CN114743008A - Single plant vegetation point cloud data segmentation method and device and computer equipment - Google Patents
Single plant vegetation point cloud data segmentation method and device and computer equipment Download PDFInfo
- Publication number
- CN114743008A CN114743008A CN202210645250.5A CN202210645250A CN114743008A CN 114743008 A CN114743008 A CN 114743008A CN 202210645250 A CN202210645250 A CN 202210645250A CN 114743008 A CN114743008 A CN 114743008A
- Authority
- CN
- China
- Prior art keywords
- point
- point cloud
- vegetation
- cloud data
- crown
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/251—Fusion techniques of input or preprocessed data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/259—Fusion by voting
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the technical field of point cloud data processing, and discloses a method, a device and computer equipment for segmenting single plant vegetation point cloud data, wherein the method comprises the steps of firstly determining vegetation crown points serving as local extreme points through vegetation point identification processing, interpolation processing and mathematical morphology, then extracting a trunk through the combination of overlook point cloud and side view point cloud by using a tensor voting method, correcting the local extreme points by using central points of the trunk as new extreme points to obtain corrected vegetation crown points, then carrying out crown growth processing on the corrected vegetation crown points according to growth limiting conditions predetermined based on the actual conditions of the data to obtain growth points for constructing crown boundaries, finally obtaining single plant crown outlines based on edge detection, extracting the coordinate affine transformation and the point cloud data, and finally segmenting to obtain the single plant vegetation point cloud data, thus, the accuracy of the segmentation result can be ensured.
Description
Technical Field
The invention belongs to the technical field of point cloud data processing, and particularly relates to a method and a device for segmenting single plant vegetation point cloud data and computer equipment.
Background
The detection and identification of single vegetation (such as single trees) are of great significance for application in forests, cities and other scenes. For example, on the basis of accurate individual tree identification, the accurate total amount of trees can be obtained, and parameters such as tree height, breast diameter, crown, volume and the like can be calculated, so that the accuracy of estimating forest biomass or tree age distribution can be improved. Therefore, how to obtain the point cloud data of the individual vegetation from the detection and segmentation of the point cloud data of the laser radar (LiDAR) (each point of the point cloud data comprises three-dimensional coordinate information, namely X, Y and Z, and sometimes comprises color information, reflection intensity information and/or echo frequency information and the like) has important application value in aspects of forest resource clearing, city planning and the like.
At present, the detection and segmentation of single plant vegetation point cloud data based on laser radar (LiDAR) point cloud data mainly have the following problems: (1) due to the complex tree shape, the extreme point is difficult to determine, and various segmentation problems are easy to occur during segmentation, for example, an under-segmentation problem caused by the sharing of the extreme point by two adjacent trees, an erroneous segmentation/over-segmentation problem caused by the irregular tree shape, and the like; (2) when the crown boundary identification is performed on the two-dimensional image, the segmentation result is not accurate enough due to the unclear crown boundary, for example, two adjacent trees are crossed seriously or a small tree is under a large tree.
Disclosure of Invention
The invention aims to solve the problem that the segmentation result is inaccurate in the existing detection and segmentation mode of single plant vegetation point cloud data based on laser radar point cloud data, and provides a single plant vegetation point cloud data segmentation method, a single plant vegetation point cloud data segmentation device and computer equipment.
In a first aspect, the invention provides a point cloud data segmentation method for single vegetation, which comprises the following steps:
inputting original point cloud data to be segmented into a vegetation point identification model which is based on a binary classification network and is trained, and outputting to obtain a vegetation point identification result, wherein the original point cloud data is multi-source point cloud data fused with top view point cloud and side view point cloud;
performing interpolation processing on the point cloud data of the vegetation points identified in the vegetation point identification result to obtain rasterized canopy height model CHM image data;
determining vegetation top crown points serving as local extreme points by applying mathematical morphology according to the CHM image data;
extracting a trunk by applying a tensor voting method according to the original point cloud data;
feeding back the central point of the trunk as a new extreme point to the CHM image data to correct the local extreme point to obtain a corrected vegetation top crown point;
performing crown growth processing on the corrected vegetation top crown point according to a growth limiting condition predetermined based on the actual data condition to obtain a growth point;
marking the same mark on the growing point and the corrected vegetation crown point, and writing the mark into new image data as a pixel value, wherein the mark is a numerical value number selected from a value range of the pixel value and used for marking the growing point and the corrected vegetation crown point, and the new image data and the CHM image data have the same grid;
carrying out edge detection processing on the new image data to obtain the outline of the single tree crown;
affine transforming the column number of the outline of the single plant crown into a real geographic coordinate to obtain a target segmentation space;
and extracting point cloud data in the target segmentation space from the original point cloud data to obtain point cloud data of the individual vegetation.
Based on the content of the invention, a new scheme capable of accurately detecting and segmenting single plant vegetation point cloud data from multi-source point cloud data is provided, namely after original point cloud data to be segmented and fused with top view point cloud and side view point cloud are prepared, vegetation top crown points used as local extreme points are determined through vegetation point identification processing, interpolation processing and mathematical morphology, then a trunk is obtained through tensor voting by combining the top view point cloud and the side view point cloud, the local extreme points are corrected by taking the central point of the trunk as a new extreme point, corrected vegetation top crown points are obtained, then crown growth processing is carried out on the corrected vegetation top crown points according to growth limiting conditions predetermined based on the actual condition of data, growth points used for constructing crown boundaries are obtained, and finally a single plant crown contour is obtained based on edge detection, through coordinate affine transformation and point cloud data extraction, single vegetation point cloud data are finally obtained through segmentation, so that the accuracy of segmentation results can be ensured, important application values in aspects of forest resource clearing, city planning and the like are improved, and practical application and popularization are facilitated.
In one possible design, the binary classification network employs a RandLA-Net network or a modified structure based on a RandLA-Net network.
In one possible design, applying mathematical morphology to determine vegetation canopy points for local extrema based on the CHM image data includes:
performing image noise removal processing on the CHM image data by adopting a median filtering method to obtain new CHM image data;
and determining vegetation crown points serving as local extreme points by applying mathematical morphology according to the new CHM image data.
In one possible design, applying mathematical morphology to determine vegetation canopy points for local extrema based on the CHM image data includes:
performing morphological corrosion operation processing on the CHM image data to obtain an image data corrosion result;
subtracting the image data corrosion result from the CHM image data to obtain an image data subtraction result;
determining the maximum value in a positive value area according to the image data subtraction result;
and determining the point corresponding to the maximum value as a vegetation crown point serving as a local extreme point.
In one possible design, a trunk is extracted by applying a tensor voting method according to the original point cloud data, and the method comprises the following steps:
traversing each of the original point clouds in the original point cloud data: for a certain original point cloud
Firstly, constructing a corresponding equation:
in the formula (I), wherein,
the number of the rods is expressed in terms of,
the representation is in the certain original point cloud
The total number of point clouds within a specified radius of the center,
a natural number is represented by a number of characters,
representing the certain original point cloud
And the second within the specified radius
Personal neighborhood point cloud
A feature vector in between and having
，
A tensor operator representing the effect of the rod tensor on the neighborhood point and having
Then solving the equation to obtain the rod tensor
And finally, if the maximum characteristic value in the at least one characteristic value is judged to be larger than a preset characteristic threshold value, determining the certain original point cloud
The characteristic points of the trunk are taken;
and extracting all trunk characteristic points in the original point cloud data to obtain a trunk.
In one possible design, the growth limitation includes a tree height limitation, a growth range limitation and/or a neighboring tree competition point limitation, wherein the tree height limitation includes a minimum value of the tree height H of the seed point being 1.5 m, the growth range limitation includes a maximum distance R between the obtained growth point and the seed point being 3 m, and the neighboring tree competition point limitation includes a growth point competing with the neighboring tree by a factor of 0.7 higher than the tree height H of the seed point.
In one possible design, the original point cloud data is multi-source point cloud data obtained by combining, registering and fusing vehicle-mounted laser radar point cloud data, airborne laser radar point cloud data and ground station laser radar point cloud data, the interpolation processing adopts a triangulation network interpolation method, and the edge detection processing adopts an openCV edge detection function.
In a second aspect, the invention provides a point cloud data segmentation device for single vegetation, which comprises a vegetation point identification unit, an interpolation processing unit, an extreme point determination unit, a trunk extraction unit, an extreme point correction unit, a crown growth unit, a mark processing unit, an edge detection unit, an affine transformation unit and a data extraction unit;
the vegetation point identification unit is used for inputting original point cloud data to be segmented into a vegetation point identification model which is based on a binary classification network and is trained, and outputting to obtain a vegetation point identification result, wherein the original point cloud data is multi-source point cloud data fused with top view point cloud and side view point cloud;
the interpolation processing unit is in communication connection with the vegetation point identification unit and is used for interpolating the point cloud data of the identified vegetation points in the vegetation point identification result into rasterized canopy height model CHM image data;
the extreme point determining unit is in communication connection with the interpolation processing unit and is used for determining vegetation top crown points serving as local extreme points by applying mathematical morphology according to the CHM image data;
the trunk extraction unit is used for extracting a trunk by applying a tensor voting method according to the original point cloud data;
the extreme point correcting unit is respectively in communication connection with the extreme point determining unit and the trunk extracting unit, and is used for feeding back the central point of the trunk serving as a new extreme point to the CHM image data to correct the local extreme point to obtain a corrected vegetation crown point;
the crown growing unit is in communication connection with the extreme point correcting unit and is used for performing crown growing processing on the corrected vegetation top crown point according to a growth limiting condition predetermined based on the actual data situation to obtain a growing point;
the mark processing unit is in communication connection with the crown growing unit, and is configured to mark the same mark on the growing point and the corrected vegetation crown point, and write the mark into new image data as a pixel value, where the mark is a numerical number selected from a value range of the pixel value and used for marking the growing point and the corrected vegetation crown point, and the new image data has the same grid as the CHM image data;
the edge detection unit is in communication connection with the mark processing unit and is used for performing edge detection processing on the new image data to obtain the outline of the single tree crown;
the affine transformation unit is in communication connection with the edge detection unit and is used for affine transforming the row number and the column number of the outline of the single tree crown into real geographic coordinates to obtain a target segmentation space;
the data extraction unit is in communication connection with the affine transformation unit and is used for extracting point cloud data located in the target segmentation space from the original point cloud data to obtain single plant vegetation point cloud data.
In a third aspect, the present invention provides a computer device, comprising a memory, a processor and a transceiver, which are sequentially connected in communication, wherein the memory is used for storing a computer program, the transceiver is used for sending and receiving messages, and the processor is used for reading the computer program and executing the point cloud data segmentation method for single vegetation as described in the first aspect or any possible design in the first aspect.
In a fourth aspect, the present invention provides a computer readable storage medium having stored thereon instructions which, when run on a computer, perform a method of point cloud data segmentation of individual vegetation as described in the first aspect or any possible design thereof.
In a fifth aspect, the invention provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method of point cloud data segmentation of individual vegetation as described in the first aspect or any of the possible designs of the first aspect.
The invention has the beneficial effects that:
(1) the invention provides a new scheme capable of accurately detecting and segmenting single plant vegetation point cloud data from multi-source point cloud data, namely, after preparing original point cloud data to be segmented and fused with top view point cloud and side view point cloud, determining vegetation top crown points used as local extreme points through vegetation point identification processing, interpolation processing and mathematical morphology, then extracting a trunk through the combination of the top view point cloud and the side view point cloud by using a tensor voting method, correcting the local extreme points by taking the central point of the trunk as a new extreme point to obtain corrected vegetation top crown points, then performing crown growth processing on the corrected vegetation top crown points according to growth limiting conditions predetermined based on the actual conditions of data to obtain growth points used for constructing crown boundaries, and finally obtaining a single plant crown contour based on edge detection, through coordinate affine transformation and point cloud data extraction, single vegetation point cloud data are finally obtained through segmentation, so that the accuracy of segmentation results can be ensured, important application values in aspects of forest resource clearing, city planning and the like are improved, and practical application and popularization are facilitated.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow diagram of a point cloud data segmentation method for single plant vegetation provided by the invention.
Fig. 2 is a schematic structural diagram of the point cloud data segmentation device for single plant vegetation provided by the invention.
Fig. 3 is a schematic structural diagram of a computer device provided by the present invention.
Detailed Description
The invention is further described with reference to the following figures and specific embodiments. It should be noted that the description of the embodiments is provided to help understanding of the present invention, but the present invention is not limited thereto. Specific structural and functional details disclosed herein are merely representative of exemplary embodiments of the invention. This invention may, however, be embodied in many alternate forms and should not be construed as limited to the embodiments set forth herein.
It will be understood that, although the terms first, second, etc. may be used herein to describe various objects, these objects should not be limited by these terms. These terms are only used to distinguish one object from another. For example, a first object may be referred to as a second object, and similarly, a second object may be referred to as a first object, without departing from the scope of example embodiments of the present invention.
It should be understood that, for the term "and/or" as may appear herein, it is merely an associative relationship describing an associated object, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, B exists alone or A and B exist at the same time; for the term "/and" as may appear herein, which describes another associative object relationship, it means that two relationships may exist, e.g., a/and B, may mean: a exists singly or A and B exist simultaneously; in addition, for the character "/" that may appear herein, it generally means that the former and latter associated objects are in an "or" relationship.
As shown in fig. 1, the segmentation method for point cloud data of individual vegetation according to the first aspect of the present embodiment can be, but is not limited to, executed by a Computer device with certain computing resources, for example, an electronic device such as a platform server, a Personal Computer (PC, which refers to a multipurpose Computer with a size, price and performance suitable for Personal use, a desktop Computer, a notebook Computer, a small notebook Computer, a tablet Computer, an ultrabook, and the like all belong to a Personal Computer), a smart phone, a Personal Digital Assistant (PDA), or a wearable device. As shown in fig. 1, the method for segmenting point cloud data of individual vegetation may include, but is not limited to, the following steps S1 to S10.
S1, inputting original point cloud data to be segmented into a vegetation point identification model which is based on a binary classification network and is trained, and outputting to obtain a vegetation point identification result, wherein the original point cloud data is multi-source point cloud data fused with an overlook point cloud and a side view point cloud.
In step S1, in order to ensure that the original point cloud data has a top view point cloud and a side view point cloud, the original point cloud data is preferably multi-source point cloud data obtained by combining, registering and fusing vehicle-mounted lidar point cloud data, and ground station lidar point cloud data. Meanwhile, the binary classification network can preferably adopt a RandLA-Net network or an improved structure based on the RandLA-Net network, and the RandLA-Net network is an existing network structure capable of carrying out large-scale point cloud semantic segmentation, and can take the whole point cloud as input without preprocessing and post-processing operations such as splitting or merging and the like, so that the vegetation point identification model capable of identifying vegetation points or non-vegetation points based on input point cloud data can be obtained through conventional training. In addition, the input form of the raw point cloud data may be, but is not limited to, a text document format containing XYZ coordinate information and RGB color information.
And S2, interpolating the point cloud data of the vegetation points identified in the vegetation point identification result to obtain rasterized canopy height model CHM image data.
In step S2, the Canopy Height Model (CHM) is a very practical Model that can be obtained by the laser radar in the forest area, and is an expression of the Height of the forest Canopy on the ground, which reflects the Height change of the forest Canopy in the vertical direction and the distribution state in the horizontal direction, and the CHM can extract important forest vegetation parameters (such as single tree parameters, stand parameters, stock amount, biomass, etc.) in various forestry surveys. Specifically, the interpolation processing may be performed by using a triangulation method, or may be performed by using a B-Spline interpolation method (B-Spline), an ordinary kriging interpolation method (OK), an inverse distance weighted interpolation method (IDW), and the like, which are all existing methods, and may obtain the rasterized CHM image data by changing the interpolation conventionally.
And S3, determining a vegetation crown point serving as a local extreme point by applying mathematical morphology according to the CHM image data.
In the step S3, the Mathematical Morphology (Mathematical Morphology) is an image analysis subject based on lattice theory and topology, and is a basic theory of Mathematical Morphology image processing; the basic operation comprises the following steps: erosion and expansion, opening and closing operations, skeleton extraction, limit erosion, hit-miss transformation, morphological gradient, Top-hat transformation, particle analysis, watershed transformation and the like. Since each pixel point in the CHM image data represents the true height of a vegetation point, the vegetation crown point can be regarded as a local extreme point of the image, and the determination is performed by using a mathematical morphology method, that is, specifically, the vegetation crown point used as the local extreme point is determined by using the mathematical morphology according to the CHM image data, including but not limited to the following steps S31 to S34: s31, performing morphological corrosion operation processing on the CHM image data to obtain an image data corrosion result; s32, subtracting the image data corrosion result from the CHM image data to obtain an image data subtraction result; s33, determining the maximum value in a positive value area according to the subtraction result of the image data; and S34, determining the point corresponding to the maximum value as a vegetation top crown point serving as a local extreme point. In the above step S31, since the erosion operation is to convolve the image (or a small region of the image) with the kernel (the kernel size can be set to 5 × 5 square), so that the smooth terrain surface is not affected, and the salient parts are cut off due to erosion, the above subtraction process can retain the salient vegetation crown parts (i.e., positive value regions), and the point corresponding to the maximum value in the positive value region can be determined as the vegetation crown point used as the local extreme point. In addition, in order to remove the influence noise in advance, it is preferable to determine the vegetation crown point as the local extreme point by applying mathematical morphology according to the CHM image data, and the method further includes, but is not limited to: firstly, performing image noise removal processing on the CHM image data by adopting a median filtering method to obtain new CHM image data; and then determining vegetation crown points serving as local extreme points by applying mathematical morphology according to the new CHM image data.
And S4, extracting the trunk by using a tensor voting method according to the original point cloud data.
In step S4, the tensor voting method is a method for extracting image features, and is a method for removing noise and highlighting edges by using the characteristic of strong tensor robustness, extracting features of points, lines, and surfaces in an image, eliminating the significance of isolated points in the image, highlighting the extracted lines and surface features, and reconstructing the image. Because the original point cloud data has the characteristics of multi-source data, the trunk can be obtained by combining the overlook point cloud and the side view point cloud and using a tensor voting method, namely specifically, the trunk is obtained by using the tensor voting method according to the original point cloud data, and the method comprises but is not limited to the following steps of S41-S42: s41, traversing each original point cloud in the original point cloud data: for a certain original point cloud
Firstly, constructing a corresponding equation:
in the formula (I), wherein,
the number of the rods is expressed in terms of,
the representation is in the certain original point cloud
The total number of point clouds within a specified radius of the center,
a natural number is represented by a number of characters,
representing the certain original point cloud
And the second within the specified radius
Personal neighborhood point cloud
A feature vector in between and having
(herein, the
Representing the point cloud from the certain original point
To the second
Personal neighborhood point cloud
The directed line segment of (a),
a tensor operator representing the effect of the rod tensor on the neighborhood point and having
Then solving the equation to obtain the rod tensor
And finally, if the maximum characteristic value in the at least one characteristic value is judged to be larger than a preset characteristic threshold value, determining the certain original point cloud
The characteristic points of the trunk are taken; s42, extracting all trunk characteristic points in the original point cloud data to obtain a treeAnd (5) drying. In the foregoing step S41, the characteristic threshold may be 0.9, for example.
And S5, feeding back the central point of the trunk serving as a new extreme point to the CHM image data to correct the local extreme point to obtain a corrected vegetation crown point.
In step S5, the correction process is performed in a conventional manner, for example, taking a middle point between the new extreme point and the corresponding local extreme point as the corrected vegetation crown point.
And S6, carrying out crown growth processing on the corrected vegetation top crown point according to a growth limiting condition predetermined based on the actual data situation to obtain a growth point.
In step S6, the crown growing process is a process of extending the boundary of the crown around the vegetation top crown point, and thus the growing point is a new crown boundary point obtained after the crown growing process. Specifically, the growth limitation includes, but is not limited to, a tree height limitation including, but not limited to, a seed point (i.e., the corrected vegetation top crown point, which is considered herein as a seed point where the crown grows because the crown growth process is a process in which the boundary of the crown is extended around the vegetation top crown point) with a minimum value of the tree height H being 1.5 m, a growth range limitation including, but not limited to, a maximum distance R between the obtained growth point and the seed point being 3 m, and/or an adjacent tree competition point limitation including, but not limited to, a condition in which the growth point competing with the adjacent tree is higher than 0.7 times the tree height H of the seed point, and the like.
And S7, marking the same marks on the growing points and the corrected vegetation crown points, and writing the marks into new image data as pixel values, wherein the marks are numerical values selected from a value range of the pixel values and used for marking the growing points and the corrected vegetation crown points, and the new image data and the CHM image data have the same grids.
In the step S7, when the value range is [0,255], a value 128 may be taken to uniquely mark the growth point and the corrected vegetation crown point.
And S8, carrying out edge detection processing on the new image data to obtain the outline of the single tree crown.
In step S8, since the corrected vegetation crown point and the corresponding growth point are marked with the same mark, the single plant crown contour corresponding to the corrected vegetation crown point can be determined by edge detection processing. Specifically, the edge detection process may be, but is not limited to, using an openCV edge detection function.
And S9, affine transforming the row number and the column number of the outline of the single tree crown into real geographic coordinates to obtain a target segmentation space.
In step S9, since the new image data and the CHM image data have the same grid, the corresponding real geographic coordinates can be obtained by a conventional affine transformation method according to the row and column number of the outline of the individual tree crown, and the target segmentation space surrounded by all the real geographic coordinates can be obtained.
And S10, extracting point cloud data in the target partition space from the original point cloud data to obtain single plant vegetation point cloud data.
In the step S10, a position relationship between each original point cloud in the original point cloud data and a polygonal contour (i.e., a boundary of the target division space) is determined, and the point cloud data located in the polygonal contour is used as the point cloud data of the single plant vegetation obtained by the final division.
Thus, based on the segmentation method of the single plant vegetation point cloud data described in the foregoing steps S1 to S10, a new scheme is provided that can accurately detect and segment single plant vegetation point cloud data from multi-source point cloud data, that is, after original point cloud data to be segmented and fused with top view point cloud and side view point cloud are prepared, vegetation crown points used as local extreme points are determined through vegetation point identification processing, interpolation processing and mathematical morphology, then a trunk is extracted by using a tensor voting method by combining the top view point cloud and the side view point cloud, and the local extreme points are corrected by using a central point of the trunk as a new extreme point to obtain corrected vegetation crown points, and then crown growth processing is performed on the corrected vegetation crown points according to growth limiting conditions predetermined based on actual conditions of the data to obtain growth points used for constructing crown boundaries, finally, the single vegetation point cloud data is obtained by partitioning the single tree crown contour obtained based on edge detection through coordinate affine transformation and point cloud data extraction, so that the accuracy of the partitioning result can be ensured, the important application value in aspects of forest resource clearing, city planning and the like is improved, and the method is convenient for practical application and popularization.
As shown in fig. 2, a second aspect of the present embodiment provides a virtual device for implementing the point cloud data segmentation method for single vegetation according to the first aspect, which includes a vegetation point identification unit, an interpolation processing unit, an extreme point determination unit, a trunk extraction unit, an extreme point correction unit, a crown growth unit, a symbol processing unit, an edge detection unit, an affine transformation unit, and a data extraction unit;
the vegetation point identification unit is used for inputting original point cloud data to be segmented into a vegetation point identification model which is based on a binary classification network and is trained, and outputting to obtain a vegetation point identification result, wherein the original point cloud data is multi-source point cloud data fused with top view point cloud and side view point cloud;
the interpolation processing unit is in communication connection with the vegetation point identification unit and is used for interpolating point cloud data of vegetation points identified in the vegetation point identification result into rasterized Canopy Height Model (CHM) image data;
the extreme point determining unit is in communication connection with the interpolation processing unit and is used for determining vegetation crown points serving as local extreme points by applying mathematical morphology according to the CHM image data;
the trunk extraction unit is used for extracting a trunk by applying a tensor voting method according to the original point cloud data;
the extreme point correcting unit is respectively in communication connection with the extreme point determining unit and the trunk extracting unit, and is used for feeding back the central point of the trunk serving as a new extreme point to the CHM image data to correct the local extreme point to obtain a corrected vegetation crown point;
the crown growing unit is in communication connection with the extreme point correcting unit and is used for performing crown growing processing on the corrected vegetation top crown point according to a growth limiting condition predetermined based on the actual data situation to obtain a growing point;
the mark processing unit is in communication connection with the crown growing unit, and is configured to mark the same mark on the growing point and the corrected vegetation crown point, and write the mark into new image data as a pixel value, where the mark is a numerical number selected from a value range of the pixel value and used for marking the growing point and the corrected vegetation crown point, and the new image data has the same grid as the CHM image data;
the edge detection unit is in communication connection with the mark processing unit and is used for carrying out edge detection processing on the new image data to obtain the outline of the single tree crown;
the affine transformation unit is in communication connection with the edge detection unit and is used for affine transforming the row number and the column number of the outline of the single tree crown into real geographic coordinates to obtain a target segmentation space;
the data extraction unit is in communication connection with the affine transformation unit and is used for extracting point cloud data located in the target segmentation space from the original point cloud data to obtain single plant vegetation point cloud data.
For the working process, working details and technical effects of the apparatus provided in the second aspect of this embodiment, reference may be made to the point cloud data segmentation method for single plant vegetation described in the first aspect, which is not described herein again.
As shown in fig. 3, a third aspect of the present embodiment provides a computer device for performing the point cloud data segmentation method for individual vegetation according to the first aspect, which includes a memory, a processor and a transceiver, which are sequentially and communicatively connected, wherein the memory is used for storing a computer program, the transceiver is used for transceiving messages, and the processor is used for reading the computer program and performing the point cloud data segmentation method for individual vegetation according to the first aspect. For example, the Memory may include, but is not limited to, a Random-Access Memory (RAM), a Read-Only Memory (ROM), a Flash Memory (Flash Memory), a First-in First-out (FIFO), a First-in Last-out (FILO), and/or a First-in Last-out (FILO); the processor may be, but is not limited to, a microprocessor of the model number STM32F105 family. In addition, the computer device may also include, but is not limited to, a power module, a display screen, and other necessary components.
For the working process, working details and technical effects of the computer device provided in the third aspect of this embodiment, reference may be made to the point cloud data segmentation method for single plant vegetation in the first aspect, which is not described herein again.
A fourth aspect of the present embodiment provides a computer-readable storage medium storing instructions including the point cloud data segmentation method for individual vegetation according to the first aspect, that is, the computer-readable storage medium has instructions stored thereon, which when executed on a computer, perform the point cloud data segmentation method for individual vegetation according to the first aspect. The computer-readable storage medium refers to a carrier for storing data, and may include, but is not limited to, a computer-readable storage medium such as a floppy disk, an optical disk, a hard disk, a flash Memory, a flash disk and/or a Memory Stick (Memory Stick), and the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.
For the working process, working details and technical effects of the computer-readable storage medium provided in the fourth aspect of this embodiment, reference may be made to the point cloud data segmentation method for single plant vegetation, which is not described herein again.
A fifth aspect of the present embodiments provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method of point cloud data segmentation of individual vegetation as described in the first aspect. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable devices.
Finally, it should be noted that the present invention is not limited to the above alternative embodiments, and that any person can obtain other products in various forms in the light of the present invention. The above detailed description should not be taken as limiting the scope of the invention, which is defined in the claims, and which the description is intended to be interpreted accordingly.
Claims (10)
1. A single plant vegetation point cloud data segmentation method is characterized by comprising the following steps:
inputting original point cloud data to be segmented into a vegetation point identification model which is based on a binary classification network and is trained, and outputting to obtain a vegetation point identification result, wherein the original point cloud data is multi-source point cloud data fused with top view point cloud and side view point cloud;
performing interpolation processing on the point cloud data of the vegetation points identified in the vegetation point identification result to obtain rasterized canopy height model CHM image data;
determining vegetation top crown points serving as local extreme points by applying mathematical morphology according to the CHM image data;
extracting a trunk by applying a tensor voting method according to the original point cloud data;
feeding back the central point of the trunk as a new extreme point to the CHM image data to correct the local extreme point to obtain a corrected vegetation top crown point;
performing crown growth processing on the corrected vegetation top crown point according to a growth limiting condition predetermined based on the actual data condition to obtain a growth point;
marking the same mark on the growing point and the corrected vegetation crown point, and writing the mark into new image data as a pixel value, wherein the mark is a numerical value number selected from a value range of the pixel value and used for marking the growing point and the corrected vegetation crown point, and the new image data and the CHM image data have the same grid;
carrying out edge detection processing on the new image data to obtain the outline of the single tree crown;
affine transforming the row number and the column number of the outline of the single tree crown into real geographic coordinates to obtain a target segmentation space;
and extracting point cloud data in the target partition space from the original point cloud data to obtain point cloud data of single plant vegetation.
2. The method for segmenting point cloud data of individual vegetation according to claim 1, wherein the binary classification network adopts a RandLA-Net network or an improved structure based on the RandLA-Net network.
3. The method of segmenting point cloud data of individual vegetation according to claim 1, wherein the step of applying mathematical morphology to determine vegetation cap points as local extreme points from the CHM image data comprises:
performing image noise removal processing on the CHM image data by adopting a median filtering method to obtain new CHM image data;
and determining vegetation crown points serving as local extreme points by applying mathematical morphology according to the new CHM image data.
4. The method of segmenting point cloud data of individual vegetation according to claim 1, wherein the step of applying mathematical morphology to determine vegetation cap points as local extreme points from the CHM image data comprises:
performing morphological corrosion operation processing on the CHM image data to obtain an image data corrosion result;
subtracting the image data corrosion result from the CHM image data to obtain an image data subtraction result;
determining the maximum value in a positive value area according to the image data subtraction result;
and determining the point corresponding to the maximum value as a vegetation crown point serving as a local extreme point.
5. The point cloud data segmentation method for vegetation cover plants as claimed in claim 1, wherein the step of extracting a trunk by applying a tensor voting method according to the original point cloud data comprises the following steps:
traversing each of the original point clouds in the original point cloud data: for a certain original point cloud
Firstly, constructing a corresponding equation:
in the formula (I), wherein,
the tensor of the rod is expressed,
the representation is in the certain original point cloud
The total number of point clouds within a specified radius of the center,
a natural number is represented by a number of characters,
representing the certain original point cloud
And the second within the specified radius
Personal neighborhood point cloud
A feature vector in between and having
，
A tensor operator representing the effect of the rod tensor on the neighborhood point and having
Then solving the equation to obtain the rod tensor
And finally, if the maximum characteristic value in the at least one characteristic value is judged to be larger than a preset characteristic threshold value, determining the certain original point cloud
The characteristic points of the trunk are taken;
and extracting all trunk characteristic points in the original point cloud data to obtain a trunk.
6. The point cloud data partitioning method for single vegetation as set forth in claim 1, wherein the growth restriction includes a tree height restriction, a growth range restriction and/or an adjacent tree competition point restriction, wherein the tree height restriction includes a minimum value of the tree height H of the seed points being 1.5 m, the growth range restriction includes a maximum distance R between the obtained growth point and the seed point being 3 m, and the adjacent tree competition point restriction includes a growth point competing with the adjacent tree being 0.7 times higher than the tree height H of the seed point.
7. The method for segmenting the point cloud data of the individual vegetation according to claim 1, wherein the original point cloud data is multi-source point cloud data obtained by combining, registering and fusing vehicle-mounted laser radar point cloud data, vehicle-mounted laser radar point cloud data and ground station laser radar point cloud data, the interpolation processing adopts a triangulation network interpolation method, and the edge detection processing adopts an openCV edge detection function.
8. A single plant vegetation point cloud data segmentation device is characterized by comprising a vegetation point identification unit, an interpolation processing unit, an extreme point determination unit, a trunk extraction unit, an extreme point correction unit, a crown growth unit, a mark processing unit, an edge detection unit, an affine transformation unit and a data extraction unit;
the vegetation point identification unit is used for inputting original point cloud data to be segmented into a vegetation point identification model which is based on a binary classification network and is trained, and outputting to obtain a vegetation point identification result, wherein the original point cloud data is multi-source point cloud data fused with top view point cloud and side view point cloud;
the interpolation processing unit is in communication connection with the vegetation point identification unit and is used for interpolating the point cloud data of the identified vegetation points in the vegetation point identification result into rasterized canopy height model CHM image data;
the extreme point determining unit is in communication connection with the interpolation processing unit and is used for determining vegetation crown points serving as local extreme points by applying mathematical morphology according to the CHM image data;
the trunk extraction unit is used for extracting a trunk by applying a tensor voting method according to the original point cloud data;
the extreme point correcting unit is respectively in communication connection with the extreme point determining unit and the trunk extracting unit, and is used for feeding back the central point of the trunk serving as a new extreme point to the CHM image data to correct the local extreme point to obtain a corrected vegetation crown point;
the crown growing unit is in communication connection with the extreme point correcting unit and is used for performing crown growing processing on the corrected vegetation top crown point according to a growth limiting condition predetermined based on the actual data situation to obtain a growing point;
the mark processing unit is in communication connection with the crown growing unit and is used for marking the same mark on the growing point and the corrected vegetation crown point and writing the mark into new image data as a pixel value, wherein the mark is a numerical value number which is selected from a value range of the pixel value and used for marking the growing point and the corrected vegetation crown point, and the new image data and the CHM image data have the same grid;
the edge detection unit is in communication connection with the mark processing unit and is used for carrying out edge detection processing on the new image data to obtain the outline of the single tree crown;
the affine transformation unit is in communication connection with the edge detection unit and is used for affine transforming the row number and the column number of the outline of the single tree crown into real geographic coordinates to obtain a target segmentation space;
the data extraction unit is in communication connection with the affine transformation unit and is used for extracting point cloud data located in the target segmentation space from the original point cloud data to obtain single plant vegetation point cloud data.
9. A computer device, comprising a memory, a processor and a transceiver which are sequentially connected in communication, wherein the memory is used for storing a computer program, the transceiver is used for transmitting and receiving messages, and the processor is used for reading the computer program and executing the individual vegetation point cloud data segmentation method according to any one of claims 1 to 7.
10. A computer-readable storage medium having instructions stored thereon, which when executed on a computer perform the method of point cloud data segmentation of individual vegetation as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210645250.5A CN114743008B (en) | 2022-06-09 | 2022-06-09 | Single plant vegetation point cloud data segmentation method and device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210645250.5A CN114743008B (en) | 2022-06-09 | 2022-06-09 | Single plant vegetation point cloud data segmentation method and device and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114743008A true CN114743008A (en) | 2022-07-12 |
| CN114743008B CN114743008B (en) | 2022-09-23 |
Family
ID=82287799
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210645250.5A Active CN114743008B (en) | 2022-06-09 | 2022-06-09 | Single plant vegetation point cloud data segmentation method and device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114743008B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116704333A (en) * | 2023-05-19 | 2023-09-05 | 中国电建集团江西省电力设计院有限公司 | Single tree detection method based on laser point cloud data |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102324102A (en) * | 2011-10-08 | 2012-01-18 | 北京航空航天大学 | Method for automatically filling structure information and texture information of hole area of image scene |
| US20120148162A1 (en) * | 2010-12-09 | 2012-06-14 | The Hong Kong University Of Science And Technology | Joint semantic segmentation of images and scan data |
| CN104599280A (en) * | 2015-02-02 | 2015-05-06 | 武汉大学 | Road crack intersection extraction method and system |
| CN106407898A (en) * | 2016-08-29 | 2017-02-15 | 中国林业科学研究院资源信息研究所 | Laser radar individual tree block identification method |
| CN106716450A (en) * | 2014-05-06 | 2017-05-24 | 河谷控股Ip有限责任公司 | Image-based feature detection using edge vectors |
| CN107274417A (en) * | 2017-07-05 | 2017-10-20 | 电子科技大学 | A kind of single wooden dividing method based on airborne laser point cloud aggregation |
| CN110223314A (en) * | 2019-06-06 | 2019-09-10 | 电子科技大学 | A kind of single wooden dividing method based on the distribution of tree crown three-dimensional point cloud |
| CN111462134A (en) * | 2020-03-31 | 2020-07-28 | 武汉大学 | Single-tree segmentation method and system for fusing high-resolution remote sensing image and laser radar point cloud |
| CN112347894A (en) * | 2020-11-02 | 2021-02-09 | 东华理工大学 | Single-plant vegetation extraction method based on transfer learning and Gaussian mixture model separation |
| CN112435344A (en) * | 2020-11-27 | 2021-03-02 | 广东电网有限责任公司肇庆供电局 | Point cloud data processing method and device and terminal equipment |
| AU2020104291A4 (en) * | 2020-12-23 | 2021-03-11 | Guilin University Of Technology | Singletree segmentation method based on chord angle discriminant clustering for layered LIDAR point cloud |
| CN112634149A (en) * | 2020-12-10 | 2021-04-09 | 浙江大学 | Point cloud denoising method based on graph convolution network |
| CN113591766A (en) * | 2021-08-09 | 2021-11-02 | 中国林业科学研究院资源信息研究所 | Multi-source remote sensing tree species identification method for unmanned aerial vehicle |
| CN113902779A (en) * | 2021-09-28 | 2022-01-07 | 燕山大学 | Point cloud registration method based on tensor voting method |
| CN114332172A (en) * | 2021-10-14 | 2022-04-12 | 中北大学 | Improved laser point cloud registration method based on covariance matrix |
-
2022
- 2022-06-09 CN CN202210645250.5A patent/CN114743008B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120148162A1 (en) * | 2010-12-09 | 2012-06-14 | The Hong Kong University Of Science And Technology | Joint semantic segmentation of images and scan data |
| CN102324102A (en) * | 2011-10-08 | 2012-01-18 | 北京航空航天大学 | Method for automatically filling structure information and texture information of hole area of image scene |
| CN106716450A (en) * | 2014-05-06 | 2017-05-24 | 河谷控股Ip有限责任公司 | Image-based feature detection using edge vectors |
| CN104599280A (en) * | 2015-02-02 | 2015-05-06 | 武汉大学 | Road crack intersection extraction method and system |
| CN106407898A (en) * | 2016-08-29 | 2017-02-15 | 中国林业科学研究院资源信息研究所 | Laser radar individual tree block identification method |
| CN107274417A (en) * | 2017-07-05 | 2017-10-20 | 电子科技大学 | A kind of single wooden dividing method based on airborne laser point cloud aggregation |
| CN110223314A (en) * | 2019-06-06 | 2019-09-10 | 电子科技大学 | A kind of single wooden dividing method based on the distribution of tree crown three-dimensional point cloud |
| CN111462134A (en) * | 2020-03-31 | 2020-07-28 | 武汉大学 | Single-tree segmentation method and system for fusing high-resolution remote sensing image and laser radar point cloud |
| CN112347894A (en) * | 2020-11-02 | 2021-02-09 | 东华理工大学 | Single-plant vegetation extraction method based on transfer learning and Gaussian mixture model separation |
| CN112435344A (en) * | 2020-11-27 | 2021-03-02 | 广东电网有限责任公司肇庆供电局 | Point cloud data processing method and device and terminal equipment |
| CN112634149A (en) * | 2020-12-10 | 2021-04-09 | 浙江大学 | Point cloud denoising method based on graph convolution network |
| AU2020104291A4 (en) * | 2020-12-23 | 2021-03-11 | Guilin University Of Technology | Singletree segmentation method based on chord angle discriminant clustering for layered LIDAR point cloud |
| CN113591766A (en) * | 2021-08-09 | 2021-11-02 | 中国林业科学研究院资源信息研究所 | Multi-source remote sensing tree species identification method for unmanned aerial vehicle |
| CN113902779A (en) * | 2021-09-28 | 2022-01-07 | 燕山大学 | Point cloud registration method based on tensor voting method |
| CN114332172A (en) * | 2021-10-14 | 2022-04-12 | 中北大学 | Improved laser point cloud registration method based on covariance matrix |
Non-Patent Citations (1)
| Title |
|---|
| RUI XIAO 等: "Efficient individual tree identification from multiple source point cloud", 《IOP CONFERENCE SERIES: EARTH AND ENVIRONMENTAL SCIENCE》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116704333A (en) * | 2023-05-19 | 2023-09-05 | 中国电建集团江西省电力设计院有限公司 | Single tree detection method based on laser point cloud data |
| CN116704333B (en) * | 2023-05-19 | 2024-03-12 | 中国电建集团江西省电力设计院有限公司 | Single tree detection method based on laser point cloud data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114743008B (en) | 2022-09-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wu et al. | Individual tree crown delineation using localized contour tree method and airborne LiDAR data in coniferous forests | |
| Ene et al. | Single tree detection in heterogeneous boreal forests using airborne laser scanning and area-based stem number estimates | |
| Liu et al. | Tree species classification of LiDAR data based on 3D deep learning | |
| CN112990086B (en) | Remote sensing image building detection method and device and computer readable storage medium | |
| CN106709517B (en) | Mangrove forest identification method and system | |
| CN107909015A (en) | Hyperspectral image classification method based on convolutional neural networks and empty spectrum information fusion | |
| US9064151B2 (en) | Device and method for detecting plantation rows | |
| Lin et al. | A multi-level morphological active contour algorithm for delineating tree crowns in mountainous forest | |
| CN108376232A (en) | A kind of method and apparatus of automatic interpretation for remote sensing image | |
| CN116704333B (en) | Single tree detection method based on laser point cloud data | |
| CN112669333A (en) | Single tree information extraction method | |
| CN114743008B (en) | Single plant vegetation point cloud data segmentation method and device and computer equipment | |
| CN112990085A (en) | Method and device for detecting change of culture pond and computer readable storage medium | |
| Zheng et al. | Single shot multibox detector for urban plantation single tree detection and location with high-resolution remote sensing imagery | |
| CN111814715A (en) | Ground object classification method and device | |
| Sun et al. | Feasibility study on the estimation of the living vegetation volume of individual street trees using terrestrial laser scanning | |
| CN105701856B (en) | A kind of vegetation extracting method and system | |
| Kumar et al. | A two-stage algorithm for ground filtering of airborne laser scanning data | |
| CN113343819B (en) | Efficient unmanned airborne SAR image target segmentation method | |
| Mao et al. | City object detection from airborne Lidar data with OpenStreetMap‐tagged superpixels | |
| Yang et al. | Adaptive slope filtering for airborne Light Detection and Ranging data in urban areas based on region growing rule | |
| Mu et al. | Canopy lidar point cloud data k-means clustering watershed segmentation method | |
| Lu et al. | Automatic regionalized coastline extraction method based on high-resolution images | |
| Tang et al. | Accuracy test of point-based and object-based urban building feature classification and extraction applying airborne LiDAR data | |
| CN109934837B (en) | 3D plant leaf contour extraction method, device and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |