A method, device, electronic device and storage medium for extracting feature line segments for laser SLAM

Abstract

The present application relates to a method, device, electronic device and storage medium for extracting feature line segments for laser SLAM. The method for extracting feature line segments for laser SLAM includes: obtaining a first data set, performing coordinate transformation on the first data set to determine a second data set, deleting interference data in the second data set to determine a third data set, determining segmentation point data in the third data set, grouping the third data set according to the segmentation point data to determine a grouped data set, and extracting feature line segments corresponding to the grouped data set. The present application solves the problem of complex and low accuracy in extracting feature line segments from a laser radar scanning point set, and implements a simple and accurate solution for extracting feature line segments from a laser radar scanning point set.

Description

Technical Field

[0001] The present application relates to the field of laser SLAM image processing, and in particular to a method, device, electronic device and storage medium for extracting feature line segments for laser SLAM. Background Art

[0002] Simultaneous location and mapping (SLAM) technology refers to a robot equipped with specific sensors in an unknown environment. By real-time processing of sensor observation data, the robot analyzes and obtains environmental features and its own position and posture, and uses this to build an incremental map of the surrounding environment in real time and achieve self-positioning. As a key technology for autonomous navigation, SLAM is currently widely used in the unmanned driving industry and the intelligent robot industry. SLAM can be divided into two types: laser-based SLAM and vision-based SLAM. LiDAR has the advantages of high measurement accuracy, fine time and space resolution, no need to arrange scenes in advance, the ability to respond quickly to environmental changes, and the ability to fuse multiple sensors. Compared with vision-based SLAM technology, laser SLAM autonomous positioning is safer and more robust, and has become a hot topic of research at home and abroad.

[0003] In the laser SLAM navigation system, feature extraction has a great influence on the subsequent composition accuracy and positioning. In order to improve the practicality of laser SLAM technology, many scholars have made a lot of efforts in feature extraction. Although the feature points extracted by the ORB algorithm are relatively robust, they are sensitive to conditions such as fast motion and fewer texture features. Although the solution based on structural line features can improve the positioning accuracy of the robot, its parameterized method of representing structural line features cannot cope with scenes with irregular distribution of texture features. Some scholars fuse point and line features, and regard the vertical distance between line segments after reprojection as reprojection error, which reduces the impact of line segment length changes on the system, but the error rate is high during feature matching. Other scholars have improved the line feature extraction method, but it is still difficult to effectively and reliably extract and track the endpoints of line segments from continuous frames under conditions such as changes in perspective.

[0004] Currently, no effective solution has been proposed for the problem of complexity and low accuracy in extracting feature line segments from laser radar scanning points in related technologies. Summary of the invention

[0005] The embodiments of the present application provide a method, device, electronic device and storage medium for extracting feature line segments for laser SLAM, so as to at least solve the problem of complex implementation and low accuracy of extracting feature line segments from laser radar scanning points in the related art.

[0006] In a first aspect, an embodiment of the present application provides a feature line segment extraction method for laser SLAM.

[0007] In some embodiments, the method comprises the following steps:

[0008] Acquire a first data set, and perform coordinate transformation on the first data set to determine a second data set;

[0009] Deleting interference data in the second data set to determine a third data set;

[0010] Determining segmentation point data in the third data set;

[0011] According to the segmentation point data, grouping the third data set to determine a grouped data set;

[0012] Extract characteristic line segments corresponding to the grouped data set.

[0013] Further, in some embodiments, determining the segmentation point data in the third data set includes:

[0014] The third data set is {(x m ,y m )|m=1,2,…,M}, where M is a positive integer greater than 2;

[0015] According to the data in the third data set (x m ,y m ), respectively determine the first slope parameter H1, the second slope parameter H2, and the third slope parameter H3:

[0016]

[0017] When |H1-H2|>β and |H3-H1|+|H3-H2|>2β, determine the data (x m ,y m ) is the initial segmentation point data, otherwise determine the data (x m ,y m ) is the initial non-segmentation point data, where β∈(0,0.1);

[0018] In determining the data (x m ,y m ) is the initial segmentation point data or the initial non-segmentation point data, according to the data (x m ,y m ), respectively determine the fourth slope parameter 4, the fifth slope parameter 5, and the sixth slope parameter 6:

[0019]

[0020] In the data (x m ,y m ) is the initial segmentation point data, when |H4-H5|≤γ1 and |H6-H4|+|H6-H5|≤2γ1, determine the data (x m ,y m ) is the non-division point data, otherwise the data (x m ,y m ) is the segmentation point data, where γ1∈(β,0.1);

[0021] In the data (x m ,y m ) is the initial non-dividing point data, when |H4-H5|>γ2 and |H6-H4|+|H6-H5|>2γ2, determine the data (x m ,y m ) is the segmentation point data, otherwise determine the data (x m ,y m ) is the non-split point data, where γ2∈(β,0.1).

[0022] Further, in some embodiments, grouping the third data set according to the segmentation point data to determine the grouped data set includes:

[0023] Traverse the data in the third data set in sequence (x m ,y m ), obtain the adjacent segmentation point data in the third data set, and use the adjacent segmentation point data as the first and last data sets to determine the grouped data set Z s ={(x s,1 ,y s,1 ),…,(x s,ds ,y s,ds )}, where S is a positive integer and ds is a positive integer greater than 1.

[0024] Further, in some embodiments, extracting the characteristic line segments corresponding to the grouped data sets includes:

[0025] When the grouped data set Z s When the corresponding ds≤3, according to the data (x s,1 ,y s,1 ) and data (x s,ds ,y s,ds ) extract the characteristic line segment:

[0026]

[0027] Where x and y are the coordinates used to fit the characteristic line segment.

[0028] Further, in some embodiments, extracting the characteristic line segments corresponding to the grouped data sets includes:

[0029] When the grouped data set Z s When the corresponding ds>3, the first reference data (x1, y1) and the second reference data (x2, y2) are determined:

[0030]

[0031] Extract the characteristic line segment according to the first reference data (x1, y1) and the second reference data (x2, y2):

[0032]

[0033] Where x and y are the coordinates used to fit the characteristic line segment.

[0034] Further, in some embodiments, acquiring the first data set and performing coordinate transformation on the first data set to determine the second data set includes:

[0035] Get the first data set {(ρ n ,θ n )|n=1,2,…,N}, coordinate transformation is performed on the first data set by the following transformation formula to determine the second data set {(x n ,y n )|n=1,2,…,N}:

[0036]

[0037] Where N is the number of data in the first dataset, ρ n is the distance measured by the nth laser beam, θ n is the angle of the nth laser beam.

[0038] Further, in some embodiments, deleting the interference data in the second data set to determine the third data set includes:

[0039] According to the second data set {(x n ,y n )|n=1,2,…,N} in the data (x n ,y n ), determine the first distance D1, the second distance D2, and the third distance D3:

[0040]

[0041] When D1+D2>(2+α)D3, the data (x n ,y n) is interference data, delete the data (x n ,y n ), where α∈[0,1];

[0042] The second data set is traversed, all the interference data in the second data set are deleted, and the second data set after the interference data is deleted is determined as the third data set.

[0043] In a second aspect, an embodiment of the present application provides a feature line segment extraction device for laser SLAM.

[0044] In some embodiments, the device includes a data acquisition module, an interference data deletion module, a segmentation point data determination module, a grouping data set determination module and a feature line segment extraction module:

[0045] The data acquisition module is used to acquire a first data set and perform coordinate transformation on the first data set to determine a second data set;

[0046] The interference data deletion module is used to delete the interference data in the second data set to determine a third data set;

[0047] The segmentation point data determination module is used to determine the segmentation point data in the third data set;

[0048] The grouped data set determining module is used to group the third data set according to the segmentation point data to determine a grouped data set;

[0049] The feature line segment extraction module is used to extract the feature line segments corresponding to the grouped data set.

[0050] In a third aspect, an embodiment of the present application 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, the feature line segment extraction method for laser SLAM as described in the first aspect above is implemented.

[0051] In a fourth aspect, an embodiment of the present application provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the feature line segment extraction method for laser SLAM as described in the first aspect above.

[0052] Compared with the related art, the feature line segment extraction method, device, electronic device and storage medium for laser SLAM provided in the embodiments of the present application solve the problems of complex and low accuracy in extracting feature line segments from a laser radar scanning point set by filtering interference data and grouping data based on segmentation point data, and realizes a solution for simply and accurately extracting feature line segments from a laser radar scanning point set.

[0053] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0055] Figure 1 is a flow chart of a feature line segment extraction method for laser SLAM according to an embodiment of the present application;

[0056] Figure 2 It is a structural block diagram of a feature line segment extraction device for laser SLAM according to an embodiment of the present application. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application. In addition, it can also be understood that although the efforts made in this development process may be complex and lengthy, for ordinary technicians in the field related to the contents disclosed in the present application, some changes such as design, manufacturing or production based on the technical contents disclosed in the present application are only conventional technical means, and should not be understood as insufficient contents disclosed in the present application.

[0058] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0059] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantitative limitation, and may represent the singular or plural. The terms "include", "comprise", "have" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to greater than or equal to two. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships, for example, "A and / or B" can represent: A exists alone, A and B exist at the same time, and B exists alone. The terms "first", "second", "third" and the like involved in the present application are merely used to distinguish similar objects and do not represent a specific ordering of the objects.

[0060] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. Taking running on a terminal as an example, the terminal may include one or more processors (the processor may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory for storing data. Optionally, the terminal may also include a transmission device and an input and output device for a communication function. It can be understood by those of ordinary skill in the art that the above structure is only for illustration and does not limit the structure of the above terminal. For example, the terminal may also include more or fewer components than the above structure, or have a configuration different from the above structure.

[0061] The memory can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the feature line segment extraction method for laser SLAM in the embodiment of the present invention, and the processor executes various functional applications and data processing by running the computer program stored in the memory, that is, realizing the above method. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory or other non-volatile solid-state memory. In some embodiments, the memory may further include a memory remotely arranged relative to the processor, and these remote memories can be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network and a combination thereof.

[0062] The transmission device is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the terminal. In one example, the transmission device includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0063] The present application embodiment provides a method for extracting feature line segments for laser SLAM. Figure 1 is a flow chart of a feature line segment extraction method for laser SLAM according to an embodiment of the present application. Figure 1 As shown, the process includes the following steps:

[0064] Step S101 : acquiring a first data set, and performing coordinate transformation on the first data set to determine a second data set.

[0065] Among them, the first data set can be the original data obtained by laser radar scanning, and the coordinate transformation can be to transform the original data into a rectangular coordinate system to obtain a second data set based on the rectangular coordinate system, so as to facilitate further processing of the data set.

[0066] Step S102: deleting interference data in the second data set to determine a third data set.

[0067] In the second data set determined in step S101, there will be a certain amount of interference data, which needs to be eliminated through distance relationship to obtain a third data set without interference data. Subsequent steps are implemented based on the third data set to more accurately extract feature line segments and improve the accuracy of positioning and map construction.

[0068] Step S103: determining segmentation point data in the third data set.

[0069] In this embodiment, for the third data set determined in step S102, the segmentation point data is determined based on the relationship of slope, etc. The points corresponding to the above segmentation point data are the data points of the endpoints of the image that need to be segmented to form line segments.

[0070] Step S104: grouping the third data set according to the segmentation point data to determine a grouped data set.

[0071] After the segmentation point data are determined, in order to obtain the data required for fitting each line segment, the third data set needs to be grouped based on the positions where the segmentation point data appear, so as to form a grouped data set.

[0072] Step S105: extracting characteristic line segments corresponding to the grouped data set.

[0073] In this embodiment, the first and last of each grouped data set are segmentation point data, the segmentation point data correspond to the endpoints of the line segment, and the middle between the first and last segmentation point data is non-segmentation point data. Therefore, the characteristic line segment can be fitted one by one through the grouped data sets.

[0074] Through the above steps, by transforming the laser radar scan point set into a rectangular coordinate system and deleting the interference data in the data set, the segmentation point data is found based on the filtered data; further, the filtered data is grouped by the segmentation point data, and finally the feature line segments are fitted by the grouped data set. Compared with the related art, the feature line segment extraction method for laser SLAM in the embodiment of the present application is simple and convenient to implement, with high accuracy of line segment feature fitting, which simplifies the process of extracting feature line segments from the laser radar scan point set and improves accuracy.

[0075] In some embodiments, step S103 further includes:

[0076] Step S1031, the third data set is {(x m ,y m )|m=1,2,…,M}, where M is a positive integer greater than 2;

[0077] According to the data in the third data set (x m ,y m ), respectively determine the first slope parameter H1, the second slope parameter H2, and the third slope parameter H3:

[0078]

[0079] When |H1-H2|>β and |H3-H1|+|H3-H2|>2β, determine the data (x m ,y m ) is the initial segmentation point data, otherwise determine the data (x m ,y m ) is the initial non-segmentation point data, where β∈(0,0.1);

[0080] In this embodiment, the segmentation point data is preliminarily determined through slope calculation and processing, and the implementation scheme is simple and has high feasibility.

[0081] Step S1032, after determining the data (x m ,y m ) is the initial segmentation point data or the initial non-segmentation point data, according to the data (x m ,y m), respectively determine the fourth slope parameter 4, the fifth slope parameter 5, and the sixth slope parameter 6:

[0082]

[0083] In the data (x m ,y m ) is the initial segmentation point data, when |H4-H5|≤γ1 and |H6-H4|+H6-H5|≤2γ1, determine the data (x m ,y m ) is the non-division point data, otherwise the data (x m ,y m ) is the segmentation point data, where γ1∈(β,0.1);

[0084] In the data (x m ,y m ) is the initial non-segmentation point data, when |H4-H5|>γ2 and |H6-H4|+H6-H5|>2γ2, determine the data (x m ,y m ) is the segmentation point data, otherwise determine the data (x m ,y m ) is the non-split point data, where γ2∈(β,0.1).

[0085] The initial segmentation point data and the initial non-segmentation point data determined in step S1031 are further processed to obtain accurate segmentation point data, so that the extracted feature line segments are more accurate.

[0086] In some embodiments, step S104 further includes:

[0087] Step S1041, sequentially traverse the data in the third data set (x m ,y m ), obtain the adjacent segmentation point data in the third data set, and use the adjacent segmentation point data as the first and last data sets to determine the grouped data set Z s ={(x s,1 ,y s,1 ),…,(x s,ds ,y s,ds )}, where S is a positive integer and ds is a positive integer greater than 1.

[0088] In some embodiments, step S105 further includes:

[0089] Step S1051, when the grouped data set Z s When the corresponding ds≤3, according to the data (x s,1 ,y s,1) and data (x s,ds ,y s,ds ) extract the characteristic line segment:

[0090]

[0091] Where x and y are the coordinates used to fit the characteristic line segment.

[0092] In some embodiments, step S105 further includes:

[0093] Step S1052: when the grouped data set Z s When the corresponding ds>3, the first reference data (x1, y1) and the second reference data (x2, y2) are determined:

[0094]

[0095] Extract the characteristic line segment according to the first reference data (x1, y1) and the second reference data (x2, y2):

[0096]

[0097] Where x and y are the coordinates used to fit the characteristic line segment.

[0098] In some embodiments, step S101 further includes:

[0099] Step S1012, obtaining the first data set {(ρ n ,θ n )|n=1,2,…,N}, coordinate transformation is performed on the first data set by the following transformation formula to determine the second data set {(x n ,y n )|n=1,2,…,N}:

[0100]

[0101] Where N is the number of data in the first dataset, ρ n is the distance measured by the nth laser beam, θ n is the angle of the nth laser beam.

[0102] In some embodiments, step S102 further includes:

[0103] Step S1021, according to the second data set {(x n ,y n )|n=1,2,…,N} in the data (x n ,y n ), determine the first distance D1, the second distance D2, and the third distance D3:

[0104]

[0105] When D1+D2>(2+α)D3, the data (x n ,y n ) is interference data, delete the data (x n ,y n ), where α∈[0,1];

[0106] The second data set is traversed, all the interference data in the second data set are deleted, and the second data set after the interference data is deleted is determined as the third data set.

[0107] The present application also provides a feature line segment extraction device for laser SLAM, which is used to implement the above-mentioned embodiments and preferred embodiments, and will not be repeated hereafter. As used below, the terms "module", "unit", "subunit", etc. can implement a combination of software and / or hardware for a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware is also possible and conceived.

[0108] Figure 2 is a structural block diagram of a feature line segment extraction device for laser SLAM according to an embodiment of the present application, such as Figure 2 As shown, the device includes: a data acquisition module 20, an interference data deletion module 30, a segmentation point data determination module 40, a grouping data set determination module 50 and a feature line segment extraction module 60:

[0109] A data acquisition module 20, configured to acquire a first data set and perform coordinate transformation on the first data set to determine a second data set;

[0110] An interference data deletion module 30, configured to delete interference data in the second data set to determine a third data set;

[0111] A segmentation point data determination module 40, configured to determine segmentation point data in the third data set;

[0112] A grouped data set determining module 50, configured to group the third data set according to the segmentation point data to determine a grouped data set;

[0113] The feature line segment extraction module 60 is used to extract the feature line segments corresponding to the grouped data set.

[0114] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0115] This embodiment further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0116] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0117] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0118] Acquire a first data set, and perform coordinate transformation on the first data set to determine a second data set;

[0119] Deleting interference data in the second data set to determine a third data set;

[0120] Determining segmentation point data in the third data set;

[0121] According to the segmentation point data, grouping the third data set to determine a grouped data set;

[0122] Extract characteristic line segments corresponding to the grouped data set.

[0123] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0124] In addition, in combination with the feature line segment extraction method for laser SLAM in the above embodiments, the present application embodiment can provide a storage medium for implementation. The storage medium stores a computer program; when the computer program is executed by a processor, any one of the feature line segment extraction methods for laser SLAM in the above embodiments is implemented.

[0125] Those skilled in the art should understand that the technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0126] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A feature line segment extraction method for laser SLAM, characterized in that: The following steps are involved: Acquire a first data set, and perform coordinate transformation on the first data set to determine a second data set; Deleting interference data in the second data set to determine a third data set; Determine the segmentation point data in the third data set, wherein the third data set is , where M is a positive integer greater than 2; According to the data in the third data set , respectively determine the first slope parameter , the second slope parameter , the third slope parameter : when and When determining the data is the initial split point data, otherwise determine the data is the initial non-split point data, where ; In determining the data After the initial segmentation point data or the initial non-segmentation point data is obtained, according to the data , respectively determine the fourth slope parameter H4, the fifth slope parameter H5, and the sixth slope parameter H6: In the data For the initial segmentation point data, when and When the data is determined is non-split point data, otherwise determine the data is the split point data, where ; In the data For the initial non-segmentation point data, when and When the data is determined is the split point data, otherwise determine the data is the non-split point data, where ; According to the segmentation point data, grouping the third data set to determine a grouped data set; Extract characteristic line segments corresponding to the grouped data set.

2. The feature line segment extraction method for laser SLAM according to claim 1, characterized in that: The step of grouping the third data set according to the segmentation point data to determine a grouped data set comprises: Traverse the data in the third data set in sequence , obtain the adjacent segmentation point data in the third data set, use the adjacent segmentation point data as the first and last data sets, and determine them as the grouped data sets ,in is a positive integer, is a positive integer greater than 1.

3. The feature line segment extraction method for laser SLAM according to claim 2, characterized in that: The extracting the characteristic line segments corresponding to the grouped data set comprises: When the grouped data set Corresponding When, according to the data and data Extract the characteristic line segments: ， Where x and y are the coordinates used to fit the characteristic line segment.

4. The feature line segment extraction method for laser SLAM according to claim 2, characterized in that: The extracting the characteristic line segments corresponding to the grouped data set comprises: When the grouped data set Corresponding When the first reference data is determined and the second reference data : ； According to the first reference data and the second reference data Extract the characteristic line segments: , Where x and y are the coordinates used to fit the characteristic line segment.

5. The feature line segment extraction method for laser SLAM according to any one of claims 1 to 4, characterized in that: The acquiring of the first data set and performing coordinate transformation on the first data set to determine the second data set comprises: Get the first dataset , the coordinates of the first data set are transformed by the following transformation formula to determine the second data set : ， Where N is the number of data in the first dataset, is the distance measured by the nth laser beam, is the angle of the nth laser beam.

6. The feature line segment extraction method for laser SLAM according to claim 5, characterized in that: Deleting the interference data in the second data set to determine the third data set includes: According to the second data set Data in , determine the first distance , Second distance , the third distance : when When the data is determined To interfere with the data, delete the data ,in ; The second data set is traversed, all the interference data in the second data set are deleted, and the second data set after the interference data is deleted is determined as the third data set.

7. A feature line segment extraction device for laser SLAM, characterized in that: It includes data acquisition module, interference data removal module, segmentation point data determination module, grouping data set determination module and feature line segment extraction module: The data acquisition module is used to acquire a first data set and perform coordinate transformation on the first data set to determine a second data set; The interference data deletion module is used to delete the interference data in the second data set to determine a third data set; The segmentation point data determination module is used to determine the segmentation point data in the third data set, wherein the third data set is , where M is a positive integer greater than 2; According to the data in the third data set , respectively determine the first slope parameter , the second slope parameter , the third slope parameter : when and When determining the data is the initial split point data, otherwise determine the data is the initial non-split point data, where ; In determining the data After the initial segmentation point data or the initial non-segmentation point data is obtained, according to the data , respectively determine the fourth slope parameter H4, the fifth slope parameter H5, and the sixth slope parameter H6: In the data For the initial segmentation point data, when and When the data is determined is non-split point data, otherwise determine the data is the split point data, where ; In the data For the initial non-segmentation point data, when and When the data is determined is the split point data, otherwise determine the data is the non-split point data, where ; The grouping data set determination module is used to determine the third data set according to the segmentation point data. Perform grouping to determine grouped data sets; The feature line segment extraction module is used to extract the feature line segments corresponding to the grouped data set.

8. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to execute the feature line segment extraction method for laser SLAM according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program is configured to execute the feature line segment extraction method for laser SLAM according to any one of claims 1 to 6 when running.

Images