact point Distance geometry gray scale; Described impact point distance is the coordinate at certain some distance three-dimensional laser scanner center in target laser point cloud; Described laser scanner is ground three-dimensional laser scanner, specifically comprises pulsed three-dimensional laser scanner and phase type three-dimensional laser scanner.Described horizontal angle is obtained by laser scanner horizontal revolving stage, and vertical angle is obtained by the vertical tilting mirror of laser scanner, and impact point Distance geometry gray scale is obtained by laser ranging.
(2) target laser point cloud origin pole coordinate information step (1) obtained is transformed into rectangular coordinate system;
Because this algorithm carries out quick sphere identification based on original scanning distance and scanning gray scale (reflectivity), therefore in order to the convenience of subsequent calculations, must be rebuild the form of data file, the raw data that three-dimensional laser scanner sweep object obtains is by horizontal angle, vertical angle, the data of 4 kinds of information such as the data under the three-dimensional polar system that impact point distance is formed and gray scale (reflectivity) information, later stage is in order to the convenience of three-dimensional imaging, usually general some cloud file data can be converted to, be generally and comprise X, Y, the rectangular coordinate system coordinate that Z-shaped formula represents and gray scale (reflectivity) information, for the ease of the calculating of algorithm, in data conversion process, tackle polar coordinates information retained, or according to existing XYZ information reconstruction polar coordinates information, in order to the convenience of compatible two kinds of common type of data format subsequent calculations processes in this algorithm, unified data are converted to comprises horizontal angle, vertical angle, impact point distance, X, Y, Z and gray scale (reflectivity) information, by the information fusion of these two kinds of data to together, and add a judgement sign position.
(3) under rectangular coordinate system, by the target laser point cloud horizontal angle interval that presets and vertical angle interval, according to the horizontal angle step-length preset and vertical angle step-length grid division, each grid cell is a feed search region; Described horizontal angle interval is: 0 ~ 360 °; Vertical angle interval is: 0 ~ 360 °.
In order to accelerate computing velocity, the size of data according to data of data layout will be rebuild, and the situation such as computer hardware ability, data are set up grid screen according to its horizontal angle interval and vertical angle interval, horizontal angle step-length and vertical angle step-length is utilized to form multiple region, as being divided into 4 regions, 16 regions, 64 regions, 128 regions etc.; Horizontal angle step-length and vertical angle step-length are determined according to allocation of computer, and the setting of horizontal angle step-length and vertical angle step-length is less than the arithmetic capability equaling to exceed computing machine.
(4) due to the characteristic of the same tropism of sphere, a bit orthogonal with sphere injecting must be had during scanner scanning, now this point and scanner center is nearest, then centered by this point, distance in concentric annular apart from scanner center increases gradually, waits the distance at the different some range scanner center on ring identical simultaneously.
For a thread is set up in each feed search region, target laser point in each feed search region is traveled through, obtain the range information of each point in every bit and same seed region of search, in in same seed region of search, the range information met between this point is all greater than the impact point distance of this point, and meet from this point more away from, the region that the larger each point of its impact point distance is formed is classified as target area;
(5) from laser instrument reflectivity calculating principle, when other conditions are identical, when body surface is orthogonal with light, the reflectivity on surface is the highest, along with gradually changing of body surface and light angle, and the gradual change in reflectivity of object, therefore the reflection characteristic of sphere is satisfied with, when laser beam is orthogonal with sphere, the reflectivity of sphere is the highest, then centered by this point, reduces gradually in concentric annular.
Therefore the gray scale of target area is judged, if the gray scale of target area weakens outward gradually from central point, then enter step (6); Otherwise, give up this target area;
(6) carry out least square sphere surface fitting to the some cloud in target area, calculate the standard deviation of sphere information and fitting data, basic representation is:
f(x,y,z)=x
2+y
2+z
2+dx+ey+fz+f=0
If the initial spherical coordinates Pi judged to be calculated is as (x
i, y
i, z
i) i=1,2,3 ..., n, corresponding criterion of least squares can be expressed as
calculate sphere information and corresponding residual values, if the standard deviation of fitting data is less than or equal to predetermined threshold value, then sphere information is exported, and this target area is labeled as sphere target, give up this target area.Described predetermined threshold value equals the cloud data precision that presets or sphere obtains precision.
Specific embodiment
The point cloud that the present invention scans using an independent scan scene is as test, and data point cloud quantity is about 8,000,000 points, and containing 4 sphere target targets in scene, test computer is common notebook, inside saves as 4g, and dominant frequency is 2.2Ghz; In reality test, altogether 64 threads are established to data, meet the number of the original ball Area Objects that distance condition judges and sphere gray scale decision condition judges as 5, the sphere surface fitting error parameter of setting is 5mm, after sphere surface fitting, the sphere target obtained is 4, and the target of erroneous judgement is exported the head that discovery is and a sphere cylinder relatively.In whole test process, from digital independent to the identification of sphere target export for consuming time about 2 points 20 seconds.
After tested surface, the spheroid target in Three Dimensional Ground laser scanning point cloud can be identified by this kind of method fast, there is efficiency high, accuracy high, and can meet user according to demand precision automatically select the function of sphere target.
The content be not described in detail in instructions of the present invention belongs to the known technology of professional and technical personnel in the field.
Claims (7)
1. a Three Dimensional Ground laser scanning point cloud sphere Motion parameters method, is characterized in that comprising the following steps:
(1) utilize three-dimensional laser scanner to scan target, obtain the laser point cloud origin pole coordinate information of target, described origin pole coordinate information comprises horizontal angle, vertical angle, impact point Distance geometry gray scale; Described impact point distance is the coordinate at certain some distance three-dimensional laser scanner center in target laser point cloud;
(2) target laser point cloud origin pole coordinate information step (1) obtained is transformed into rectangular coordinate system;
(3) under rectangular coordinate system, by the target laser point cloud horizontal angle interval that presets and vertical angle interval, according to the horizontal angle step-length preset and vertical angle step-length grid division, each grid cell is a feed search region;
(4) for a thread is set up in each feed search region, target laser point in each feed search region is traveled through, obtain the range information of each point in every bit and same seed region of search, in in same seed region of search, the range information met between this point is all greater than the impact point distance of this point, and meet from this point more away from, the region that the larger each point of its impact point distance is formed is classified as target area;
(5) gray scale of target area is judged, if the gray scale of target area weakens outward gradually from central point, then enter step (6); Otherwise, give up this target area;
(6) least square sphere surface fitting is carried out to the some cloud in target area, calculate the standard deviation of sphere information and fitting data, if the standard deviation of fitting data is less than or equal to predetermined threshold value, then sphere information is exported, and this target area is labeled as sphere target, otherwise, give up this target area.
2. a kind of Three Dimensional Ground laser scanning point cloud sphere Motion parameters method according to claim 1, is characterized in that: described laser scanner is ground three-dimensional laser scanner.
3. a kind of Three Dimensional Ground laser scanning point cloud sphere Motion parameters method according to claim 2, is characterized in that: described ground three-dimensional laser scanner comprises: pulsed three-dimensional laser scanner and phase type three-dimensional laser scanner.
4. a kind of Three Dimensional Ground laser scanning point cloud sphere Motion parameters method according to claim 1, it is characterized in that: described horizontal angle is obtained by laser scanner horizontal revolving stage, vertical angle is obtained by the vertical tilting mirror of laser scanner, and impact point Distance geometry gray scale is obtained by laser ranging.
5. Three Dimensional Ground laser scanning point cloud sphere Motion parameters method according to claim 1, is characterized in that: described predetermined threshold value equals the cloud data precision that presets or sphere obtains precision.
6. Three Dimensional Ground laser scanning point cloud sphere Motion parameters method according to claim 1, is characterized in that: described horizontal angle interval is: 0 ~ 360 °; Vertical angle interval is: 0 ~ 360 °.
7. Three Dimensional Ground laser scanning point cloud sphere Motion parameters method according to claim 1, it is characterized in that: described horizontal angle step-length and vertical angle step-length are determined according to allocation of computer, and the setting of horizontal angle step-length and vertical angle step-length is less than the arithmetic capability equaling to exceed computing machine.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510780431.9A CN105447855B (en) | 2015-11-13 | 2015-11-13 | A kind of Three Dimensional Ground laser scanning point cloud sphere Motion parameters method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510780431.9A CN105447855B (en) | 2015-11-13 | 2015-11-13 | A kind of Three Dimensional Ground laser scanning point cloud sphere Motion parameters method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105447855A true CN105447855A (en) | 2016-03-30 |
CN105447855B CN105447855B (en) | 2018-04-27 |
Family
ID=55557988
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510780431.9A Active CN105447855B (en) | 2015-11-13 | 2015-11-13 | A kind of Three Dimensional Ground laser scanning point cloud sphere Motion parameters method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105447855B (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107093210A (en) * | 2017-04-20 | 2017-08-25 | 北京图森未来科技有限公司 | A kind of laser point cloud mask method and device |
CN108710367A (en) * | 2018-05-23 | 2018-10-26 | 广州视源电子科技股份有限公司 | Laser data identification method and device, robot and storage medium |
CN109459439A (en) * | 2018-12-06 | 2019-03-12 | 东南大学 | A kind of Tunnel Lining Cracks detection method based on mobile three-dimensional laser scanning technique |
CN110763148A (en) * | 2019-11-01 | 2020-02-07 | 中交三航局第三工程有限公司 | Automatic extraction method for multi-station three-dimensional laser point cloud target ball data |
CN112536643A (en) * | 2019-09-23 | 2021-03-23 | 富鼎电子科技(嘉善)有限公司 | Machine health monitoring method and device and computer readable storage medium |
CN113219439A (en) * | 2021-04-08 | 2021-08-06 | 广西综合交通大数据研究院 | Target main point cloud extraction method, device, equipment and computer storage medium |
CN113295142A (en) * | 2021-05-14 | 2021-08-24 | 上海大学 | Terrain scanning analysis method and device based on FARO scanner and point cloud |
US20210352323A1 (en) * | 2019-02-06 | 2021-11-11 | Panasonic Intellectual Property Xorporation of America | Three-dimensional data encoding method, three-dimensional data decoding method, three-dimensional data encoding device, and three-dimensional data decoding device |
CN114422712A (en) * | 2022-03-29 | 2022-04-29 | 深圳市海清视讯科技有限公司 | Sphere detection tracking method and device, electronic equipment and storage medium |
CN114862788A (en) * | 2022-04-29 | 2022-08-05 | 湖南联智科技股份有限公司 | Automatic identification method for plane target coordinates of three-dimensional laser scanning |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102944174A (en) * | 2012-11-28 | 2013-02-27 | 北京矿冶研究总院 | Point cloud data processing method and system |
CN103646156A (en) * | 2013-12-30 | 2014-03-19 | 北京建筑大学 | Ball target detection-based automatic registration method for laser point cloud data |
CN104019765A (en) * | 2014-06-25 | 2014-09-03 | 山东理工大学 | Multi-site point cloud integral orientation method based on laser beam process block adjustment |
CN104599272A (en) * | 2015-01-22 | 2015-05-06 | 中国测绘科学研究院 | Movable target sphere oriented onboard LiDAR point cloud and image united rectification method |
-
2015
- 2015-11-13 CN CN201510780431.9A patent/CN105447855B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102944174A (en) * | 2012-11-28 | 2013-02-27 | 北京矿冶研究总院 | Point cloud data processing method and system |
CN103646156A (en) * | 2013-12-30 | 2014-03-19 | 北京建筑大学 | Ball target detection-based automatic registration method for laser point cloud data |
CN104019765A (en) * | 2014-06-25 | 2014-09-03 | 山东理工大学 | Multi-site point cloud integral orientation method based on laser beam process block adjustment |
CN104599272A (en) * | 2015-01-22 | 2015-05-06 | 中国测绘科学研究院 | Movable target sphere oriented onboard LiDAR point cloud and image united rectification method |
Non-Patent Citations (3)
Title |
---|
MAREK FREANASZEK: "Fast automatic registration of range images from 3D imaging systems using sphere targets", 《AUTOMATION IN CONSTRUCTION》 * |
张东: "点云数据中球面点的自动提取", 《测绘》 * |
李嘉 等: "复杂场景三维点云中未知球形目标的自动识别方法", 《计算机辅助设计与图形学学报》 * |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107093210A (en) * | 2017-04-20 | 2017-08-25 | 北京图森未来科技有限公司 | A kind of laser point cloud mask method and device |
US11455772B2 (en) | 2017-04-20 | 2022-09-27 | Beijing Tusen Zhitu Technology Co., Ltd. | Method and device of labeling laser point cloud |
CN108710367B (en) * | 2018-05-23 | 2022-02-11 | 广州视源电子科技股份有限公司 | Laser data identification method and device, robot and storage medium |
CN108710367A (en) * | 2018-05-23 | 2018-10-26 | 广州视源电子科技股份有限公司 | Laser data identification method and device, robot and storage medium |
CN109459439A (en) * | 2018-12-06 | 2019-03-12 | 东南大学 | A kind of Tunnel Lining Cracks detection method based on mobile three-dimensional laser scanning technique |
US20210352323A1 (en) * | 2019-02-06 | 2021-11-11 | Panasonic Intellectual Property Xorporation of America | Three-dimensional data encoding method, three-dimensional data decoding method, three-dimensional data encoding device, and three-dimensional data decoding device |
US11902577B2 (en) * | 2019-02-06 | 2024-02-13 | Panasonic Intellectual Property Corporation Of America | Three-dimensional data encoding method, three-dimensional data decoding method, three-dimensional data encoding device, and three-dimensional data decoding device |
CN112536643A (en) * | 2019-09-23 | 2021-03-23 | 富鼎电子科技(嘉善)有限公司 | Machine health monitoring method and device and computer readable storage medium |
CN112536643B (en) * | 2019-09-23 | 2023-01-24 | 富鼎电子科技(嘉善)有限公司 | Machine health monitoring method and device and computer readable storage medium |
CN110763148A (en) * | 2019-11-01 | 2020-02-07 | 中交三航局第三工程有限公司 | Automatic extraction method for multi-station three-dimensional laser point cloud target ball data |
CN113219439A (en) * | 2021-04-08 | 2021-08-06 | 广西综合交通大数据研究院 | Target main point cloud extraction method, device, equipment and computer storage medium |
CN113219439B (en) * | 2021-04-08 | 2023-12-26 | 广西综合交通大数据研究院 | Target main point cloud extraction method, device, equipment and computer storage medium |
CN113295142A (en) * | 2021-05-14 | 2021-08-24 | 上海大学 | Terrain scanning analysis method and device based on FARO scanner and point cloud |
CN114422712B (en) * | 2022-03-29 | 2022-06-24 | 深圳市海清视讯科技有限公司 | Sphere detection tracking method and device, electronic equipment and storage medium |
CN114422712A (en) * | 2022-03-29 | 2022-04-29 | 深圳市海清视讯科技有限公司 | Sphere detection tracking method and device, electronic equipment and storage medium |
CN114862788A (en) * | 2022-04-29 | 2022-08-05 | 湖南联智科技股份有限公司 | Automatic identification method for plane target coordinates of three-dimensional laser scanning |
CN114862788B (en) * | 2022-04-29 | 2024-05-24 | 湖南联智科技股份有限公司 | Automatic identification method for plane target coordinates of three-dimensional laser scanning |
Also Published As
Publication number | Publication date |
---|---|
CN105447855B (en) | 2018-04-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105447855A (en) | Terrestrial 3D laser scanning point cloud spherical target automatic identification method | |
KR102125959B1 (en) | Method and apparatus for determining a matching relationship between point cloud data | |
CN109509256B (en) | Automatic measurement and 3D model generation method for building structure based on laser radar | |
TWI394087B (en) | Method and apparatus for tracking target object | |
US9245345B2 (en) | Device for generating three dimensional feature data, method for generating three-dimensional feature data, and recording medium on which program for generating three-dimensional feature data is recorded | |
CN109283538A (en) | A kind of naval target size detection method of view-based access control model and laser sensor data fusion | |
CN116148808B (en) | Automatic driving laser repositioning method and system based on point cloud descriptor | |
CN104299260A (en) | Contact network three-dimensional reconstruction method based on SIFT and LBP point cloud registration | |
CN108387885A (en) | Aircraft wake characteristic parameter inversion method under clear sky condition based on laser radar detection | |
CN112305559A (en) | Power transmission line distance measuring method, device and system based on ground fixed-point laser radar scanning and electronic equipment | |
CN103969656A (en) | Building modeling method and device based on airborne laser radar | |
CN103247045A (en) | Method of obtaining artificial scene main directions and image edges from multiple views | |
CN112068153B (en) | Crown clearance rate estimation method based on foundation laser radar point cloud | |
CN111311650A (en) | Point cloud data registration method and device and storage medium | |
CN108389256A (en) | Two three-dimensional interactive unmanned plane electric force pole tower inspection householder methods | |
CN110136178B (en) | Three-dimensional laser point cloud registration method and device based on endpoint fitting | |
CN110163871A (en) | A kind of ground dividing method of multi-line laser radar | |
CN108692656B (en) | Laser scanning data acquisition method and device | |
CN103455815A (en) | Self-adaptive license plate character segmentation method in complex scene | |
Wang et al. | Autonomous landing of multi-rotors UAV with monocular gimbaled camera on moving vehicle | |
CN111028345B (en) | Automatic identification and butt joint method for circular pipeline in harbor scene | |
Ma et al. | An intelligent object detection and measurement system based on trinocular vision | |
CN114494385A (en) | Visual early warning method for water delivery tunnel diseases | |
CN109031235A (en) | The method of quick obtaining radar baseis reflectivity three-dimensional isopleth data | |
CN114782357A (en) | Self-adaptive segmentation system and method for transformer substation scene |
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 |