CN114545436A - Mulching film identification method and device, computer equipment and storage medium - Google Patents

Mulching film identification method and device, computer equipment and storage medium Download PDF

Info

Publication number
CN114545436A
CN114545436A CN202111620173.XA CN202111620173A CN114545436A CN 114545436 A CN114545436 A CN 114545436A CN 202111620173 A CN202111620173 A CN 202111620173A CN 114545436 A CN114545436 A CN 114545436A
Authority
CN
China
Prior art keywords
mulching film
point
reflection intensity
soil
points
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
Application number
CN202111620173.XA
Other languages
Chinese (zh)
Inventor
徐健
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Xaircraft Technology Co Ltd
Original Assignee
Guangzhou Xaircraft Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangzhou Xaircraft Technology Co Ltd filed Critical Guangzhou Xaircraft Technology Co Ltd
Priority to CN202111620173.XA priority Critical patent/CN114545436A/en
Publication of CN114545436A publication Critical patent/CN114545436A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/88—Lidar systems specially adapted for specific applications
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
    • G01S17/06—Systems determining position data of a target
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/88—Lidar systems specially adapted for specific applications
    • G01S17/89—Lidar systems specially adapted for specific applications for mapping or imaging

Landscapes

  • Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Electromagnetism (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • General Physics & Mathematics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Optical Radar Systems And Details Thereof (AREA)

Abstract

The embodiment of the application provides a laser radar-based mulching film identification method and device, computer equipment and a storage medium, and solves the problems that in the prior art, a mulching film identification method is long in time consumption, complex in algorithm and low in precision. The method comprises the following steps: constructing a point cloud map based on point cloud data of a land parcel acquired by a laser radar; dividing the point cloud map into a plurality of grids; determining a boundary value of the laser reflection intensity based on a distribution rule of the laser reflection intensity of each point in the grids, wherein the boundary value is used for indicating the maximum value of the laser reflection intensity of the non-covered land film point corresponding to the non-covered land area; calculating the average value of the laser reflection intensity of all points contained in each of the grids; determining all points in the grid with the mean value less than or equal to the boundary value as mulching film points corresponding to the mulching film, wherein the mulching film points comprise mulching film points corresponding to the soil covering area and non-mulching film points corresponding to the non-soil covering area; a mulch is identified from the point cloud map based on the geographic location of the mulch points.

Description

Mulching film identification method and device, computer equipment and storage medium
Technical Field
The application relates to the technical field of autonomous navigation of farmland operation vehicles, in particular to a mulching film identification method and device, computer equipment and a storage medium.
Background
In the autonomous navigation process of the farm work vehicle, the mulching film laid in the land is usually used as a navigation path. In this case, in order to realize autonomous navigation, the mulching film needs to be identified from the map first. The mulching film is generally classified into a near-earth aerial photography recognition method and a satellite image recognition method according to the difference in shooting height.
For a near-earth aerial photography identification method, an unmanned aerial vehicle or a manned aircraft is required to acquire an image in the air, and then the position of a mulching film is acquired by splicing the image and identifying Artificial Intelligence (AI). The problems with this approach include at least: 1. because data acquisition needs to be carried out in the air, a large amount of time is spent in the early stage; 2. because of using the AI recognition method, a large amount of manual labeling work and training are needed; 3. since the image characteristics of the mulching film are not obvious, the overfitting condition is easy to occur, so that the false detection is caused; 4. due to the fact that splicing is needed, the requirement on splicing precision is high, and errors at seams can cause errors in identification of mulching films.
For the satellite image identification method, a multispectral camera is required to acquire an image to acquire the characteristics of the mulching film, and finally, the position of the mulching film is acquired through an AI identification method. The problems with this approach include at least: 1. the cost is high; 2. a large amount of work is required to reduce noise; 3. the relatively low precision of the satellite images can result from the narrow width of the mulch.
Disclosure of Invention
In view of this, the embodiment of the present application provides a laser radar-based mulch identification method and apparatus, a computer device, and a storage medium, so as to solve the problems of long time consumption, complex algorithm, and low precision of the mulch identification method in the prior art.
The application provides a mulch film identification method based on laser radar in a first aspect, which comprises the following steps: constructing a point cloud map based on point cloud data of a plot acquired by a laser radar, wherein the plot comprises soil and a mulching film laid on the soil, the mulching film comprises a soil covering area and a non-soil covering area, and the point cloud data comprises geographical positions of all points and laser reflection intensities of all points; dividing the point cloud map into a plurality of grids; determining a boundary value of the laser reflection intensity based on a distribution rule of the laser reflection intensity of each point in the grids, wherein the boundary value is used for indicating the maximum value of the laser reflection intensity of the non-covered land film point corresponding to the non-covered land area; calculating the average value of the laser reflection intensity of all points contained in each of the grids; determining all points in the grid with the mean value less than or equal to the boundary value as mulching film points corresponding to the mulching film, wherein the mulching film points comprise mulching film points corresponding to the soil covering area and non-mulching film points corresponding to the non-soil covering area; a mulch is identified from the point cloud map based on the geographic location of the mulch points.
In one embodiment, the collecting direction of the laser radar is the extending direction of the mulching film; before dividing the point cloud map into a plurality of grids, the method further comprises the following steps: and determining a target area from the point cloud map based on the acquired acquisition direction, initial position and effective radius of the laser radar and the length of the land parcel. Dividing the point cloud map into a plurality of grids comprises: the target area is divided into a plurality of grids.
In one embodiment, before dividing the target area into a plurality of grids, further comprising: and adjusting the direction of the target area so that the extension direction of the mulching film is parallel to any coordinate axis of the point cloud map.
In one embodiment, the grid is square, and the side length of the grid is 1/2 of the width of the mulching film.
In one embodiment, determining the boundary value of the laser reflection intensity based on the distribution rule of the laser reflection intensity of each point in the plurality of grids comprises: constructing a histogram based on point clouds in a plurality of grids, wherein the horizontal coordinate of the histogram is the laser reflection intensity, and the vertical coordinate is the number of points; and determining a predetermined point of the histogram in the coverage area of the abscissa as a boundary value of the reflection intensity.
In one embodiment, before constructing the histogram based on the point clouds in the plurality of grids, further comprises: calculating the variance of the laser reflection intensity of all the points contained in each of the grids; and filtering the variance based on a preset variance interval to filter grids which simultaneously contain the uncovered soil film points and the soil points corresponding to the soil. Constructing a histogram based on point clouds in a plurality of grids comprises: a histogram is constructed based on the point clouds in the filtered mesh.
In one embodiment, determining that a predetermined point of the histogram within the coverage area of the abscissa is a boundary value of the reflection intensity comprises: and determining the middle point of the coverage interval of the horizontal coordinate of the histogram as a boundary value of the reflection intensity.
This application second aspect provides a plastic film recognition device based on laser radar, includes: the construction module is used for constructing a point cloud map based on point cloud data of a land parcel acquired by a laser radar, the land parcel comprises soil and a mulching film laid on the soil, the mulching film comprises a soil covering area and a non-soil covering area, and the point cloud data comprises the geographical positions of all points and the laser reflection intensity of all points; the dividing module is used for dividing the point cloud map into a plurality of grids; the first determining module is used for determining a boundary value of the laser reflection intensity based on the distribution rule of the laser reflection intensity of each point in the grids, and the boundary value is used for indicating the maximum value of the laser reflection intensity of the non-soil-covering membrane point corresponding to the non-soil-covering area; the calculation module is used for calculating the mean value of the laser reflection intensity of all the points contained in each grid; the second determination module is used for determining all points in the grid with the mean value smaller than or equal to the boundary value as mulching film points corresponding to the mulching films, and the mulching film points comprise mulching film points corresponding to the soil covered area and non-mulching film points corresponding to the non-soil covered area; and the identification module is used for identifying the mulching film from the point cloud map based on the geographic position of the mulching film point.
A third aspect of the application provides a computer device, comprising a memory, a processor and a computer program stored on the memory and executed by the processor, wherein the processor implements the steps of the lidar-based mulch identification method provided by any of the above embodiments when executing the computer program.
A fourth aspect of the present application provides a computer-readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the steps of the lidar-based mulch identification method provided in any of the above embodiments.
According to the mulch identification method and device based on the laser radar, the computer equipment and the storage medium, firstly, a point cloud map is constructed based on point cloud data of a land parcel acquired by the laser radar in real time; secondly, dividing the point cloud map into a plurality of grids; secondly, determining the maximum value of the laser reflection intensity of the non-soil covering film points corresponding to the non-soil covering area based on the distribution rule of the laser reflection intensity of each point in the grids; then, with the maximum value as a reference, all points in the grid where the average of the laser reflection intensities of the grid is larger than the maximum value are determined as the mulching film points. According to the process, on one hand, the geographical position of the mulching film in the land is quickly acquired by adopting the laser radar, so that the time spent on image acquisition in the early stage of mulching film identification is saved; on the other hand, the mulching film identification process is simple in logic and easy to realize in algorithm; on the other hand, the soil covering area of the mulching film is identified by adopting a statistical method, the identified edge of the mulching film is ensured to be the real edge of the mulching film instead of the boundary between the soil covering area and the soil non-covering area, and therefore the identification precision of the mulching film is improved.
Drawings
Fig. 1 is a schematic flow chart of a laser radar-based mulch identification method according to a first embodiment of the present application.
Fig. 2 is a schematic flow chart of a laser radar-based mulch identification method according to a second embodiment of the present application.
Fig. 3 is a schematic position diagram of a target area in a point cloud map according to an embodiment of the present disclosure.
Fig. 4 is a schematic diagram illustrating an implementation process of step S130 according to the first embodiment of the present application.
Fig. 5 is a histogram constructed based on point clouds in a plurality of grids according to an embodiment of the present disclosure.
Fig. 6 is a schematic diagram illustrating an execution process of step S130 according to a second embodiment of the present application.
Fig. 7 is a block diagram of a laser radar-based mulch identification apparatus according to an embodiment of the present application.
Fig. 8 is a block diagram of an electronic device according to an exemplary embodiment of the present application.
Detailed Description
As described in the background art, the mulch identification methods in the prior art, including the near-earth aerial photography identification method and the satellite image identification method, have the problems of long time spent on mulch identification, complex algorithm and low precision. In view of the above, embodiments of the present application provide a method and an apparatus for identifying a mulch film based on a laser radar, a computer device, and a storage medium, where first, a point cloud data of a predetermined land area is collected in real time by the laser radar, the predetermined land area includes soil and a mulch film laid on the soil, and the point cloud data includes geographical locations and laser reflection intensities of points. Secondly, because the laser reflection intensity of the non-soil area of the mulching film is obviously different from that of other areas (including the soil area and soil of the mulching film), a boundary value can be determined based on the laser reflection intensity of each point, and the boundary value is the maximum value of the laser reflection intensity of the non-soil area of the mulching film. And then, further carrying out meshing processing on the point clouds, counting the average reflection intensity of the point clouds in the grids, and when the average reflection intensity is smaller than a boundary value, considering all the points in the grids as mulching film point clouds, wherein the mulching film point clouds comprise the point clouds corresponding to the non-soil-covered areas of the mulching films and the point clouds corresponding to the soil-covered areas of the mulching films, so that all the point clouds of the mulching films are obtained, and the identification process of the mulching films is completed.
According to the mulch identification method and device based on the laser radar, the computer equipment and the storage medium, firstly, a point cloud map is constructed based on point cloud data of a land parcel acquired by the laser radar in real time; secondly, dividing the point cloud map into a plurality of grids; secondly, determining the maximum value of the laser reflection intensity of the non-soil covering film points corresponding to the non-soil covering area based on the distribution rule of the laser reflection intensity of each point in the grids; then, with the maximum value as a reference, all points in the grid where the average of the laser reflection intensities of the grid is larger than the maximum value are determined as the mulching film points. According to the process, on one hand, the geographical position of the mulching film in the land is quickly acquired by adopting the laser radar, and compared with a method for identifying the mulching film by using an image method, the time spent on image acquisition is saved; on the other hand, the mulching film identification process is simple in logic and easy to realize in algorithm; on the other hand, the soil covering area of the mulching film is identified by adopting a statistical method, the identified edge of the mulching film is ensured to be the real edge of the mulching film instead of the boundary between the soil covering area and the non-soil covering area, and therefore the identification precision of the mulching film is improved.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Exemplary method
Fig. 1 is a schematic flow chart of a laser radar-based mulch identification method according to a first embodiment of the present application. The embodiment can be applied to a farmland operation vehicle and is suitable for a scene that the farmland operation vehicle autonomously navigates on a land parcel paved with a mulching film. As shown in fig. 2, the lidar-based mulch identification method 100 includes:
and step S110, constructing a point cloud map based on the point cloud data of the parcel acquired by the laser radar. The land parcel includes soil and the plastic film of laying on soil, and the plastic film includes earthing region and non-earthing region. The point cloud data includes the geographical location of each point and the laser reflection intensity of each point.
Based on the point cloud data of the parcel acquired by the laser radar, a map construction method, such as a simultaneous localization and mapping (SLAM) technology, is adopted to obtain a point cloud map of the parcel.
Step S120, dividing the point cloud map into a plurality of grids.
Theoretically, the smaller the grid, the higher the accuracy of the subsequently identified mulch. However, in the present embodiment, in order to ensure the calculation efficiency, the grid is set to be square, and the side length of the grid is half of the width of the mulching film. The width of plastic film can set up rationally according to actual conditions. For example, before the mulching film identification method shown in fig. 1 is performed, the width of the mulching film to be identified is obtained through actual measurement, and the width is input to the flow inlet of the mulching film identification method as an initial value.
And step S130, determining a boundary value of the laser reflection intensity based on the distribution rule of the laser reflection intensity of each point in the grids, wherein the boundary value is used for indicating the maximum value of the laser reflection intensity of the non-soil-covered area of the mulching film.
After the laser radar transmits the laser beam, the intensity of the received beam is different according to the reflectivity and the distance of the object. Normalized reflection intensity can be obtained by normalizing the intensity of the light beam according to the distance information, and the laser reflection intensity mentioned herein refers to normalized reflection intensity. The normalized reflection intensity is only related to the reflectivity of the object, the reflectivity of the soil and the area without soil covering the mulch are sequentially increased, the laser reflection intensity of the soil, the area without soil covering the mulch is also sequentially increased, and the laser reflection intensity of the area without soil covering the mulch is greatly different from the laser reflection intensity of the soil and the area with soil covering the mulch. Therefore, a boundary value can be visually determined by carrying out statistical analysis on the laser reflection intensity of each point in the point cloud map, the point of which the laser reflection intensity is less than or equal to the boundary value is certainly the point of the non-soil-covered area of the mulching film, and the point of which the laser reflection intensity is greater than the boundary value is possibly the point of the soil-covered area of the mulching film or the soil point.
In step S140, a mean value of the laser reflection intensities of all the points included in each of the plurality of grids is calculated.
The number of points in different grids may be the same or different. The average of the laser reflection intensity of all points is counted for all points within the same grid.
And S150, determining all points in the grid with the mean value less than or equal to the boundary value as mulching film points corresponding to the mulching films, wherein the mulching film points comprise mulching film points corresponding to the soil covered area and non-mulching film points corresponding to the non-soil covered area. That is, when the average reflection intensity of all points in the grid is smaller than the boundary value, all points in the grid are considered to be the mulch film point cloud.
Step S160, a mulch is identified from the point cloud map based on the geographic location of the mulch point. The identified area where the mulching film point is located is the mulching film.
Subsequently, the farmland operation vehicle can take the extension direction of the mulching film as a running path to realize autonomous navigation operation.
According to the mulch identification method based on the laser radar provided by the embodiment, firstly, a point cloud map is constructed based on point cloud data of a land parcel acquired by the laser radar in real time; secondly, dividing the point cloud map into a plurality of grids; secondly, determining the maximum value of the laser reflection intensity of the non-soil covering film points corresponding to the non-soil covering area based on the distribution rule of the laser reflection intensity of each point in the grids; then, with the maximum value as a reference, all points in the grid where the average of the laser reflection intensities of the grid is larger than the maximum value are determined as the mulching film points. According to the process, on one hand, the geographical position of the mulching film in the land is quickly acquired by adopting the laser radar, and compared with a method for identifying the mulching film by using an image method, the time spent on image acquisition is saved; on the other hand, the mulching film identification process is simple in logic and easy to realize in algorithm; on the other hand, the soil covering area of the mulching film is identified by adopting a statistical method, the identified edge of the mulching film is ensured to be the real edge of the mulching film instead of the boundary between the soil covering area and the soil non-covering area, and therefore the identification precision of the mulching film is improved.
Fig. 2 is a schematic flow chart of a laser radar-based mulch identification method according to a second embodiment of the present application. As shown in fig. 2, according to the present embodiment, a mulch film identification method 200 is provided, in which the collecting direction of the lidar is the extending direction of the mulch film. Before step S120, the method further includes:
and step S210, determining a target area from the point cloud map based on the acquired acquisition direction, initial position and effective range of the laser radar and the length of the land parcel.
In this case, step S120 is specifically executed as:
step S220, the target area is divided into a plurality of grids.
In step S210, for example, fig. 3 is a schematic position diagram of the target area in the point cloud map according to an embodiment of the present application. As shown in fig. 3, the collecting direction of the laser radar is an extending direction S of the mulching film, and an included angle between the extending direction S and any coordinate axis, for example, an x axis, of the point cloud map is θ. The initial position of the lidar is p (x, y, z). The effective radius of the lidar is d. The length of the land mass is L. In this case, it can be determined that the four boundary points of the target area are a [ x-dsin θ, y + dcon θ ], B [ x + dsin θ, y-dcon θ ], C [ x + lcos θ + dsin θ, y + lsin θ -dcon θ ], and D [ x + lcos θ -dsin θ, y + lsin θ + dcon θ ], respectively, and then the target area ABCD is a rectangular area surrounded by the four boundary points.
The lidar is typically scanned around its location or over a predetermined sector. When the distance is too far away, the acquired point cloud data is too sparse, and the accuracy of the acquired data is affected. In view of this, in the embodiment, based on the effective range of the laser radar, the target area is selected from the point cloud map, which is equivalent to filtering out an area where the point cloud acquired by the laser radar is too sparse, so that the accuracy of the point cloud data is ensured.
In step S220, as shown in fig. 3, the target area ABCD is gridded from the central line along the extension direction S of the mulching film to both sides, and when the edge area m is not enough to form a complete grid, the edge area m may be discarded, or the edge area m may be compensated by using the critical area n of the point cloud map to form a complete grid. On the opposite side of the initial position p of the laser radar, when the edge area i is not enough to form a complete grid, the edge area i may be discarded, or a critical area j of the edge area i on the global point cloud map may be used for compensation to form a complete grid.
In one embodiment, the method for identifying a mulching film based on a laser radar as shown in fig. 2 further includes, before step S220, adjusting the direction of the target area so that the extending direction of the mulching film is parallel to any coordinate axis of the point cloud map S230.
For example, referring to fig. 3, the target area ABCD is rotated clockwise by θ such that the extension direction S of the mulch is parallel to the x-axis of the point cloud map. Steps S130 to S160 may be subsequently performed based on the adjusted target area (as indicated by the dashed rectangle in fig. 3).
According to the laser radar-based mulch identification method provided by the embodiment, the direction of the target area ABCD is adjusted, so that the extension direction S of the mulch is parallel to any coordinate axis of the point cloud map, and then meshing treatment can be performed on the basis of the adjusted target area. In this case, the coordinates of the grid lines are easily determined, and the calculation is simplified.
Fig. 4 is a schematic diagram illustrating an execution process of step S130 according to a first embodiment of the present application. The implementation may be applied to the mulch identification method 100 and/or the mulch identification method 200. As shown in fig. 4, step S130 specifically includes:
step S310, constructing a histogram based on the point clouds in the grids, wherein the abscissa of the histogram is the laser reflection intensity, and the ordinate is the number of points.
Fig. 5 is a histogram constructed based on point clouds in a plurality of grids according to an embodiment of the present disclosure. As shown in fig. 5, in the present embodiment, the histogram is constructed at intervals of 1 unit intensity, i.e., the abscissa of the adjacent bars differ by 1 unit intensity. As can be seen from fig. 5, taking a bar corresponding to the abscissa 10 as an example, the bar indicates that the number of points in the point cloud map with the laser reflection intensity of 10 is 78. The laser reflection intensity of the point cloud in the point cloud map is 0-45.
In step S320, a predetermined point of the histogram in the coverage area of the abscissa is determined as a boundary value of the reflection intensity.
Still taking the histogram shown in fig. 5 as an example, a predetermined point between 4 and 45 is determined as a boundary value of the reflection intensity, for example, a middle point between 0 and 45, that is, 23 is determined as a boundary value of the reflection intensity. In this case, the point having the laser reflection intensity of less than 23 is necessarily the mulching film point not covered with soil, and the point having the laser reflection intensity of greater than or equal to 23 is the mulching film point covered with soil or the soil point.
It should be understood that in other embodiments, step S120 may also be implemented by using other mathematical statistical methods, such as a statistical table.
According to the mulch identification method based on the laser radar provided by the embodiment, the histogram can be used for intuitively displaying the boundary value of the reflection intensity.
Fig. 6 is a schematic diagram illustrating an implementation process of step S130 according to a second embodiment of the present application. The implementation may be applied to the mulch identification method 100 and/or the mulch identification method 200. As shown in fig. 6, step S130 specifically includes:
in step S410, the variance of the laser reflection intensities of all the points included in each of the plurality of grids is calculated.
Step S420, filtering the variance based on a preset variance interval to filter out grids which simultaneously contain the uncovered soil film points and the soil points corresponding to the soil.
The preset variance interval is sigma e (sigma)1,σ2) Where σ is1、σ2Is a hyper-parameter. And filtering the variance by using the preset variance interval to filter out the grids which are not uniformly distributed, namely the grids which simultaneously contain the non-covered land film points and the soil points corresponding to the soil.
Step S430, a histogram is constructed based on the point clouds included in the filtered grid.
For further details, reference is made to the detailed description of the histogram illustrated in fig. 5.
In step S440, the middle point of the coverage area of the abscissa of the histogram is determined as the boundary value of the reflection intensity. For further details, reference is made to the detailed description of the histogram illustrated in fig. 5.
According to the laser radar-based mulch identification method provided by the embodiment, before the point cloud map is used for constructing the histogram, the point cloud in the point cloud map is filtered to filter out the grid with uneven distribution, so that on one hand, the calculated amount is simplified, and on the other hand, the precision of the obtained boundary value of the reflection intensity is improved.
Exemplary devices
The application also provides a plastic film recognition device based on laser radar. Fig. 7 is a block diagram of a laser radar-based mulch identification apparatus according to an embodiment of the present application. As shown in fig. 7, the mulching film recognition device 70 includes: a building module 71, a dividing module 72, a first determining module 73, a calculating module 74, a second determining module 75 and a recognition module 76. The construction module 71 is configured to construct a point cloud map based on point cloud data of a parcel acquired by a laser radar, the parcel includes soil and a mulching film laid on the soil, the mulching film includes a soil covering area and a non-soil covering area, and the point cloud data includes a geographical position of each point and a laser reflection intensity of each point. The dividing module 72 is configured to divide the point cloud map into a plurality of grids. The first determining module 73 is configured to determine a boundary value of the laser reflection intensity based on a distribution rule of the laser reflection intensities of the points in the multiple grids, where the boundary value is used to indicate a maximum value of the laser reflection intensity of an uncovered soil film point corresponding to an uncovered soil area. The calculation module 74 is configured to calculate an average value of the reflected laser intensities of all the points included in each of the plurality of grids. The second determining module 75 is configured to determine that all points in the grid with the mean value less than or equal to the boundary value are mulching film points corresponding to a mulching film, where the mulching film points include mulching film points corresponding to an earth covered area and non-mulching film points corresponding to a non-earth covered area. The identification module 76 is used to identify the mulch from the point cloud map based on the geographic location of the mulch points.
According to the mulch identification device based on the laser radar provided by the embodiment, on one hand, the laser radar is adopted to quickly acquire the geographical position of the mulch in the land, so that the time spent on image acquisition in the early stage of mulch identification is saved; on the other hand, the mulching film identification process is simple in logic and easy to realize in algorithm; on the other hand, the soil covering area of the mulching film is identified by adopting a statistical method, the identified edge of the mulching film is ensured to be the real edge of the mulching film instead of the boundary between the soil covering area and the soil non-covering area, and therefore the identification precision of the mulching film is improved.
In one embodiment, the collecting direction of the laser radar is the extending direction of the mulching film. The mulch identification device 70 further includes a third determination module configured to determine a target area from the point cloud map based on the acquired collection direction, initial position, and effective radius of the lidar, and the length of the plot. In this case, the dividing module 72 is specifically configured to divide the target area into a plurality of grids.
In one embodiment, the mulch identification device 70 further comprises an adjusting module for adjusting the direction of the target area so that the extending direction of the mulch is parallel to any coordinate axis of the point cloud map.
In one embodiment, the grid is square, and the side length of the grid is 1/2 of the width of the mulching film.
In one embodiment, the first determining module 73 is specifically configured to construct a histogram based on point clouds in a plurality of grids, an abscissa of the histogram is laser reflection intensity, and an ordinate is the number of points; and determining a predetermined point of the histogram in the coverage area of the abscissa as a boundary value of the reflection intensity.
In another embodiment, the first determining module 73 is specifically configured to calculate a variance of the laser reflection intensity of all the points included in each of the plurality of grids; filtering the variance based on a preset variance interval to filter out a grid which simultaneously contains the uncovered soil film points and the soil points corresponding to the soil; constructing a histogram based on the point cloud in the filtered grid; and determining the middle point of the coverage interval of the horizontal coordinate of the histogram as a boundary value of the reflection intensity.
The mulching film identification device based on the laser radar and the mulching film identification method based on the laser radar belong to the same application concept, can execute the mulching film identification method provided by any embodiment of the application, and has the corresponding functional modules and the beneficial effects of executing the mulching film identification method. The technical details that are not described in detail in this embodiment can be referred to the mulch identification method provided in the embodiments of the present application, and are not described herein again.
Exemplary electronic device
Fig. 8 is a block diagram of an electronic device according to an exemplary embodiment of the present application. The electronic device can be integrated on a farm work vehicle. As shown in fig. 8, the electronic device 10 includes one or more processors 11 and memory 12.
The processor 11 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.
Memory 12 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. Volatile memory can include, for example, Random Access Memory (RAM), cache memory (or the like). The non-volatile memory may include, for example, Read Only Memory (ROM), a hard disk, flash memory, and the like. One or more computer program instructions may be stored on a computer-readable storage medium and executed by processor 11 to implement the lidar-based mulch identification methods of the various embodiments of the application described above and/or other desired functionality.
In one example, the electronic device 10 may further include: an input device 13 and an output device 14, which are interconnected by a bus system and/or other form of connection mechanism (not shown).
For example, the input device 13 may be a laser radar for capturing point cloud data of a parcel. The input device 13 may also include, for example, a keyboard, a mouse, and the like.
The output device 14 can output various information including the determined position information of the mulching film and the like to the outside. Output devices 14 may include, for example, a display, speakers, a printer, and a communication network and remote output devices connected thereto, among others.
Of course, for simplicity, only some of the components of the electronic device 10 relevant to the present application are shown in fig. 8, and components such as buses, input/output interfaces, and the like are omitted. In addition, the electronic device 10 may include any other suitable components depending on the particular application.
Exemplary computer program product and computer-readable storage Medium
In addition to the above-described methods and apparatus, embodiments of the present application may also be a computer program product comprising computer program instructions that, when executed by a processor, cause the processor to perform the steps in the lidar-based mulch identification method according to various embodiments of the present application described in the "exemplary methods" section above of the specification.
The computer program product may include program code for carrying out operations for embodiments of the present application in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server.
Furthermore, embodiments of the present application may also be a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, cause the processor 11 to perform the steps in the lidar-based mulch identification method according to various embodiments of the present application described in the "exemplary methods" section above of the specification.
The computer-readable storage medium may take any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may include, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The foregoing describes the general principles of the present application in conjunction with specific embodiments, however, it is noted that the advantages, effects, etc. mentioned in the present application are merely examples and are not limiting, and they should not be considered essential to the various embodiments of the present application. Furthermore, the foregoing disclosure of specific details is for the purpose of illustration and description and is not intended to be limiting, since the foregoing disclosure is not intended to be exhaustive or to limit the disclosure to the precise details disclosed.
The block diagrams of devices, apparatuses, systems referred to in this application are only given as illustrative examples and are not intended to require or imply that the connections, arrangements, configurations, etc. must be made in the manner shown in the block diagrams. These devices, apparatuses, devices, systems may be connected, arranged, configured in any manner, as will be appreciated by those skilled in the art. Words such as "including," "comprising," "having," and the like are open-ended words that mean "including, but not limited to," and are used interchangeably therewith. The words "or" and "as used herein mean, and are used interchangeably with, the word" and/or, "unless the context clearly dictates otherwise. The word "such as" is used herein to mean, and is used interchangeably with, the phrase "such as but not limited to". It should also be noted that in the devices, apparatuses, and methods of the present application, the components or steps may be decomposed and/or recombined. These decompositions and/or recombinations are to be considered as equivalents of the present application.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the application. Thus, the present application is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description has been presented for purposes of illustration and description. Furthermore, the description is not intended to limit embodiments of the application to the form disclosed herein. While a number of example aspects and embodiments have been discussed above, those of skill in the art will recognize certain variations, modifications, alterations, additions and sub-combinations thereof.

Claims (10)

1. A mulch film identification method based on a laser radar is characterized by comprising the following steps:
constructing a point cloud map based on point cloud data of a plot acquired by a laser radar, wherein the plot comprises soil and a mulching film laid on the soil, the mulching film comprises a soil covering area and a non-soil covering area, and the point cloud data comprises the geographical positions of all points and the laser reflection intensity of all points;
dividing the point cloud map into a plurality of grids;
determining a boundary value of the laser reflection intensity based on a distribution rule of the laser reflection intensity of each point in the grids, wherein the boundary value is used for indicating the maximum value of the laser reflection intensity of the non-soil covering membrane point corresponding to the non-soil covering area;
calculating the mean value of the laser reflection intensity of all the points contained in each of the grids;
determining all points in the grid with the mean value smaller than or equal to the boundary value as mulching film points corresponding to the mulching film, wherein the mulching film points comprise mulching film points corresponding to the soil covered area and non-mulching film points corresponding to the non-soil covered area;
identifying the mulch from the point cloud map based on the geographic location of the mulch point.
2. The method for identifying a mulching film based on a laser radar as claimed in claim 1, wherein the collecting direction of the laser radar is the extending direction of the mulching film; before the dividing the point cloud map into a plurality of grids, further comprising:
determining a target area from the point cloud map based on the acquired acquisition direction, initial position and effective radius of the laser radar and the length of the land parcel;
the dividing the point cloud map into a plurality of grids comprises:
the target area is divided into a plurality of grids.
3. The lidar-based mulch identification method of claim 2, further comprising, prior to said dividing said target area into a plurality of grids:
and adjusting the direction of the target area so that the extension direction of the mulching film is parallel to any coordinate axis of the point cloud map.
4. The lidar-based mulch identification method of claim 1, wherein the grid is square, the side length of the grid being 1/2 times the width of the mulch.
5. The lidar-based geomembrane identification method according to claim 1, wherein said determining a demarcation value of the laser reflection intensity based on a distribution rule of the laser reflection intensity at each point in the plurality of meshes comprises:
constructing a histogram based on the point clouds in the grids, wherein the abscissa of the histogram is the laser reflection intensity, and the ordinate is the number of points;
and determining a predetermined point of the histogram in the coverage interval of the abscissa as a boundary value of the reflection intensity.
6. The lidar-based geomembrane identification method of claim 5, further comprising, prior to said constructing a histogram based on point clouds in said plurality of grids:
calculating a variance of the laser reflection intensity for all points included in each of the plurality of grids;
filtering the variance based on a preset variance interval to filter out a grid which simultaneously contains the non-covered land film points and the soil points corresponding to the soil;
the constructing a histogram based on point clouds in the plurality of grids comprises:
constructing the histogram based on the point clouds in the filtered mesh.
7. A lidar-based geomembrane identification method according to claim 5 or 6, wherein said determining that a predetermined point of said histogram within a coverage interval of said abscissa is a boundary value of said reflection intensity comprises:
and determining the middle point of the coverage interval of the horizontal coordinate of the histogram as a boundary value of the reflection intensity.
8. The utility model provides a plastic film recognition device based on laser radar which characterized in that includes:
the system comprises a construction module, a data acquisition module and a data processing module, wherein the construction module is used for constructing a point cloud map based on point cloud data of a land parcel acquired by a laser radar, the land parcel comprises soil and a mulching film laid on the soil, the mulching film comprises a soil covering area and a soil non-covering area, and the point cloud data comprises the geographic position of each point and the laser reflection intensity of each point;
the dividing module is used for dividing the point cloud map into a plurality of grids;
a first determining module, configured to determine a boundary value of the laser reflection intensity based on a distribution rule of the laser reflection intensity of each point in the multiple grids, where the boundary value is used to indicate a maximum value of the laser reflection intensity of an uncovered soil film point corresponding to the uncovered soil area;
a calculation module, configured to calculate a mean value of the laser reflection intensities of all the points included in each of the plurality of grids;
a second determining module, configured to determine that all points in the grid whose mean value is less than or equal to the boundary value are mulching film points corresponding to the mulching film, where the mulching film points include mulching film points corresponding to the soil covered area and non-mulching film points corresponding to the non-soil covered area;
an identification module to identify the mulch from the point cloud map based on the geographic location of the mulch point.
9. A computer device comprising a memory, a processor and a computer program stored on the memory for execution by the processor, wherein the steps of the lidar-based mulch identification method according to any one of claims 1 to 7 are implemented when the computer program is executed by the processor.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the lidar-based mulch identification method according to any one of claims 1 to 7.
CN202111620173.XA 2021-12-27 2021-12-27 Mulching film identification method and device, computer equipment and storage medium Pending CN114545436A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111620173.XA CN114545436A (en) 2021-12-27 2021-12-27 Mulching film identification method and device, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111620173.XA CN114545436A (en) 2021-12-27 2021-12-27 Mulching film identification method and device, computer equipment and storage medium

Publications (1)

Publication Number Publication Date
CN114545436A true CN114545436A (en) 2022-05-27

Family

ID=81669562

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111620173.XA Pending CN114545436A (en) 2021-12-27 2021-12-27 Mulching film identification method and device, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN114545436A (en)

Similar Documents

Publication Publication Date Title
RU2768997C1 (en) Method, device and equipment for recognition of obstacles or ground and flight control, and data carrier
US11422261B2 (en) Robot relocalization method and apparatus and robot using the same
EP3932199A1 (en) Pesticide spraying control method, apparatus, and device, and storage medium
CA2994508C (en) Vegetation management for power line corridor monitoring using computer vision
CA2994511C (en) Condition detection using image processing
US20070162193A1 (en) Accuracy enhancing system for geospatial collection value of an image sensor aboard an airborne platform and associated methods
EP1806699A1 (en) Geospatial image change detecting system with environmental enhancement and associated methods
US20180075319A1 (en) 3d building extraction apparatus, method and system
CN110135278B (en) Obstacle detection method and device and electronic equipment
US11466992B2 (en) Method, apparatus, device and medium for detecting environmental change
CN103383773A (en) Automatic ortho-rectification frame and method for dynamically extracting remote sensing satellite image of image control points
CN113761999A (en) Target detection method and device, electronic equipment and storage medium
CN115406457A (en) Driving region detection method, system, equipment and storage medium
CN111445472A (en) Laser point cloud ground segmentation method and device, computing equipment and storage medium
CN115077540A (en) Map construction method and device
CN115346183A (en) Lane line detection method, terminal and storage medium
CN114519712A (en) Point cloud data processing method and device, terminal equipment and storage medium
JP7028336B2 (en) Learning equipment, learning methods and learning programs
US11361502B2 (en) Methods and systems for obtaining aerial imagery for use in geospatial surveying
CN114545436A (en) Mulching film identification method and device, computer equipment and storage medium
CN113436336B (en) Ground point cloud segmentation method and device and automatic driving vehicle
CN115240168A (en) Perception result obtaining method and device, computer equipment and storage medium
CN110243357B (en) Unmanned aerial vehicle positioning method and device, unmanned aerial vehicle and storage medium
CN112508970A (en) Point cloud data segmentation method and device
Sihvo et al. Tree detection around forest harvester based on onboard LiDAR measurements

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