CN117557457A - Method and device for filtering trailing points of point cloud - Google Patents
Method and device for filtering trailing points of point cloud Download PDFInfo
- Publication number
- CN117557457A CN117557457A CN202311505308.7A CN202311505308A CN117557457A CN 117557457 A CN117557457 A CN 117557457A CN 202311505308 A CN202311505308 A CN 202311505308A CN 117557457 A CN117557457 A CN 117557457A
- Authority
- CN
- China
- Prior art keywords
- point
- point cloud
- tailing
- points
- identified
- 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
- 238000001914 filtration Methods 0.000 title claims abstract description 32
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 238000004891 communication Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 238000003708 edge detection Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 2
- 238000005457 optimization Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration by the use of local operators
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/86—Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/89—Lidar systems specially adapted for specific applications for mapping or imaging
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- 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
- G06T2207/10024—Color image
-
- 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
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30204—Marker
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Electromagnetism (AREA)
- Artificial Intelligence (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a method and a device for filtering tailing points of point clouds, which relate to the technical field of tailing points of the point clouds, and comprise the following steps: s1: acquiring edge information in a three-dimensional space based on the color picture; s2: projecting the edge information into the point cloud, and identifying the point to be identified; s3: and judging whether the point to be identified is a tailing point according to the information of the auxiliary point, and deleting the tailing point. According to the method, the tailing point to be identified is marked through the colored edge information, the tailing point is identified through the normal line of the point cloud and the vector included angle from the origin point to the point to be identified, the interference object is removed based on the semantic information, the calculated amount is reduced, the robustness is improved, the tailing point is identified through the colored semantic information, and the influence of the radar rotation direction is avoided.
Description
Technical Field
The invention relates to the technical field of tailing point filtering of point clouds, in particular to a method and a device for filtering tailing points of point clouds.
Background
In the prior art, tailing points of the point cloud are mainly filtered through original frame data scanned by a laser radar, for example, the point cloud judged as the tailing point is filtered out according to the trend change of reflection intensity of one or more adjacent points of the single-line point cloud or the relative distance difference value of one or more adjacent points by using a certain threshold value. Because the rotation direction of the laser radar is limited by a physical structure, only the tailing phenomenon of an included angle with the rotation axis of the laser radar within a certain threshold can be removed, and the tailing phenomenon perpendicular to the rotation axis direction of the laser radar cannot be well removed.
Therefore, we provide a method and apparatus for filtering the tailing point of the point cloud to solve the above problems.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a method and a device for filtering the tailing points of point clouds, which fully utilize the original data scanned by a single-line or multi-line laser radar to generate dense point clouds, combine color image information, and can well judge the tailing points of the point clouds and filter.
In order to achieve the above object, the method for filtering the tailing point of the point cloud adopted by the invention comprises the following steps:
s1: based on the color picture, the edge information in the three-dimensional space is acquired, and the specific steps are as follows:
the color picture is a color panorama, and image enhancement processing is carried out on the color panorama;
converting the color panorama into a gray scale image;
denoising the gray image by using Gaussian filtering to form an edge image;
applying an edge detection algorithm on the generated edge image to extract edge information in the edge image;
the interference edges are taken out, the field Jing Yuyi is segmented through training the neural network, the edge information in the same object is removed, the operand of a subsequent algorithm is reduced, and the robustness of the algorithm is improved;
in the pixels of the color panorama, marking edge information, wherein a pixel set P= { Xi, yi } containing the edge information, wherein the set P refers to a set of all pixel points containing the edge information, xi refers to an x-axis coordinate of an ith point on the color panorama, and Yi refers to a y-axis coordinate of the ith point on the color panorama;
s2: projecting edge information into a point cloud, and identifying points to be identified at the positions, wherein the specific steps are as follows:
mapping zenith angle theta and azimuth angle on corresponding spherical surface according to length and width of the color panoramaThe specific calculation formula is as follows:
where HX is the horizontal pixel value of the color panorama, HY is the vertical pixel value of the color panorama,is the azimuth angle of the ith point, θi is the zenith angle of the ith point;
converting the point of the edge information into coordinates on a unit sphere, wherein the coordinates of the sphere center are (0, 0), and converting the coordinates into a Cartesian coordinate system;
the point cloud is projected onto the unit sphere, and the specific steps are as follows:
the spherical center coordinates are (0, 0), the spherical radius is 1, and the projection coordinates of any point Pci on the spherical surface are determined;
identifying edge points in a three-dimensional point cloud of the color panorama and marking the edge points as points to be identified, wherein the specific method comprises the following steps of: searching a pixel set P= { Xi, yi } neighborhood point of the edge information on a three-dimensional unit sphere, setting the radius to be 0.008 radian, searching a near point with a specified radius in the unit sphere coordinates of the point cloud projection, and marking the near point as a point set V to be identified in the point cloud;
s3: judging whether the point to be identified is a tailing point according to the information of the auxiliary point, and deleting the tailing point, wherein the specific steps are as follows:
calculating normal directions of all points in the point set V to be identified;
specific point c (Xj, yj, zj) to be identified, wherein Xj, yj, zj are the coordinates of the point to be identified on the x-axis, the coordinates of the point to be identified on the y-axis and the coordinates of the point to be identified on the z-axis, and the normal thereof is calculated to beCalculating a vector of the point cloud origin of coordinates (0, 0) to the point to be identified (Xj, yj, zj)>
Calculating normalSum vector->And the included angle alpha, alpha angle is within a threshold value, the point to be identified is judged to be the tailing point, otherwise, the point is the normal point, and the tailing point is deleted from the original point cloud.
As a further optimization of the above scheme, in S1, the contrast, sharpness, and definition of the color panorama are enhanced.
As a further optimization of the above scheme, the specific method for converting the color panorama into the grayscale image in S1 is as follows: the RGB values for each pixel are weighted averaged to convert the RGB values to a single gray value, the weight taken being R: g: b= 0.2989:0.5870:0.1140.
as a further optimization of the above scheme, the edge detection algorithm in S1 adopts Canny.
As a further optimization of the above scheme, the azimuth angle in S2The value range is [ -pi, pi]The value range of zenith angle theta>
As a further optimization of the above solution, the cartesian coordinate system in S2:
as a further optimization of the above scheme, the projection coordinates of any point Pci on the sphere in S2 are:
the Pci, xci, yci, zci is a point cloud projection coordinate of an arbitrary point, an x-axis coordinate on the point cloud projection, a y-axis coordinate on the point cloud projection, and a z-axis coordinate on the point cloud projection, respectively.
As a further optimization of the scheme, the color panorama and the point cloud are acquired through a point cloud acquisition device, the point cloud acquisition device uses scanning equipment, the scanning equipment integrates a laser radar and a color camera, three-dimensional data of a physical space are acquired through the laser radar, and the point cloud is generated through processing in the later period; color information of the physical space is acquired through a color camera, and a color panorama is generated through processing in the later period.
The invention also discloses a device for filtering the trailing points of the point cloud, which comprises: the system comprises a memory, a processor and a computer program stored on the memory and running on the processor, wherein the processor realizes a method for filtering tailing points of point cloud when executing the computer program.
As a further optimization of the above scheme, the processor is also connected with a communication interface, and the communication interface is used for communication between the memory and the processor.
The method and the device for filtering the trailing points of the point cloud have the following beneficial effects:
according to the method and the device for filtering the tailing point of the point cloud, the tailing point to be identified is marked through the colored edge information, the tailing point is identified through the normal line of the point cloud and the vector included angle from the origin point to the point to be identified, the interference objects are removed based on semantic information, the calculated amount is reduced, the robustness is improved, the tailing point is identified through judgment of the colored semantic information, and the influence of the radar rotation direction is avoided.
Specific embodiments of the invention have been disclosed in detail below with reference to the following description and drawings, indicating the manner in which the principles of the invention may be employed, it being understood that the embodiments of the invention are not limited in scope but are capable of numerous variations, modifications and equivalents within the spirit and scope of the appended claims.
Drawings
FIG. 1 is a diagram of a method of filtering tailing points of a point cloud according to the present invention;
FIG. 2 is a color panorama co-ordinate of the present invention;
fig. 3 is a schematic structural diagram of an apparatus for filtering tailing points of a point cloud according to the present invention.
Detailed Description
The present invention will be further described in detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the detailed description and specific examples, while indicating the invention, are intended for purposes of illustration only and are not intended to limit the scope of the invention.
It should be noted that, when an element is referred to as being "disposed on," or having an intermediate element, it can be directly on the other element or intervening elements may be present, and when an element is referred to as being "connected to," or having an intermediate element, it may be directly connected to the other element or intervening elements may be present, and the term "fixedly connected" is used herein in a wide variety of manners and is not intended to be limiting, and the terms "vertical", "horizontal", "left", "right", and the like are used herein for illustrative purposes only and are not meant to be exclusive embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs, and the terms used herein in this description are for the purpose of describing particular embodiments only and are not intended to limit the invention to any and all combinations of one or more of the associated listed items;
referring to fig. 1-3 of the specification, the present invention provides a technical scheme: a method of filtering tailing points of a point cloud, comprising the steps of:
the method comprises the steps that a point cloud acquisition device is provided, a model of the point cloud acquisition device comprises scanning equipment, a laser radar and a color camera are integrated on the scanning equipment, three-dimensional data of a physical space are acquired through the laser radar, and the point cloud is generated through processing in the later period; color information of a physical space is acquired through a color camera, and a color panorama is processed and generated in the later period, so that the laser radar internal reference, the color camera internal reference and the laser radar external reference and the color camera external reference are calibrated.
In step S1, based on the color picture, edge information in the three-dimensional space is acquired, specifically as follows:
the color picture is a color panorama, and image enhancement processing is performed on the color panorama, for example, enhancement processing is performed on contrast, sharpness, and definition. The present invention is not limited to the specific image enhancement processing method used.
The color panorama is converted into a gray-scale image. The method is realized by weighted average of RGB (Red Green Bule Red, green and blue) values of each pixel. I.e. converting the RGB values into a single gray value. The weight that is preferably taken is R: g: b= 0.2989:0.5870:0.1140.
gaussian filtering is applied to the gray scale image to reduce noise, forming an edge image. Gaussian filtering helps smooth the image and reduces noise in edge detection.
And applying a traditional edge detection algorithm on the generated edge image, and extracting edge information in the edge image by adopting an algorithm such as Canny. The specific manner of edge detection is not limited in the present invention.
Interference edge removal. In a real scene, there are many edges (such as pictures on wall, curtains, etc.) in the same object. According to the invention, the field Jing Yuyi is segmented by training the neural network, and the edge information in the same object is removed to reduce the operand of a subsequent algorithm, so that the robustness of the algorithm is improved. The invention is not limited to the specific semantic segmentation neural network used.
As shown in fig. 2, in the pixels of the color panorama, edge information is marked; the pixel set p= { Xi, yi } containing the edge information, wherein the pixel set P containing the edge information refers to the set of all pixel points containing the edge information, xi refers to the x-axis coordinate of the ith point on the color panorama, and Yi refers to the y-axis coordinate of the ith point on the color panorama.
In step S2, the edge information is projected to the point cloud to identify the point to be identified, and the specific steps are as follows:
according to the length and width of the color panorama, the zenith angle theta and azimuth angle on the corresponding sphere can be mappedThe specific calculation formula is as follows:
where HX is the horizontal pixel value of the color panorama and HY is the vertical pixel value of the color panorama.Is the azimuth angle of the i-th point, and θi is the zenith angle of the i-th point.
Azimuth angleThe value range is [ -pi, pi]；
Zenith angle theta value range
Converting the point of the edge information into coordinates on a unit sphere, wherein the coordinates of the sphere center are (0, 0), and converting the coordinates into a Cartesian coordinate system:
the point cloud is projected onto the unit sphere, and the specific steps are as follows:
the spherical center coordinates are (0, 0), the spherical radius is 1, and the projection coordinates of any point Pci on the spherical surface are as follows:
the Pci, xci, yci, zci is a point cloud projection coordinate of an arbitrary point, an x-axis coordinate on the point cloud projection, a y-axis coordinate on the point cloud projection, and a z-axis coordinate on the point cloud projection, respectively.
Identifying edge points in the three-dimensional point cloud of the color panorama and marking the edge points as points to be identified, wherein the specific method comprises the following steps of:
searching the point of the neighborhood of the pixel set P= { Xi, yi } of the edge information on the three-dimensional unit sphere, wherein the radius can be set to be 0.008 radian; searching for a nearby point with a specified radius in unit spherical coordinates of the point cloud projection; and marked in the point cloud as a set of points V to be identified.
In step S3, it is determined whether the point to be identified is a tailing point, and the tailing point is deleted, and the specific steps are as follows:
calculating normal directions of all points in the point set V to be identified;
specific point c (Xj, yj, zj) to be identified, wherein Xj, yj, zj are the coordinates of the point to be identified on the x-axis, the coordinates of the point to be identified on the y-axis and the coordinates of the point to be identified on the z-axis, and the normal thereof is calculated to beCalculating a vector of the point cloud origin of coordinates (0, 0) to the point to be identified (Xj, yj, zj)>
Calculating normalSum vector->And the included angle alpha, alpha angle is within a threshold value, the point to be identified is judged to be the tailing point, otherwise, the point is the normal point, and the tailing point is deleted from the original point cloud.
The invention also discloses a device for filtering the trailing points of the point cloud, which comprises: a memory, a processor, and a computer program stored on the memory and running on the processor;
the processor executes the computer program to implement a method for filtering the tailing point of the point cloud provided in the above embodiment.
Meanwhile, the processor is also connected with a communication interface, and the communication interface is used for communication between the memory and the processor.
It should be understood that the invention is not limited to the preferred embodiments, but is intended to cover modifications, equivalents, or alternatives falling within the spirit and principles of the invention.
Claims (10)
1. A method of filtering tailing points of a point cloud, comprising the steps of:
s1: based on the color picture, the edge information in the three-dimensional space is acquired, and the specific steps are as follows:
the color picture is a color panorama, and image enhancement processing is carried out on the color panorama;
converting the color panorama into a gray scale image;
denoising the gray image by using Gaussian filtering to form an edge image;
applying an edge detection algorithm on the generated edge image to extract edge information in the edge image;
the interference edges are taken out, the field Jing Yuyi is segmented through training the neural network, the edge information in the same object is removed, the operand of a subsequent algorithm is reduced, and the robustness of the algorithm is improved;
in the pixels of the color panorama, marking edge information, wherein a pixel set P= { Xi, yi } containing the edge information, wherein the set P refers to a set of all pixel points containing the edge information, xi refers to an x-axis coordinate of an ith point on the color panorama, and Yi refers to a y-axis coordinate of the ith point on the color panorama;
s2: projecting edge information into a point cloud, and identifying points to be identified at the positions, wherein the specific steps are as follows:
mapping zenith angle theta and azimuth angle on corresponding spherical surface according to length and width of the color panoramaThe specific calculation formula is as follows:
where HX is the horizontal pixel value of the color panorama, HY is the vertical pixel value of the color panorama,is the azimuth angle of the ith point, θi is the zenith angle of the ith point;
converting the point of the edge information into coordinates on a unit sphere, wherein the coordinates of the sphere center are (0, 0), and converting the coordinates into a Cartesian coordinate system;
the point cloud is projected onto the unit sphere, and the specific steps are as follows:
the spherical center coordinates are (0, 0), the spherical radius is 1, and the projection coordinates of any point Pci on the spherical surface are determined;
identifying edge points in a three-dimensional point cloud of the color panorama and marking the edge points as points to be identified, wherein the specific method comprises the following steps of: searching a pixel set P= { Xi, yi } neighborhood point of the edge information on a three-dimensional unit sphere, setting the radius to be 0.008 radian, searching a near point with a specified radius in the unit sphere coordinates of the point cloud projection, and marking the near point as a point set V to be identified in the point cloud;
s3: judging whether the point to be identified is a tailing point according to the information of the auxiliary point, and deleting the tailing point, wherein the specific steps are as follows:
calculating normal directions of all points in the point set V to be identified;
specific point c (Xj, yj, zj) to be identified, wherein Xj, yj, zj are the coordinates of the point to be identified on the x-axis, the coordinates of the point to be identified on the y-axis and the coordinates of the point to be identified on the z-axis, and the normal thereof is calculated to beCalculating a vector of the point cloud origin of coordinates (0, 0) to the point to be identified (Xj, yj, zj)>
Calculating normalSum vector->And the included angle alpha, alpha angle is within a threshold value, the point to be identified is judged to be the tailing point, otherwise, the point is the normal point, and the tailing point is deleted from the original point cloud.
2. The method for filtering tailing points of a point cloud as claimed in claim 1, wherein: and in the step S1, the contrast, the sharpness and the definition of the color panorama are enhanced.
3. The method for filtering tailing points of a point cloud as claimed in claim 1, wherein: the specific method for converting the color panorama into the gray-scale image in the step S1 is as follows: the RGB values for each pixel are weighted averaged to convert the RGB values to a single gray value, the weight taken being R: g: b= 0.2989:0.5870:0.1140.
4. the method for filtering tailing points of a point cloud as claimed in claim 1, wherein: and the edge detection algorithm in the S1 adopts Canny.
5. The method for filtering tailing points of a point cloud as claimed in claim 1, wherein: the azimuth angle theta in the S2 takes a value range of [ -pi, pi]Zenith angleValue range zenith angle theta value range +.>
6. The method for filtering tailing points of a point cloud as claimed in claim 1, wherein: the cartesian coordinate system in S2:
7. the method for filtering tailing points of a point cloud as claimed in claim 1, wherein: the projection coordinates of any point Pci in the S2 on the spherical surface are as follows:
wherein Pci, xci, yci, zci is divided intoThe coordinate system is a point cloud projection coordinate of any point, an x-axis coordinate on the point cloud projection, a y-axis coordinate on the point cloud projection and a z-axis coordinate on the point cloud projection.
8. The method for filtering tailing points of a point cloud as claimed in claim 1, wherein: the color panorama and the point cloud are acquired by a point cloud acquisition device, the point cloud acquisition device uses scanning equipment, the scanning equipment integrates a laser radar and a color camera, three-dimensional data of a physical space are acquired by the laser radar, and the point cloud is generated by processing in the later period; color information of the physical space is acquired through a color camera, and a color panorama is generated through processing in the later period.
9. A device for filtering tailing points of a point cloud, which is characterized in that: comprising the following steps: memory, a processor and a computer program stored on the memory and running on the processor, the processor implementing the method of filtering tailing points of a point cloud according to any of claims 1 to 8 when the computer program is executed by the processor.
10. The apparatus for filtering tailing points of a point cloud as claimed in claim 9, wherein: the processor is also connected with a communication interface, and the communication interface is used for communication between the memory and the processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311505308.7A CN117557457A (en) | 2023-11-13 | 2023-11-13 | Method and device for filtering trailing points of point cloud |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311505308.7A CN117557457A (en) | 2023-11-13 | 2023-11-13 | Method and device for filtering trailing points of point cloud |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117557457A true CN117557457A (en) | 2024-02-13 |
Family
ID=89810325
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311505308.7A Pending CN117557457A (en) | 2023-11-13 | 2023-11-13 | Method and device for filtering trailing points of point cloud |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117557457A (en) |
-
2023
- 2023-11-13 CN CN202311505308.7A patent/CN117557457A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109785291B (en) | Lane line self-adaptive detection method | |
| CN107292965B (en) | Virtual and real shielding processing method based on depth image data stream | |
| CN111428748B (en) | HOG feature and SVM-based infrared image insulator identification detection method | |
| US8126268B2 (en) | Edge-guided morphological closing in segmentation of video sequences | |
| CN107844750A (en) | A kind of water surface panoramic picture target detection recognition methods | |
| CN110232389B (en) | Stereoscopic vision navigation method based on invariance of green crop feature extraction | |
| CN109086724B (en) | Accelerated human face detection method and storage medium | |
| CN111415363A (en) | Image edge identification method | |
| CN106952307B (en) | Method and system for positioning sphere in image | |
| CN108171674B (en) | Vision correction method for projector image with any visual angle | |
| CN110009615B (en) | Image corner detection method and detection device | |
| CN110674812B (en) | Civil license plate positioning and character segmentation method facing complex background | |
| CN109447036A (en) | A kind of segmentation of image digitization and recognition methods and system | |
| CN114241438B (en) | Traffic signal lamp rapid and accurate identification method based on priori information | |
| CN109635809B (en) | Super-pixel segmentation method for visual degradation image | |
| CN113313116A (en) | Vision-based accurate detection and positioning method for underwater artificial target | |
| CN116758423A (en) | Power transmission line foreign matter detection method based on white point rate method | |
| CN117557457A (en) | Method and device for filtering trailing points of point cloud | |
| CN114842335B (en) | Grooving target identification method and system for construction robot | |
| CN107330436B (en) | Scale criterion-based panoramic image SIFT optimization method | |
| CN110633705A (en) | Low-illumination imaging license plate recognition method and device | |
| CN113689365B (en) | Target tracking and positioning method based on Azure Kinect | |
| CN106339709A (en) | Real-time image extraction method | |
| CN114926332A (en) | Unmanned aerial vehicle panoramic image splicing method based on unmanned aerial vehicle mother vehicle | |
| Rui | Lane line detection technology based on machine vision |
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 |