CN114581464A - Boundary detection method and device, electronic equipment and computer readable storage medium - Google Patents
Boundary detection method and device, electronic equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN114581464A CN114581464A CN202210216828.5A CN202210216828A CN114581464A CN 114581464 A CN114581464 A CN 114581464A CN 202210216828 A CN202210216828 A CN 202210216828A CN 114581464 A CN114581464 A CN 114581464A
- Authority
- CN
- China
- Prior art keywords
- boundary
- data
- point cloud
- plot
- land parcel
- 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
Images
Classifications
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/10—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Processing Or Creating Images (AREA)
Abstract
The embodiment of the invention provides a boundary detection method, a boundary detection device, electronic equipment and a computer readable storage medium, belonging to the technical field of data processing, wherein the method comprises the following steps: the method comprises the steps of obtaining original point cloud data of a region to be detected, screening the original point cloud data to obtain the point cloud data to be detected, extracting land parcel data after land parcel segmentation is conducted on the basis of the point cloud data to be detected by means of a preset segmentation algorithm, generating a land parcel comparison map according to the point cloud data to be detected and the land parcel data, auditing and correcting the land parcel data on the basis of the land parcel comparison map, and drawing a land parcel boundary of the region to be detected. By screening the original point cloud data and correcting the plot data by combining the plot comparison map, the drawing accuracy of the plot boundary is greatly improved.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a boundary detection method, an apparatus, an electronic device, and a computer-readable storage medium.
Background
The plot is one of cadastre units in land grading, the plot boundary data can describe and show plot elements of a real agricultural scene, and can also be applied to plant protection operations of agricultural robots, unmanned planes and the like, for example, an operation range is determined based on the plot boundary data, and an operation route is planned. Currently, a plot boundary drawing method is usually adopted to draw the plot boundary of each region to be measured. However, these methods tend to result in a lower accuracy of the mapped parcel boundary due to uncertainty in the parcel boundary.
Disclosure of Invention
In view of the above, the present invention provides a boundary detection method, an apparatus, an electronic device and a computer-readable storage medium, which can solve the problem of low accuracy of a mapped region boundary caused by uncertainty of the region boundary in the current region mapping method.
In order to achieve the above object, the embodiments of the present invention adopt the following technical solutions.
In a first aspect, an embodiment of the present invention provides a boundary detection method, which adopts the following technical solution.
A boundary detection method, comprising:
acquiring original point cloud data of a region to be detected;
screening the original point cloud data to obtain point cloud data to be detected;
based on the point cloud data to be detected, extracting land parcel data after performing land parcel segmentation by using a preset segmentation algorithm;
generating a plot comparison map according to the point cloud data to be detected and the plot data;
and based on the plot comparison graph, auditing and correcting the plot data, and drawing the plot boundary of the region to be detected.
Further, the segmentation algorithm comprises a region growing segmentation algorithm based on color and a point cloud segmentation algorithm based on region growing, and the step of extracting the land mass data after performing land mass segmentation by using a preset segmentation algorithm based on the point cloud data to be detected comprises the following steps:
based on the point cloud data to be detected, performing land parcel identification and segmentation by using the region growing and segmenting algorithm based on colors, and extracting first segmentation data;
and performing secondary land parcel segmentation by using the point cloud segmentation algorithm based on the region growing based on the first segmentation data, and extracting land parcel data.
Further, the plot contrast map comprises a two-dimensional orthophoto map and a three-dimensional scene map, the plot data comprises boundary data of each divided plot, and the three-dimensional scene map and the two-dimensional orthophoto map both comprise boundary data of the plots;
the step of auditing and correcting the plot data and drawing the plot boundary of the region to be detected based on the plot comparison graph comprises the following steps:
controlling the two-dimensional orthophoto map and the three-dimensional scene map in a linkage manner;
hiding data with the elevation exceeding a preset value from the earth surface in the three-dimensional scene graph to obtain a three-dimensional graph to be drawn, and taking the two-dimensional orthophoto map as the image map to be drawn;
amplifying the three-dimensional image to be drawn by a preset multiple, and drawing a plot boundary line on the three-dimensional image to be drawn and the image to be drawn by combining boundary data of the plot, wherein the plot boundary line comprises a plurality of boundary points;
judging whether each boundary point on the boundary line of the land block meets a preset rule or not, if not, displaying the image map to be drawn and the boundary point on the three-dimensional map to be drawn which does not meet the preset rule as an abnormal point;
and determining a target boundary point by combining the three-dimensional image to be drawn and the image to be drawn, and replacing the abnormal point with the target boundary point to finish the drawing of the plot boundary.
Further, the step of determining the target boundary point includes:
determining the three-dimensional image to be drawn and the area of the abnormal point in the image to be drawn according to the position of the abnormal point;
after the area where the abnormal point is located is enlarged to a preset resolution ratio, determining a boundary point between the plot where the abnormal point is located and an adjacent plot;
and taking the boundary point as a target boundary point.
Further, the land parcel comprises a plurality of categories, each category corresponds to a preset rule, the land parcel data further comprises the category of each land parcel, and the preset rule comprises a height difference threshold value;
the step of judging whether each boundary point on the land parcel boundary line accords with a preset rule comprises the following steps:
and calculating the elevation difference between adjacent boundary points on the boundary line of the land parcel, wherein if the elevation difference is greater than the elevation difference threshold value corresponding to the type of the land parcel, the adjacent boundary points do not accord with the preset rule.
Further, the step of screening the original point cloud data to obtain point cloud data to be detected includes:
filtering the original point cloud data by adopting a filtering method to obtain filtered point cloud data;
and eliminating data with the elevation exceeding a preset threshold value from the earth surface in the filtering point cloud data.
Further, the filtering method includes at least one of a statistical filtering method, a bilateral filtering method, a gaussian filtering method, and a radius filtering method.
In a second aspect, an embodiment of the present invention provides a boundary detection apparatus, which adopts the following technical solutions.
A boundary detection device comprises a preprocessing module, a segmentation module and a drawing module;
the preprocessing module is used for acquiring original point cloud data of a region to be detected and screening the original point cloud data to obtain point cloud data to be detected;
the dividing module is used for extracting land parcel data after performing land parcel division by using a preset dividing algorithm based on the point cloud data to be detected, wherein the land parcel data comprises land parcel number and land parcel boundary data;
the drawing module is used for generating a plot comparison graph according to the point cloud data to be detected and the plot data, auditing and correcting the plot data based on the plot comparison graph, and drawing the plot boundary of the region to be detected.
In a third aspect, an embodiment of the present invention provides an electronic device, which adopts the following technical solutions.
An electronic device comprising a processor and a memory, the memory storing machine executable instructions executable by the processor to implement the boundary detection method of the first aspect.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which adopts the following technical solutions.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the boundary detection method according to the first aspect.
Compared with the prior art, the embodiment of the invention has the following beneficial effects: the method comprises the steps of screening original point cloud data of an obtained region to be detected to obtain point cloud data to be detected, screening out interference data in the original point cloud data, then carrying out land parcel segmentation on the point cloud data to be detected by utilizing a segmentation algorithm, extracting land parcel data, generating a land parcel comparison map by combining the point cloud data to be detected, further correcting the land parcel data according to the land parcel comparison map to draw a land parcel boundary of the region to be detected, enabling the drawn land parcel boundary to be more accurate, and greatly improving the problem that the accuracy of the drawn land parcel boundary is lower due to the uncertainty of the land parcel boundary.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a block diagram illustrating a boundary detection system according to an embodiment of the present invention.
Fig. 2 is a block diagram of an electronic device according to an embodiment of the present invention.
Fig. 3 shows a schematic flowchart of a boundary detection method according to an embodiment of the present invention.
Fig. 4 shows a schematic flow chart of a part of the sub-steps of step S103 in fig. 3.
Fig. 5 shows a schematic flow chart of a part of the sub-steps of step S105 in fig. 3.
Fig. 6 shows a schematic flow chart of a part of the sub-steps of step S109 in fig. 3.
Fig. 7 shows a linkage diagram of a two-dimensional orthophoto map and a three-dimensional scene map.
Fig. 8 shows a schematic flow diagram of part of the sub-steps of step S109-4 in fig. 6.
Fig. 9 shows a schematic flow diagram of part of the sub-steps of step S109-6 in fig. 6.
Fig. 10 is a block diagram illustrating a boundary detection apparatus according to an embodiment of the present invention.
Icon: 100-a boundary detection system; 110-a collection device; 120-an electronic device; 130-a memory; 140-a processor; 150-a communication module; 160-boundary detection means; 170-a pre-processing module; 180-a segmentation module; 190-drawing module.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.
It is noted that relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The plot boundary data can be used for demonstrating and describing plot elements of a real operation scene, and can also be applied to plant protection operations of agricultural robots, unmanned aerial vehicles and the like. For example, intelligent machines such as agricultural robots and unmanned aerial vehicles determine a working range based on land boundary data, and plan a working route.
Currently, a plot boundary drawing method is generally adopted to draw the boundary of each plot in each region, so as to obtain the plot boundary and the plot condition. However, these methods tend to result in a lower accuracy of the mapped parcel boundary due to uncertainty in the parcel boundary.
Based on the above consideration, the embodiment of the invention provides a boundary detection scheme, which is used for drawing a parcel boundary by screening original point cloud data of a region to be detected, dividing the original point cloud data by using an algorithm, and performing auditing and correction on the parcel data obtained by division, so as to solve the problem that the parcel boundary drawn by the existing parcel boundary drawing method is low in accuracy.
Referring to fig. 1, a block diagram of a boundary detection system 100 according to an embodiment of the present invention is shown, and the boundary detection method according to the embodiment of the present invention is applied to the boundary detection system 100. The boundary detection system 100 includes an acquisition device 110 and an electronic device 120, and the acquisition device 110 and the electronic device 120 may be communicatively connected by a near field communication device, a network, a bus, or the like.
The collecting device 110 is configured to collect original point cloud data of a region to be detected, and send the original point cloud data to the electronic device 120.
The electronic device 120 is configured to implement the boundary detection method provided in the embodiment of the present invention.
Wherein the acquisition device 110 may be, but is not limited to: install laser radar's unmanned aerial vehicle or fixed shooting equipment. The electronic device 120 may be, but is not limited to: personal computers, notebook computers, ipads, wearable devices, and servers. The server can be an independent server or a server cluster.
It should be understood that in other embodiments, the electronic device 120 and the acquisition device 110 may be integrated.
Fig. 2 is a block diagram of the electronic device 120. The electronic device 120 includes a memory 130, a processor 140, and a communication module 150. The elements of the memory 130, the processor 140, and the communication module 150 are electrically connected to each other, directly or indirectly, to enable the transmission or interaction of data. For example, the components may be electrically connected to each other via one or more communication buses or signal lines.
The memory 130 is used to store programs or data. The Memory 130 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like.
The processor 140 is used to read/write data, computer programs, or machine executable instructions stored in the memory 130 and perform corresponding functions. In particular, the processor 140, when executing the computer program or machine executable instructions in the memory 130, implements the boundary detection method provided by the embodiments of the present invention.
The communication module 150 is used for establishing a communication connection between the electronic device 120 and other communication terminals through a network, and for transceiving data through the network.
It should be understood that the configuration shown in fig. 2 is merely a schematic diagram of the configuration of the electronic device 120, and that the electronic device 120 may include more or fewer components than shown in fig. 2, or have a different configuration than shown in fig. 1. The components shown in fig. 2 may be implemented in hardware, software, or a combination thereof.
Referring to fig. 3, fig. 3 is a flowchart illustrating a boundary detection method according to an embodiment of the present invention. In this embodiment, as an example of applying the method to the electronic device 120 in fig. 1 and 2, the method may include the following steps.
S101, obtaining original point cloud data of a region to be detected.
For example, in the architecture shown in fig. 1, after the acquisition device 110 acquires the original point cloud data of the region to be detected, the original point cloud data is sent to the electronic device 120, and the electronic device 120 receives the original point cloud data. For another example, in other implementations, the electronic device 120 may obtain the raw point cloud data from a database storing the raw point cloud data, or the user may input the raw point cloud data to the electronic device 120.
S103, screening the original point cloud data to obtain point cloud data to be detected.
After the electronic device 120 receives the original point cloud data, the original point cloud data is screened, and after part of interference data is eliminated, point cloud data to be detected is obtained. Namely, the point cloud data to be detected is the point cloud data with interference data screened out.
And S105, based on the point cloud data to be detected, extracting land data after performing land segmentation by using a preset segmentation algorithm.
The preset segmentation algorithm can perform block segmentation based on the point cloud data to be detected so as to extract the block data.
And S107, generating a plot comparison map according to the point cloud data to be detected and the plot data.
And S109, auditing and correcting the plot data based on the plot comparison graph, and drawing the plot boundary of the region to be detected.
Since the land parcel data may have a problem of poor accuracy, the electronic device 120 generates a land parcel comparison map by combining the land parcel data on the basis of the point cloud data to be detected. And then checking and correcting the data of the land parcel based on the land parcel comparison graph to draw the land parcel boundary of the land parcel to be detected.
In the boundary detection method, the obtained original point cloud data of the region to be detected is screened to obtain the point cloud data to be detected, and interference data in the original point cloud data is screened out. And then, the block segmentation is carried out on the point cloud data to be detected by utilizing a segmentation algorithm, the block data is extracted, so that a block comparison graph is generated by combining the point cloud data to be detected, the block data is further corrected according to the block comparison graph, the block boundary of the region to be detected is drawn, the drawn block boundary is more accurate, and the problem that the accuracy of the drawn block boundary is lower due to the uncertainty of the block boundary is greatly solved.
It should be noted that after the original point cloud data is acquired, if the area of the region to be detected is large, for example, the area of the region to be detected exceeds a preset area, the original point cloud data may be divided into a plurality of smaller regions to be detected based on the preset area, and then the original point cloud data of each smaller region to be detected is processed in S103-S109 to describe the parcel data of each region to be detected.
The original point cloud data can be screened in various ways, for example, the screening can be performed by filtering, denoising, and a set selection rule. In this embodiment, a possible implementation manner of the step S103 is provided, referring to fig. 4, fig. 4 is a schematic flow chart of a part of sub-steps of the step S103, and the original point cloud data can be screened through the following steps to obtain the point cloud data to be detected.
S103-1, filtering the original point cloud data by adopting a filtering method to obtain filtered point cloud data.
For example, the original point cloud data is filtered to remove the hash points and the independent points in the original point cloud data which interfere with the subsequent segmentation algorithm, so as to improve the target extraction precision.
S103-2, eliminating data with the elevation from the earth surface exceeding a preset threshold value in the filtering point cloud data.
Since the land is of a certain thickness, such as trees, viaducts, buildings, etc., which are far higher than the land, a portion of the land may be blocked. Therefore, a certain preset threshold value is set, and the data with the elevation exceeding the preset threshold value from the earth surface in the filtering point cloud data are removed, so that the shelters such as trees, high-price bridges, buildings and the like can be removed.
It should be understood that the point cloud data refers to a set of vectors in a three-dimensional coordinate system, and therefore the point cloud data itself has the attribute of elevation data, i.e. the elevation data can be obtained from the point cloud data. Moreover, the point cloud data records the scanning data in the form of points, each point includes three-dimensional coordinates and color information, and even some points include reflection intensity information.
In other embodiments, the filtering method may be adopted to filter the original point cloud data, and then the filtered point cloud data is subjected to data screening according to a set selection rule to obtain the point cloud data to be detected. Or filtering after screening data according to a set selection rule.
The data such as hash points, independent points, shelters and the like are eliminated through a filtering method, so that the interference caused by the point cloud data can be reduced, the interference of the shelters is eliminated, and the accuracy of drawing the boundary of the land parcel is improved.
The filtering method in S103-2 can be flexibly selected. For example, at least one of a statistical filtering method, a bilateral filtering method, a gaussian filtering method, and a radius filtering method may be included.
The segmentation algorithm in S105 can flexibly select various clustering segmentation algorithms, a point cloud frequency-based segmentation algorithm, a region growing algorithm, a point cloud segmentation algorithm, and the like.
For example, in one embodiment, a color-based region growing segmentation algorithm and a region growing-based point cloud segmentation algorithm may be included. On this basis, referring to fig. 5, a flow diagram of a part of the sub-steps of S105 includes the following steps.
S105-1, based on the point cloud data to be detected, performing land parcel identification and segmentation by using a region growing and segmenting algorithm based on colors, and extracting first segmentation data.
Wherein the first segmentation data includes identification of each land parcel obtained by the segmentation, boundary data of each land parcel, and an initial classification of each land parcel. The categories include cultivated land, forest, pond, lake, etc.
The region growing and dividing algorithm based on colors is used for identifying and dividing the land parcel according to the color information of each point in the point cloud data to be detected and outputting first dividing data related to land parcel division.
Due to the growth of plants in one land, the regions in the same land generally have the same characteristics, such as agricultural land, one land is planted with the same crop, a pond contains water, a forest contains trees, and the points in the point cloud data corresponding to the land with the same characteristics have homochromatism. Therefore, the point cloud data can be identified and divided into the land blocks by using the color information of the points as the basis by using the color-based region growing and dividing algorithm.
It should be understood that, because the points in the point cloud data to be measured include color information, and because there are multiple real objects corresponding to the points, the points corresponding to different real objects have different color information. Therefore, the color-based region growing segmentation algorithm can identify the attributes of each point besides identifying and segmenting the land, wherein the attributes comprise trees, ponds, agricultural land parcels, grass and the like.
Therefore, each point in the point cloud data to be detected is assigned with semantic information based on the identified attribute of each point, wherein the semantic information refers to semantic information about the attribute, for example, if the attribute of the point is a tree, the voice information of the point is the tree.
And S105-2, performing secondary land parcel segmentation by using a point cloud segmentation algorithm based on region growing on the basis of the first segmentation data, and extracting land parcel data.
The land data comprises each land obtained by secondary segmentation, boundary data of each land and a category of each land. Categories include mountainous regions, paddy fields, dry lands, ponds, forests, lakes, buildings, and the like.
The point cloud segmentation algorithm based on region growing is used for carrying out land parcel segmentation according to the curvature value of the midpoint of the number to be measured and outputting land parcel data related to land parcel segmentation. And the curvature value of the point cloud data point is a measure of the terrain.
And inputting the point cloud data to be detected on which the first segmentation data are superposed into a point cloud segmentation algorithm based on region growing, and performing land block segmentation again according to the curvature values of the points on the basis of the first segmentation data to obtain land block data. The block data is data obtained by further dividing the block, that is, data obtained by finely dividing the block.
For example, the first plot segmentation is to identify an agricultural plot, and for a large, medium or large scale farm, the plot is also characterized by flatness, normativity, regularity and the like, and the curve values of the points are reflected on the point cloud data. Thus, after the second division, the agricultural land can be specifically subdivided into mountainous, dry, and paddy fields, etc., and the large, medium, or large-scale agricultural land can be divided into smaller agricultural lands.
In the above steps S105-1 to S105-2, the point cloud data to be measured is further divided into secondary land blocks by using the region growing division algorithm based on color and the point cloud division algorithm based on region growing to divide the land blocks more accurately, so as to further subdivide the land blocks and obtain the types and boundary data of each subdivided land block.
Note that, since semantic information of each point in the point cloud data is already given when the first divided data is obtained, the block data obtained after the second division also includes semantic information of each point.
In another embodiment, the first block division may be performed by using a point cloud division algorithm based on region growing, and the second block division may be performed by using a region growing division algorithm based on color.
In this embodiment, the plot contrast map can be flexibly selected. For example, a plot contrast graph is a contrast between multiple graphs of different dimensions, i.e., plot data is displayed on the graphs of different dimensions. In one embodiment, the plot contrast map may include a two-dimensional orthophotomap and a three-dimensional scene map.
For example, the point cloud data to be detected on which the land data is superimposed is projected to obtain a two-dimensional orthophoto map, and the three-dimensional scene map can be obtained according to the point cloud data to be detected on which the land data is superimposed.
The principle of the orthophoto map is that the real world is projected to a two-dimensional plane according to a certain mathematical rule to obtain a two-dimensional orthophoto map.
Meanwhile, because the two-dimensional orthophoto map is obtained by projection, a shielding area formed by a tree crown and other shielding objects is easy to appear on the two-dimensional orthophoto map, so that the boundary of the land parcel in the shielded area has uncertainty, and the accuracy of the drawn boundary of the land parcel is poor. Therefore, the sheltering object forming the sheltering area is removed by combining the three-dimensional scene graph, so that the effect of auditing and correcting the land parcel data is improved.
It should be understood that the three-dimensional scene map and the two-dimensional orthophoto map each include boundary data of the parcel and a parcel category.
For example, when a boundary of a certain block is drawn on a three-dimensional scene graph and a two-dimensional orthophoto map, the type of the block is displayed as semantic information.
On this basis, regarding S109, in an embodiment, referring to fig. 6 and 7, fig. 6 is a schematic flow chart of a part of sub-steps of S109, and includes the following steps.
And S109-1, controlling the two-dimensional orthophoto map and the three-dimensional scene map in a linkage manner.
The linkage control means that when any one of the two-dimensional orthophoto map and the three-dimensional scene map is rotated, translated, slid, enlarged, reduced and the like, the other map synchronously performs the same operation.
And the two-dimensional orthophoto map and the three-dimensional scene map are cut into tile data to be loaded and rendered, wherein the two-dimensional orthophoto map adopts a tile cutting rule of Google, and the three-dimensional scene map adopts a cutting rule of EPT. Therefore, the two-dimensional orthophoto map and the three-dimensional scene map can be checked by human eyes, and the efficiency of data transmission and display is accelerated on the premise of not influencing the display effect.
One implementation of the coordinated control is that the three-dimensional scene graph and the two-dimensional orthophoto graph can be displayed on the screen of the electronic device 120 in a dual-view manner, that is, the three-dimensional scene graph and the two-dimensional orthophoto graph are simultaneously displayed, and a single-view full-screen display is supported.
S109-2, hiding data with the elevation exceeding a preset value from the earth surface in the three-dimensional scene graph to obtain a three-dimensional graph to be drawn, and taking the two-dimensional orthophoto map as the image map to be drawn.
The size of the preset value can be flexibly set according to the actual processing requirement, and different preset values can be provided in different regions. For example, in the present embodiment, the preset value may be smaller than the preset threshold in step S103-2, and if the preset threshold is 1.5m, the preset value may be 1m, so as to further exclude a blocking object capable of blocking the boundary of the parcel, and simplify the three-dimensional image to be drawn and the image to be drawn, so as to reduce interference factors during the drawing process.
And S109-3, amplifying the three-dimensional image to be drawn by a preset multiple, and drawing a plot boundary line on the three-dimensional image to be drawn and the image to be drawn by combining the plot boundary data.
After the three-dimensional image to be drawn is amplified by the preset times, the three-dimensional image to be drawn and the image to be drawn synchronously reach the required resolution ratio, and the full appearance of the area to be drawn can be clearly displayed, so that boundary points can be drawn in the image to be drawn and the three-dimensional image to be drawn according to the boundary data of the land parcel.
It should be understood that drawing the boundary points on one of the graphs will simultaneously draw the boundary points at corresponding locations on the other graph.
And S109-4, judging whether each boundary point on the boundary line of the land block meets a preset rule or not. If not, executing S109-5, otherwise, ending the drawing.
The preset rule is a basis for judging whether the boundary point is reasonable, so that different boundary drawing requirements, for example, different precisions, can have different preset rules.
And S109-5, displaying the image to be drawn and the boundary points which do not accord with the preset rule on the three-dimensional image to be drawn as abnormal points.
The logic for displaying the outliers can be flexibly set. For example, in this embodiment, as long as a boundary point corresponding to the same boundary data does not conform to a preset rule in at least one of the image to be drawn and the three-dimensional image to be drawn, both the boundary points are displayed as abnormal points.
And S109-6, determining target boundary points by combining the three-dimensional image to be drawn and the image to be drawn, and replacing the abnormal points with the target boundary points to finish the drawing of the plot boundary.
It should be understood that after the rendering of the land parcel boundary is finished, the land parcel data is synchronously updated to obtain the corrected land parcel data. After the drawing is finished, clicking any point in the plot boundary of a certain plot displays the category of the plot in a voice information mode, such as paddy field, mountain land and the like.
Through the steps S109-1 to S109-6, according to the land parcel data, boundary lines are drawn on the three-dimensional image to be drawn and the image to be drawn, and under the condition that at least one of the image display boundary points does not accord with the preset rule, the abnormal points which do not accord with the preset rule are corrected, so that the drawn land parcel boundary and the corrected land parcel data are more accurate.
It should be noted that the plot boundary line of each plot can be drawn through the above-mentioned steps S109-1 to S109-6. Before drawing the boundary, the type of the land, such as paddy field, can be selected, after the boundary line of the selected land is drawn, the preset rule corresponding to the selected type is called, the drawn boundary line of the land is checked, and abnormal points are highlighted. The drawn boundary points can also be checked in real time based on preset rules during the process of drawing the boundary points.
Further, since the plot includes multiple categories, different categories have their own characteristics, such as hilly terrain, which changes rapidly in slope, and paddy fields, which are flat, which changes slowly in slope. Therefore, the different categories have respective preset rules, that is, each category has a corresponding preset rule.
For example, in the present embodiment, the preset rule may be related to elevation changes, i.e., the preset rule may include an elevation difference threshold. I.e., different categories of plots have different elevation difference thresholds.
And the land parcel data comprises the number of the land parcels obtained by the division, the types of the land parcels and the boundary data of the land parcels.
Therefore, in one embodiment, referring to fig. 8, a flow chart of a part of the sub-steps of the above step S109-4 is shown.
S201, calculating the elevation difference between adjacent boundary points on the boundary line of the land parcel.
A plot boundary line includes multiple sets of adjacent boundary points and a complete plot boundary line should be a closed line.
For example, there are 4 boundary points on the boundary line of the land, each boundary point forms a set of adjacent boundary points with the adjacent boundary points, there are 4 sets of adjacent boundary points, and the four sets of adjacent boundary points belong to the same land. For each set of adjacent boundary points, S202 is performed.
S202, if the elevation difference is larger than the elevation difference threshold value corresponding to the type of the land parcel, the adjacent boundary points do not accord with the preset rule.
That is, as long as the height difference is greater than the height difference threshold, it is determined that the two boundary points corresponding to the height difference are both abnormal points.
By judging the abnormal points according to the elevation difference threshold, the boundary points with gradient changes not conforming to the characteristics of the land can be eliminated, the drawn land boundary is more reasonable, and the accuracy of land data can be improved.
Optionally, the preset rule may further include a preset distance, that is, the interval length between the boundary points cannot exceed the preset distance, for example, cannot exceed 100 m. And, the plots of different categories have different preset distances.
In addition, the three-dimensional scene graph and the three-dimensional graph to be drawn both support viewing of the cut-away view of the parcel boundary for analysis of elevation information of the parcel boundary.
Further, the method for determining the target boundary point may be flexibly selected, and may include, for example, a set boundary point rule, a detection algorithm, and the like. In the present embodiment, the method of specifying the target boundary point may be a set boundary point rule. Referring to fig. 9, which is a flowchart of a part of the sub-step of S109-6, the determination of the target boundary point is achieved by the following steps.
S301, determining the three-dimensional image to be drawn and the area of the abnormal point in the image to be drawn according to the position of the abnormal point.
S302, after the area where the abnormal point is located is enlarged to a preset resolution, a boundary point between the land where the abnormal point is located and an adjacent land is determined.
The area where the abnormal point is located is amplified to the preset resolution, and the accuracy of the determined junction point can be improved to a certain extent.
And S303, taking the boundary point as a target boundary point.
Through the above S301 to S303, the target boundary point can be determined more accurately.
When the abnormal point can not be eliminated all the time, warning information can be sent out to remind a user of artificial correction, for example, the three-dimensional image to be drawn and the image to be drawn are edited through operations such as rotation and the like, so that the drawing is completed.
According to the boundary detection method provided by the embodiment of the invention, after the plot data is obtained by utilizing the segmentation algorithm, the two-dimensional orthophoto map and the three-dimensional scene map which are obtained by combining the point cloud data to be detected and the plot data are combined, the plot data are further checked and corrected, and the plot boundary line is drawn, so that more accurate plot boundary lines and plot data can be obtained, and the method is more efficient and convenient.
And, the data that may produce interference in the original point cloud data is excluded, thereby being capable of further improving the accuracy. And finally, the obtained land data has elevation data and voice information.
It should be understood that although the various steps in the flowcharts of fig. 3-9 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 3-9 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
In order to perform the corresponding steps in the above embodiments and various possible manners, an implementation manner of the boundary detection device 160 is given below, and optionally, the boundary detection device 160 may adopt the device structure of the electronic device 120 shown in fig. 2. Further, referring to fig. 10, fig. 10 is a functional block diagram of a boundary detection apparatus 160 according to an embodiment of the present invention. It should be noted that the basic principle and the generated technical effect of the boundary detection device 160 provided in the present embodiment are the same as those of the above embodiments, and for the sake of brief description, no part of the present embodiment is mentioned, and corresponding contents in the above embodiments may be referred to. The boundary detection apparatus 160 includes a preprocessing module 170, a segmentation module 180, and a rendering module 190.
The preprocessing module 170 is configured to acquire original point cloud data of a region to be detected, and screen the original point cloud data to obtain point cloud data to be detected.
And the segmentation module 180 is used for extracting the land parcel data after performing land parcel segmentation by using a preset segmentation algorithm based on the point cloud data to be detected.
The land parcel data comprises land parcel number and land parcel boundary data.
And the drawing module 190 is configured to generate a plot comparison map according to the point cloud data to be detected and the plot data, perform audit correction on the plot data based on the plot comparison map, and draw a plot boundary of the region to be detected.
Alternatively, the modules may be stored in the memory 130 shown in fig. 2 in the form of software or Firmware (Firmware) or be fixed in an Operating System (OS) of the electronic device 120, and may be executed by the processor 140 in fig. 2. Meanwhile, data, codes of programs, and the like required to execute the above-described modules may be stored in the memory 130.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, the functional modules in the embodiments of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A boundary detection method, comprising:
acquiring original point cloud data of a region to be detected;
screening the original point cloud data to obtain point cloud data to be detected;
based on the point cloud data to be detected, extracting land parcel data after land parcel segmentation is carried out by utilizing a preset segmentation algorithm;
generating a plot comparison map according to the point cloud data to be detected and the plot data;
and based on the plot comparison graph, auditing and correcting the plot data, and drawing the plot boundary of the region to be detected.
2. The boundary detection method according to claim 1, wherein the segmentation algorithm includes a region growing segmentation algorithm based on color and a point cloud segmentation algorithm based on region growing, and the step of extracting the land parcel data after performing land parcel segmentation by using a preset segmentation algorithm based on the point cloud data to be detected comprises:
based on the point cloud data to be detected, performing land parcel identification and segmentation by using the region growing and segmenting algorithm based on colors, and extracting first segmentation data;
and performing secondary land parcel segmentation by using the point cloud segmentation algorithm based on the region growing based on the first segmentation data, and extracting land parcel data.
3. The boundary detection method according to claim 1 or 2, wherein the map of land parcel comparison comprises a two-dimensional orthophoto map and a three-dimensional scene map, the map of land parcel data comprises boundary data of each land parcel obtained by segmentation, and the three-dimensional scene map and the two-dimensional orthophoto map each comprise boundary data of a land parcel;
the step of auditing and correcting the plot data and drawing the plot boundary of the region to be detected based on the plot comparison graph comprises the following steps:
controlling the two-dimensional orthophoto map and the three-dimensional scene map in a linkage manner;
hiding data with the elevation exceeding a preset value from the earth surface in the three-dimensional scene graph to obtain a three-dimensional graph to be drawn, and taking the two-dimensional orthophoto map as the image map to be drawn;
amplifying the three-dimensional image to be drawn by a preset multiple, and drawing a plot boundary line on the three-dimensional image to be drawn and the image to be drawn by combining boundary data of the plot, wherein the plot boundary line comprises a plurality of boundary points;
judging whether each boundary point on the boundary line of the land block meets a preset rule or not, if not, displaying the image map to be drawn and the boundary point on the three-dimensional map to be drawn which does not meet the preset rule as an abnormal point;
and determining a target boundary point by combining the three-dimensional image to be drawn and the image to be drawn, and replacing the abnormal point with the target boundary point to finish the drawing of the plot boundary.
4. The boundary detection method of claim 3, wherein the step of determining the target boundary points comprises:
determining the three-dimensional image to be drawn and the area of the abnormal point in the image to be drawn according to the position of the abnormal point;
after the area where the abnormal point is located is enlarged to a preset resolution ratio, determining a boundary point between a plot where the abnormal point is located and an adjacent plot;
and taking the boundary point as a target boundary point.
5. The boundary detection method according to claim 3, wherein the land parcel comprises a plurality of categories, each category corresponds to a preset rule, the land parcel data further comprises a category of each land parcel, and the preset rule comprises a height difference threshold;
the step of judging whether each boundary point on the plot boundary line meets a preset rule comprises the following steps:
and calculating the elevation difference between adjacent boundary points on the boundary line of the land parcel, wherein if the elevation difference is greater than the elevation difference threshold value corresponding to the type of the land parcel, the adjacent boundary points do not accord with the preset rule.
6. The boundary detection method according to claim 1, wherein the step of screening the original point cloud data to obtain point cloud data to be detected comprises:
filtering the original point cloud data by adopting a filtering method to obtain filtered point cloud data;
and eliminating data with the elevation exceeding a preset threshold value from the earth surface in the filtering point cloud data.
7. The boundary detection method of claim 6, wherein the filtering method includes at least one of a statistical filtering method, a bilateral filtering method, a Gaussian filtering method, and a radius filtering method.
8. A boundary detection device is characterized by comprising a preprocessing module, a segmentation module and a drawing module;
the preprocessing module is used for acquiring original point cloud data of a region to be detected and screening the original point cloud data to obtain point cloud data to be detected;
the segmentation module is used for extracting land parcel data after performing land parcel segmentation by using a preset segmentation algorithm based on the point cloud data to be detected, wherein the land parcel data comprises land parcel number and land parcel boundary data;
the drawing module is used for generating a plot comparison graph according to the point cloud data to be detected and the plot data, auditing and correcting the plot data based on the plot comparison graph, and drawing the plot boundary of the region to be detected.
9. An electronic device comprising a processor and a memory, the memory storing machine executable instructions executable by the processor to implement the boundary detection method of any one of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the boundary detection method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210216828.5A CN114581464A (en) | 2022-03-07 | 2022-03-07 | Boundary detection method and device, electronic equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210216828.5A CN114581464A (en) | 2022-03-07 | 2022-03-07 | Boundary detection method and device, electronic equipment and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114581464A true CN114581464A (en) | 2022-06-03 |
Family
ID=81777998
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210216828.5A Pending CN114581464A (en) | 2022-03-07 | 2022-03-07 | Boundary detection method and device, electronic equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114581464A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115338874A (en) * | 2022-10-19 | 2022-11-15 | 爱夫迪(沈阳)自动化科技有限公司 | Laser radar-based robot real-time control method |
| CN115661664A (en) * | 2022-12-08 | 2023-01-31 | 东莞先知大数据有限公司 | Boundary occlusion detection and compensation method, electronic equipment and storage medium |
-
2022
- 2022-03-07 CN CN202210216828.5A patent/CN114581464A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115338874A (en) * | 2022-10-19 | 2022-11-15 | 爱夫迪(沈阳)自动化科技有限公司 | Laser radar-based robot real-time control method |
| CN115338874B (en) * | 2022-10-19 | 2023-01-03 | 爱夫迪(沈阳)自动化科技有限公司 | Real-time robot control method based on laser radar |
| CN115661664A (en) * | 2022-12-08 | 2023-01-31 | 东莞先知大数据有限公司 | Boundary occlusion detection and compensation method, electronic equipment and storage medium |
| CN115661664B (en) * | 2022-12-08 | 2023-04-07 | 东莞先知大数据有限公司 | Boundary occlusion detection and compensation method, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jayathunga et al. | Evaluating the performance of photogrammetric products using fixed-wing UAV imagery over a mixed conifer–broadleaf forest: Comparison with airborne laser scanning | |
| Koreň et al. | Accuracy of tree diameter estimation from terrestrial laser scanning by circle-fitting methods | |
| CN106384081B (en) | Slope farmland extraction method and system based on high-resolution remote sensing image | |
| Mu et al. | Characterization of peach tree crown by using high-resolution images from an unmanned aerial vehicle | |
| Gruszczyński et al. | Comparison of low-altitude UAV photogrammetry with terrestrial laser scanning as data-source methods for terrain covered in low vegetation | |
| CN108846352B (en) | Vegetation classification and identification method | |
| Di Gennaro et al. | Evaluation of novel precision viticulture tool for canopy biomass estimation and missing plant detection based on 2.5 D and 3D approaches using RGB images acquired by UAV platform | |
| CN114581464A (en) | Boundary detection method and device, electronic equipment and computer readable storage medium | |
| Jiang et al. | Quantitative analysis of cotton canopy size in field conditions using a consumer-grade RGB-D camera | |
| CN106407880A (en) | Inventory, growth, and risk prediction using image processing | |
| Packalen et al. | Predicting the spatial pattern of trees by airborne laser scanning | |
| Röder et al. | Application of optical unmanned aerial vehicle-based imagery for the inventory of natural regeneration and standing deadwood in post-disturbed spruce forests | |
| Vázquez-Arellano et al. | Determination of stem position and height of reconstructed maize plants using a time-of-flight camera | |
| CN108919295A (en) | Airborne LiDAR point cloud road information extracting method and device | |
| CN111222539B (en) | Method for optimizing and expanding supervision classification samples based on multi-source multi-temporal remote sensing image | |
| CN114548277B (en) | Method and system for ground point fitting and crop height extraction based on point cloud data | |
| Xu et al. | An improved space colonization algorithm with DBSCAN clustering for a single tree skeleton extraction | |
| Lucena et al. | The combined use of UAV-based RGB and DEM images for the detection and delineation of orange tree crowns with mask R-CNN: an approach of labeling and unified framework | |
| CN116739739A (en) | Loan amount evaluation method and device, electronic equipment and storage medium | |
| Ullah et al. | Comparing image-based point clouds and airborne laser scanning data for estimating forest heights | |
| Sarıtaş et al. | Enhancing Ground Point Extraction in Airborne LiDAR Point Cloud Data Using the CSF Filter Algorithm | |
| CN114743008B (en) | Single plant vegetation point cloud data segmentation method and device and computer equipment | |
| Oliveira et al. | Citrus orchards under formation evaluated by UAV-Based RGB Imagery | |
| CN111861836B (en) | Three-dimensional mountain land planning method and device, storage medium and computer equipment | |
| Berveglieri et al. | Forest cover change analysis based on temporal gradients of the vertical structure and density |
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 |