Plane parameter extraction method and device of plane point cloud and electronic equipment

Abstract

The invention provides a plane parameter extraction method and device of a plane point cloud and electronic equipment, and relates to the technical field of computers. The plane parameter extraction method of the plane point cloud comprises the following steps: acquiring a to-be-processed point cloud frame; dividing the to-be-processed point cloud frame into a plurality of block point cloud sets by using the spherical coordinate system; according to the characteristic value of each block point cloud set, identifying plane point clouds from the plurality of block point cloud sets to obtain a plurality of first plane point clouds; extracting plane parameters of the plurality of first plane point clouds; according to the method, the plane parameters of the plane point cloud can be efficiently and accurately extracted from the point cloud frame.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method, device and electronic device for extracting plane parameters of a plane point cloud. Background Art

[0002] In recent years, with the rapid development of science and technology, the robotics industry has made significant progress. Mobile robots have been widely used in many fields and have become an important part of production and life. However, with the continuous expansion and deepening of application fields, mobile robots are facing more and more complex and diverse task requirements and operating environments.

[0003] In mobile robots, the laser SLAM (Simultaneous Localization and Mapping) system is an important means of perception and positioning. It can effectively perceive the geometric information of the environment around the robot and accurately estimate the robot's posture state. There are often a large number of geometric features in the real environment, such as line segment features, plane features, curve features, surface features, etc. In addition to the commonly used point features, these geometric features can also provide additional constraints for state estimation. Especially in indoor scenes with fewer feature points and difficult to track accurately, these scenes are often rich in line and surface features. The extraction of geometric features can provide effective constraint information for the SLAM system and optimize the mapping results. However, in the current laser SLAM technology, there is still a lack of effective methods for extracting plane parameters for planar point clouds.

[0004] Therefore, how to efficiently and accurately extract the planar parameters of planar point clouds from point cloud frames is a technical problem that needs to be solved urgently. Summary of the invention

[0005] The present invention provides a method, device and electronic device for extracting plane parameters of a plane point cloud, so as to solve the defect of the prior art that there is a lack of an effective method for extracting plane parameters of a plane point cloud, so as to efficiently and accurately extract the plane parameters of a plane point cloud from a point cloud frame.

[0006] The present invention provides a method for extracting plane parameters of a plane point cloud, comprising the following steps.

[0007] Acquire a point cloud frame to be processed; divide the point cloud frame to be processed into a plurality of block point cloud sets using a spherical coordinate system; identify plane point clouds from the plurality of block point cloud sets according to the characteristic value of each of the block point cloud sets to obtain a plurality of first plane point clouds; and extract plane parameters of the plurality of first plane point clouds.

[0008] According to a method for extracting plane parameters of a plane point cloud provided by the present invention, the method also includes: merging the first plane point clouds that have both adjacent and similar relationships into the same set of adjacent similar plane point clouds to obtain multiple second plane point clouds; and extracting the plane parameters of the multiple second plane point clouds.

[0009] According to a method for extracting plane parameters of a planar point cloud provided by the present invention, the point cloud frame to be processed is divided into multiple block point cloud sets using a spherical coordinate system, including: projecting the point cloud frame to be processed onto the spherical coordinate system to obtain the spherical coordinates of each point cloud data in the point cloud frame to be processed; dividing the point cloud data with the same spherical coordinates into a block point cloud set to obtain the multiple block point cloud sets.

[0010] According to a method for extracting plane parameters of a plane point cloud provided by the present invention, the first plane point clouds that have both adjacent and similar relationships are merged into the same set of adjacent similar plane point clouds to obtain multiple second plane point clouds, including: determining a current first plane point cloud from all the first plane point clouds; for the current first plane point cloud and each adjacent first plane point cloud corresponding to the current first plane point cloud, performing the following operations: using the cosine of the plane angle between the current first plane point cloud and the adjacent first plane point cloud, and the distance between the center points of the two, determining whether the two have a similar relationship; system; in response to the existence of a similarity relationship between the current first plane point cloud and the adjacent first plane point cloud, merge the current first plane point cloud and the adjacent first plane point cloud into the same adjacent similar plane point cloud set; return to execute the step of determining the current first plane point cloud from all the first plane point clouds until all the first plane point clouds are traversed; each of the adjacent similar plane point cloud sets generated during the traversal process is used as a second plane point cloud; wherein the adjacent first plane point cloud corresponding to the current first plane point cloud is determined based on the spherical coordinates of the current first plane point cloud in the spherical coordinate system.

[0011] According to a method for extracting plane parameters of a plane point cloud provided by the present invention, the method also includes: adding a non-plane point cloud block set whose distance from the center point of the adjacent similar plane point cloud set is less than a preset threshold to the adjacent similar plane point cloud set; wherein the non-plane point cloud block set is the block point cloud set identified as a non-plane point cloud.

[0012] According to a method for extracting plane parameters of a plane point cloud provided by the present invention, the method also includes: using a global coordinate system to determine the association relationship between the second plane point cloud of the point cloud frame to be processed and the second plane point cloud of the processed point cloud frame; in response to the fact that the second plane point cloud of the point cloud frame to be processed and the second plane point cloud of the processed point cloud frame do not have an association relationship, establishing a global plane based on the second plane point cloud, and adding the global plane to a sliding window; optimizing the posture information of each point cloud frame in the sliding window by minimizing the minimum eigenvalue; and performing a mapping operation using the point cloud frame to be processed after the optimized posture.

[0013] The present invention also provides a plane parameter extraction device for a plane point cloud, comprising the following modules: a first acquisition module, used to acquire a point cloud frame to be processed; a division module, used to divide the point cloud frame to be processed into multiple block point cloud sets using a spherical coordinate system; a second acquisition module, used to identify plane point clouds from the multiple block point cloud sets according to the characteristic value of each of the block point cloud sets, to obtain multiple first plane point clouds; an extraction module, used to extract the plane parameters of the multiple first plane point clouds.

[0014] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, a method for extracting plane parameters of a plane point cloud as described above is implemented.

[0015] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for extracting plane parameters of a plane point cloud as described in any one of the above is implemented.

[0016] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method for extracting plane parameters of a plane point cloud as described above is implemented.

[0017] The plane parameter extraction method, device and electronic device of the plane point cloud provided by the present invention use a spherical coordinate system to divide the point cloud frame to be processed into a plurality of block point cloud sets, and the recognition accuracy and processing efficiency of the plane point cloud in the point cloud frame to be processed can be effectively improved by using the block point cloud sets. Then, according to the characteristic value of each block point cloud set, the first plane point cloud can be accurately identified from the point cloud frame to be processed, and the plane parameters can be extracted from the first plane point cloud efficiently and accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 This is one of the flow charts of the method for extracting plane parameters of a plane point cloud provided by the present invention.

[0020] Figure 2 This is the second flow chart of the method for extracting plane parameters of a plane point cloud provided by the present invention.

[0021] Figure 3 It is a flowchart of the method for obtaining multiple second plane point clouds provided by the present invention.

[0022] Figure 4 It is a flow chart of a method for performing a mapping operation based on a second plane point cloud provided by the present invention.

[0023] Figure 5 It is an exemplary schematic diagram of the plane feature extraction result of the second plane point cloud provided by the present invention.

[0024] Figure 6 It is an exemplary schematic diagram of the plane feature extraction result before global optimization provided by the present invention.

[0025] Figure 7 It is an exemplary schematic diagram of the plane feature extraction result after global optimization provided by the present invention.

[0026] Figure 8 It is a structural schematic diagram of a plane parameter extraction device for a plane point cloud provided by the present invention.

[0027] Fig. 9 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] Combine the following Figure 1-Figure 6 The present invention describes a method for extracting plane parameters of a plane point cloud.

[0030] Figure 1 This is one of the flow charts of the method for extracting plane parameters of a plane point cloud provided by the present invention, such as Figure 1 As shown, the method includes the following: Step 101: Obtain a point cloud frame to be processed.

[0031] In a specific implementation process, the plane parameter extraction method of the plane point cloud provided by the present invention can be executed by a self-moving device (for example, an inspection robot, etc.).

[0032] The point cloud frame to be processed is a point cloud data frame obtained by the mobile device using a sensor configured by the mobile device (for example, a radar sensor or a laser sensor). As an example only, the point cloud frame to be processed can be a point cloud frame of the current position obtained by the inspection robot using a radar.

[0033] Step 102: using a spherical coordinate system, divide the point cloud frame to be processed into a plurality of block point cloud sets.

[0034] In a specific implementation process, the point cloud frame to be processed may be projected onto a spherical coordinate system. For example, if the point cloud frame to be processed is a point cloud frame acquired by a radar sensor, the point cloud data may be projected onto a spherical coordinate system with the radar position as the sphere center.

[0035] In a specific implementation process, the spherical coordinates of each point cloud data in the point cloud frame to be processed can be obtained, and the point cloud data with the same spherical coordinates can be divided into a block point cloud set to obtain multiple block point cloud sets.

[0036] As an example only, for N Radar point cloud frame of points , for the i-th point cloud of the radar point cloud frame , first calculate the pitch angle according to the three-dimensional coordinates of the point cloud and yaw angle , the calculation formula is as follows: (1)

[0037] (2)

[0038] in: (3)

[0039] in, , as well as , respectively point clouds The coordinates on the x-axis, y-axis, and z-axis.

[0040] The pitch angle resolution and yaw angle resolution of the spherical grid are , then the point cloud The spherical coordinates of for: (4)

[0041] in, Point Cloud Spherical coordinates along the X-axis, Point Cloud Spherical coordinates along the Y-axis.

[0042] Traversing radar point cloud frames All point clouds with the same spherical coordinates are included in one set to obtain M block point cloud sets .

[0043] The embodiment provided by the present invention, due to the introduction of a spherical coordinate system, is applicable to sensors of different scanning modes for acquiring point cloud frames to be processed, thereby overcoming the defect that the commonly used feature extraction method of point cloud data can only be used for sensors of rotating scanning mode (for example, rotating laser radar).

[0044] Step 103 : According to the feature value of each block point cloud set, plane point clouds are identified from the multiple block point cloud sets to obtain multiple first plane point clouds.

[0045] During the specific implementation process, the covariance of all point cloud data in the block point cloud set can be determined; the covariance is decomposed by eigenvalue to obtain the eigenvalue of the block point cloud set; wherein the eigenvalues ​​include a first eigenvalue, a second eigenvalue and a third eigenvalue; when the ratio between the first eigenvalue and the second eigenvalue is greater than a preset threshold, the block point cloud set is identified as a planar point cloud; when the ratio between the first eigenvalue and the second eigenvalue is not greater than the preset threshold, the block point cloud set is identified as a non-planar point cloud block set.

[0046] As an example only, in order to obtain a high-precision calculation result, the point cloud set in step 102 is Select the block point cloud set whose point cloud number is greater than the preset threshold (for example, 50) and construct the covariance and decompose the eigenvalue. The block point cloud set is denoted as , the covariance of the block point cloud set can be calculated using the following formula for: (5)

[0047] (6)

[0048] in, It is the center point of the block point cloud.

[0049] Pair Covariance Perform eigenvalue decomposition to obtain the first, second, and third eigenvalues: (from small to large), and the corresponding characteristic roots ,if , is a preset threshold, the block point cloud set is marked as a plane point cloud and is used as the first plane point cloud.

[0050] Step 104: extracting plane parameters of a plurality of first plane point clouds.

[0051] After extracting the first plane point cloud from the point cloud frame to be processed, the plane parameters of the first plane point cloud can be extracted. ( j is the number of the first plane point cloud). The plane parameter π is usually expressed as a vector or set, which is used to uniquely identify a plane in three-dimensional space. It can usually be expressed using a combination of a normal vector n and a distance d (the signed distance from the plane to the origin), that is, .

[0052] Subsequently, SLAM mapping may be performed based on the plane parameters of the extracted first plane point cloud.

[0053] Figure 2 This is a second flow chart of the method for extracting plane parameters of a plane point cloud provided by the present invention. Figure 2 As shown, the method includes the following: Step 201: Obtain a point cloud frame to be processed.

[0054] For a detailed description of this step, please refer to the relevant content in step 101, which will not be repeated here.

[0055] Step 202: using a spherical coordinate system, divide the point cloud frame to be processed into a plurality of block point cloud sets.

[0056] For a detailed description of this step, please refer to the relevant content in step 102, which will not be repeated here.

[0057] Step 203 : According to the feature value of each block point cloud set, plane point clouds are identified from the multiple block point cloud sets to obtain multiple first plane point clouds.

[0058] For a detailed description of this step, please refer to the relevant content in step 103, which will not be repeated here.

[0059] Step 204: merge the first plane point clouds that have both adjacent and similar relationships into the same set of adjacent similar plane point clouds to obtain multiple second plane point clouds.

[0060] In some embodiments, in order to obtain a plane point cloud with a larger range than the first plane point cloud, and to obtain more accurate plane parameters based on a plane point cloud with a larger range, the first plane point clouds with adjacent similar relationships can be merged by plane area expansion to obtain multiple second plane point clouds.

[0061] In the specific implementation process, the first plane point clouds that have both adjacent and similar relationships can be merged into the same adjacent similar plane point cloud set in a variety of ways, which are not limited to the description of this specification.

[0062] Regarding an embodiment of merging first plane point clouds that have both adjacent and similar relationships into the same adjacent similar plane point cloud set to obtain multiple second plane point clouds, see Figure 3 The relevant content in will not be repeated here.

[0063] Step 205: extracting plane parameters of a plurality of second plane point clouds.

[0064] In the specific implementation process, the plane parameters of the second plane point cloud can be extracted ( i is the number of the second plane point cloud). The plane parameter π is usually expressed as a vector or set, which is used to uniquely determine a plane in three-dimensional space. It can usually be expressed using a combination of a normal vector n and a distance d, that is, .

[0065] For each second plane point cloud, based on all the point cloud data it contains, the covariance is constructed and the eigenvalue decomposition is performed to obtain the plane parameters of the second plane point cloud; the distances from all point clouds to the center of the second plane point cloud are solved according to the plane parameters, and point clouds with a large distance (for example, greater than 0.01 meters) are eliminated; the covariance of the remaining point clouds is calculated again and the eigenvalue decomposition is performed to obtain the plane parameters of the second plane point cloud, so as to filter out some points that are slightly farther away and obtain better plane parameters.

[0066] In the embodiment provided by the present invention, the first plane point clouds with both adjacent and similar relationships are merged into the same adjacent similar plane point cloud set, so that multiple second plane point clouds with a larger range can be accurately obtained. The plane feature extraction result of the second plane point cloud is as follows: Figure 5 As shown, the larger plane in the figure is the result of processing the point cloud of the point cloud frame to be processed using the embodiment provided by the present invention. Obviously, the plane feature has clear and rich surface features, which can provide effective constraint information for the SLAM system.

[0067] Figure 3 It is a flowchart of the method for obtaining multiple second plane point clouds provided by the present invention.

[0068] In this embodiment, the current first plane point cloud is determined from all first plane point clouds, and the following is performed for the current first plane point cloud and each adjacent first plane point cloud corresponding to the current first plane point cloud: Figure 3 The steps shown are: Step 301: Determine whether there is a similarity relationship between the current first plane point cloud and the adjacent first plane point cloud by using the cosine of the plane angle between the two and the distance between the center points of the two.

[0069] In a specific implementation process, the adjacent first plane point clouds corresponding to the current first plane point cloud are determined according to the spherical coordinates of the current first plane point cloud in the spherical coordinate system, and each first plane point cloud has at most 4 nearest neighbor planes.

[0070] Just as an example, for the current first plane point cloud And its corresponding adjacent first plane point cloud ,if and If it is already in the same adjacent similar plane set, continue to traverse the next adjacent first plane point cloud corresponding to the current first plane point cloud, otherwise determine it using the following method and Is there a similar relationship? Use the following formula to calculate and The cosine of the angle between : (7)

[0071] in, for The normal vector of for The normal vector of .

[0072] Use the following formula to calculate and The center distance between , : (8)

[0073] (9)

[0074] in, for The center point of for The center point of for The signed distance to the coordinate origin; for The signed distance to the coordinate origin.

[0075] If the above calculation result satisfies the following conditions: γ is not greater than the first preset threshold (for example, ), is not greater than a second preset threshold (for example, ), is not greater than a third preset threshold, (for example, ). and There is a similar relationship between them.

[0076] If confirmed and If there is no similarity relationship between the two plane point clouds, the next adjacent plane point cloud of the current first plane point cloud is traversed, and step 301 is continued until all adjacent plane point clouds of the current first plane point cloud are traversed.

[0077] If confirmed and There is a similar relationship between them, perform the following steps.

[0078] Step 302: In response to the existence of a similarity relationship between the current first plane point cloud and the adjacent first plane point cloud, the current first plane point cloud and the adjacent first plane point cloud are merged into the same adjacent similar plane point cloud set.

[0079] As an example only, the current first plane point cloud can be converted into And the adjacent first plane point cloud Merge into the same adjacent similar plane point cloud set.

[0080] if and are not in the adjacent similar plane set, then a new adjacent similar plane set is constructed containing and ; If only In the set of adjacent similar planes, join in In the adjacent similar plane set; if and If both are in the adjacent similar plane set, then the one with the smaller number of planes in the adjacent similar plane set is merged into the one with the larger number; if only In the set of adjacent similar planes, join in The adjacent similar plane set.

[0081] Will and It is marked that an adjacent similar plane set already exists, and the indexes of the adjacent similar plane sets to which the two belong are updated.

[0082] After executing the above steps for the current first plane point cloud and each of its corresponding adjacent first plane point clouds, continue to select the next first plane point cloud to be traversed from all the first plane point clouds, and execute the same processing steps (i.e., steps 301 and 302) for the first plane point cloud and each of its corresponding adjacent first plane points until all the first plane point clouds have been traversed.

[0083] Each set of adjacent similar plane point clouds generated during the traversal process is taken as a second plane point cloud.

[0084] In some embodiments, in order to obtain a second planar point cloud with a larger range, a non-planar point cloud block set whose distance from the center point of the adjacent similar planar point cloud set is less than a preset threshold can be added to the adjacent similar planar point cloud set. The non-planar point cloud block set is a block point cloud set identified as a non-planar point cloud in step 103.

[0085] Just as an example, For the non-planar point cloud block set adjacent to the current first planar point cloud, you can use the following method to convert join in The adjacent similar plane point cloud is located in the set.

[0086] if If it already exists in the adjacent similar plane set, then directly Add the non-planar point cloud block set corresponding to the adjacent similar plane set, otherwise create a new one containing only The non-planar point cloud block set, in When adding an adjacent similar plane set, the newly created non-plane point cloud block set is simultaneously merged into the non-plane point cloud block set corresponding to the adjacent similar plane set. And the adjacent first plane point cloud In the process of merging into the same adjacent similar plane point cloud set, the The non-planar point cloud block set is merged into The non-planar point cloud block set corresponding to the adjacent similar plane set is as follows: if and are not in the adjacent similar plane set, then a new adjacent similar plane set is constructed containing and , and will also include The non-planar point cloud block set is used as the non-planar point cloud block set corresponding to the new adjacent similar plane set; if only In the set of adjacent similar planes, join in The adjacent similar plane set will contain The non-planar point cloud block set is added In the non-planar point cloud block set corresponding to the adjacent similar plane set; if and If all of them are in the adjacent similar plane set, the one with the smaller number of planes in the adjacent similar plane set will be merged into the one with the larger number, and the corresponding non-planar point cloud block set will be merged at the same time; if only In the set of adjacent similar planes, join in The adjacent similar planes are collected and updated Non-planar point cloud block set.

[0087] In the embodiment provided by the present invention, all first plane point clouds are traversed, and the first plane point clouds with adjacent similar relationships are merged into the second plane point cloud using the adjacent similar plane point cloud set, so that a larger plane point cloud can be accurately obtained.

[0088] Figure 4 is a flow chart of a method for performing a mapping operation based on a second plane point cloud provided by the present invention, such as Figure 4 As shown, the method includes the following: Step 401: using the global coordinate system, determine the association relationship between the second plane point cloud of the point cloud frame to be processed and the second plane point cloud of the processed point cloud frame.

[0089] In a specific implementation process, the embodiment provided by the present invention can be used to process each point cloud frame acquired from a mobile device to obtain a second plane point cloud of each point cloud frame.

[0090] For the initial point cloud frame, a global coordinate system can be established based on the point cloud frame, each second plane point cloud of the point cloud frame can be converted into a global plane, and the center point of the global plane, the parameters of the global plane and the index of the global plane in all generated global planes can be recorded. Then, the information of these global planes is added to the octree and the initial point cloud frame is added to the sliding window.

[0091] When the point cloud frame to be processed arrives, each second plane point cloud of the point cloud frame to be processed is traversed, the second plane point cloud of the point cloud frame to be processed is projected onto the established global coordinate system, and the global plane of the processed point cloud frame with the nearest center point is found with the help of the octree. According to the similarity between the parameters of the second plane point cloud of the point cloud frame to be processed and the parameters of the global plane of the processed point cloud frame, it is determined whether there is a correlation between the two.

[0092] As an example only, the parameters of the second plane point cloud of the point cloud frame to be processed are , the parameters of the global plane of the processed point cloud frame are , if satisfied , it is determined that there is an association relationship between the two, that is, the second plane point cloud of the point cloud frame to be processed belongs to the global plane of the processed point cloud frame, and the association relationship is recorded for subsequent processing. Otherwise, it is determined that there is no association relationship between the two.

[0093] Step 402: In response to the fact that the second plane point cloud of the point cloud frame to be processed has no association relationship with the second plane point cloud of the processed point cloud frame, a global plane is established according to the second plane point cloud, and the global plane is added to the sliding window.

[0094] When it is determined that the second plane point cloud of the point cloud frame to be processed has no association with the second plane point cloud of the processed point cloud frame, a global plane is established according to the second plane point cloud, and then the information of the global plane is added to the octree and the global plane is added to the sliding window.

[0095] Step 403: Optimize the position and posture information of each point cloud frame in the sliding window by minimizing the minimum eigenvalue.

[0096] When the number of global planes contained in the sliding window is greater than 1, a covariance matrix is ​​constructed based on the point cloud data contained in all global planes in the sliding window and their corresponding pose information. Subsequently, the covariance matrix is ​​subjected to eigenvalue decomposition to obtain the minimum eigenvalue. By minimizing the minimum eigenvalue, the pose information of each point cloud frame in the sliding window is optimized. After the optimization is completed, if the length of the sliding window is greater than the preset threshold, the earliest point cloud frame added to the sliding window is marginalized.

[0097] Step 404: Perform a mapping operation using the point cloud frame to be processed after the pose is optimized.

[0098] During the sliding window optimization process, key frames can be retained according to the change of pose, and the first point cloud frame is automatically regarded as a key frame. Whenever a new key frame is added, the pose information of the key frame and the parameters of the global plane can be adjusted through global optimization to ensure accuracy. Subsequently, the pose information of all point cloud frames is updated and a map is built based on this information.

[0099] During the SLAM initialization process, when the second frame of point cloud data is received, a pose optimization operation is performed to obtain the accurate pose information of the new frame. After that, for each new frame of data, the relative pose information between the previous two frames is used to preliminarily estimate the pose of the new frame for subsequent mapping processing and analysis.

[0100] In the embodiment provided by the present invention, the global coordinate system can ensure that the point cloud data between different point cloud frames are processed under a unified spatial reference, thereby improving the accuracy of point cloud registration. Global optimization in the sliding window can adjust the pose information of the key frame so that the entire point cloud map remains consistent in the global scope. At the same time, the sliding window is used to limit the number of point cloud frames involved in the optimization to reduce the computational complexity. The plane feature extraction results before and after global optimization are shown in Figure 2. Figure 6 and Figure 7 As shown in the figure, it is obvious that the surface features after global optimization are clearer and have a larger range, which can provide more effective constraint information for the SLAM system.

[0101] The plane parameter extraction device of the plane point cloud provided by the present invention is described below. The plane parameter extraction device of the plane point cloud described below and the plane parameter extraction method of the plane point cloud described above can be referred to each other.

[0102] Figure 8 Schematic diagram of the structure of the device for extracting plane parameters of a plane point cloud provided by the present invention. Figure 8 As shown, the device 800 includes the following modules.

[0103] The first acquisition module 810 is used to acquire a point cloud frame to be processed.

[0104] The division module 820 is used to divide the point cloud frame to be processed into a plurality of block point cloud sets using a spherical coordinate system.

[0105] The second acquisition module 830 is used to identify a plane point cloud from the multiple block point cloud sets according to the feature value of each of the block point cloud sets, so as to obtain multiple first plane point clouds.

[0106] The extraction module 840 is used to extract plane parameters of the plurality of first plane point clouds.

[0107] Fig. 9 An example of a physical structure diagram of an electronic device is shown in FIG. Fig. 9As shown, the electronic device may include: a processor 910, a communication interface 920, a memory 930 and a communication bus 940, wherein the processor 910, the communication interface 920 and the memory 930 communicate with each other through the communication bus 940. The processor 910 may call the logic instructions in the memory 930 to execute the plane parameter extraction method of the plane point cloud, the method comprising: obtaining a point cloud frame to be processed; using a spherical coordinate system, dividing the point cloud frame to be processed into a plurality of block point cloud sets; according to the characteristic value of each of the block point cloud sets, identifying a plane point cloud from the plurality of block point cloud sets to obtain a plurality of first plane point clouds; extracting the plane parameters of the plurality of first plane point clouds.

[0108] In addition, the logic instructions in the above-mentioned memory 930 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0109] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the plane parameter extraction method of the plane point cloud provided by the above-mentioned methods, and the method includes: obtaining a point cloud frame to be processed; using a spherical coordinate system, dividing the point cloud frame to be processed into multiple block point cloud sets; according to the characteristic value of each of the block point cloud sets, identifying plane point clouds from the multiple block point cloud sets to obtain multiple first plane point clouds; extracting the plane parameters of the multiple first plane point clouds.

[0110] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it is implemented to execute the plane parameter extraction method of the plane point cloud provided by the above-mentioned methods, the method comprising: obtaining a point cloud frame to be processed; using a spherical coordinate system, dividing the point cloud frame to be processed into a plurality of block point cloud sets; identifying a plane point cloud from the plurality of block point cloud sets according to the characteristic value of each of the block point cloud sets to obtain a plurality of first plane point clouds; and extracting the plane parameters of the plurality of first plane point clouds.

[0111] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0112] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0113] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for extracting plane parameters of a plane point cloud, characterized in that: include: Get the point cloud frame to be processed; Using a spherical coordinate system, dividing the point cloud frame to be processed into a plurality of block point cloud sets; Identifying a plane point cloud from the plurality of block point cloud sets according to the feature value of each of the block point cloud sets to obtain a plurality of first plane point clouds; Extracting plane parameters of the plurality of first plane point clouds.

2. The method for extracting plane parameters of a plane point cloud according to claim 1, characterized in that: The method further comprises: Merging the first plane point clouds that have both adjacent and similar relationships into the same set of adjacent and similar plane point clouds to obtain a plurality of second plane point clouds; Extracting plane parameters of the plurality of second plane point clouds.

3. The method for extracting plane parameters of a plane point cloud according to any one of claims 1 or 2, characterized in that: The method of dividing the point cloud frame to be processed into a plurality of block point cloud sets by using a spherical coordinate system includes: Projecting the point cloud frame to be processed onto the spherical coordinate system to obtain the spherical coordinates of each point cloud data in the point cloud frame to be processed; The point cloud data with the same spherical coordinates are divided into a block point cloud set to obtain the multiple block point cloud sets.

4. The method for extracting plane parameters of a plane point cloud according to claim 2, characterized in that: The step of merging the first plane point clouds that have both adjacent and similar relationships into the same set of adjacent and similar plane point clouds to obtain a plurality of second plane point clouds includes: Determine a current first plane point cloud from all of the first plane point clouds; For the current first plane point cloud and each adjacent first plane point cloud corresponding to the current first plane point cloud, perform the following operations: Determine whether there is a similarity relationship between the current first plane point cloud and the adjacent first plane point cloud by using the cosine of the plane angle between the two and the distance between the center points of the two; In response to a similarity relationship between the current first plane point cloud and the adjacent first plane point cloud, merging the current first plane point cloud and the adjacent first plane point cloud into the same adjacent similar plane point cloud set; Returning to the step of determining the current first plane point cloud from all the first plane point clouds until all the first plane point clouds are traversed; Taking each of the adjacent similar plane point cloud sets generated during the traversal process as a second plane point cloud; The adjacent first plane point cloud corresponding to the current first plane point cloud is determined according to the spherical coordinates of the current first plane point cloud in the spherical coordinate system.

5. The method for extracting plane parameters of a plane point cloud according to claim 4, characterized in that: The method further comprises: A non-planar point cloud block set whose distance from the center point of the adjacent similar planar point cloud set is less than a preset threshold is added to the adjacent similar planar point cloud set; wherein the non-planar point cloud block set is the block point cloud set identified as a non-planar point cloud.

6. The method for extracting plane parameters of a plane point cloud according to claim 2, characterized in that: The method further comprises: Determine the association relationship between the second plane point cloud of the point cloud frame to be processed and the second plane point cloud of the processed point cloud frame by using the global coordinate system; In response to the second plane point cloud of the to-be-processed point cloud frame not having an association relationship with the second plane point cloud of the processed point cloud frame, establishing a global plane according to the second plane point cloud, and adding the global plane to the sliding window; Optimizing the pose information of each point cloud frame in the sliding window by minimizing the minimum eigenvalue; The mapping operation is performed using the point cloud frame to be processed after the pose is optimized.

7. A device for extracting plane parameters of a plane point cloud, characterized in that: include: A first acquisition module, used to acquire a point cloud frame to be processed; A division module, used for dividing the point cloud frame to be processed into a plurality of block point cloud sets using a spherical coordinate system; A second acquisition module is used to identify a plane point cloud from the multiple block point cloud sets according to the feature value of each of the block point cloud sets, so as to obtain multiple first plane point clouds; An extraction module is used to extract plane parameters of the plurality of first plane point clouds.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for extracting plane parameters of a planar point cloud as claimed in any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for extracting plane parameters of a planar point cloud as claimed in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for extracting plane parameters of a planar point cloud as claimed in any one of claims 1 to 6 is implemented.

Images