A method and device for structuring data of a threaded steel based on a laser point cloud

Abstract

The application provides a method and device for structuring thread steel data based on a laser point cloud, and the method comprises the following steps: obtaining a three-dimensional structure point cloud of thread steel; unfolding the three-dimensional structure point cloud to obtain an unfolded point cloud; generating an unfolded depth map of thread steel through the unfolded point cloud; identifying the unfolded depth map to obtain the positions of different structures in the unfolded depth map; and obtaining a plurality of groups of point clouds from the three-dimensional structure point cloud based on the positions of different structures in the unfolded depth map, wherein the structure types of each group of point clouds are the same. The technical problem of poor accuracy of structured data caused by manual measurement of thread steel data in the prior art is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of image processing, in particular to a method and device for data structuring of deformed steel bar based on laser point cloud. BACKGROUND

[0002] Deformed steel bar is a kind of steel material that must be used in medium and large construction components. In the production process of deformed steel bar, the billet is rolled by a rolling mill to become a strip close to the diameter of the finished product, and the deformed steel bar is produced by the pattern roller on the last rolling mill. China has formulated strict national standards for the quality of deformed steel bar. The outgoing steel bar must meet the national standards to be sold to the outside for the construction of various buildings and other industrial purposes. Therefore, each steel bar manufacturer is equipped with special personnel to regularly detect the quality of the produced steel bar. The quality problem of the steel bar is generally caused by equipment reasons such as misalignment of the roller and wear of the roller. Since the production process of the steel bar is continuous and the production line speed is very fast, the quality inspector cannot detect each batch of steel bar in real time, so it is possible to miss the best opportunity to solve the problem. Once a problem occurs, if it is not discovered and corrected in time, the subsequent batch of steel bar is all scrap and cannot be put on the market, which reduces the effective production capacity and consumes a large amount of resources.

[0003] Therefore, an automatic deformed steel bar quality inspection system is in actual demand for steel bar manufacturers. Several important indicators for evaluating the quality of deformed steel bar include the diameter of the steel bar, the oblique angle of the transverse rib, the height of the transverse rib, the angle between the transverse rib and the axis, the height of the longitudinal rib, the oblique angle of the longitudinal rib, the top width of the longitudinal rib, the distance between the transverse ribs, the top width of the transverse rib, and the gap between the ends of the transverse rib. Due to the assembly precision and wear degree of the mold, some structural defects also need to be detected, such as misaligned rollers and no longitudinal ribs.

[0004] It should be noted that the premise of deformed steel bar defect detection is to collect data of the steel bar and perform data structuring processing. However, in the prior art, if the data of the steel bar is to be collected and processed, the steel bar is usually measured by manual contact, and then the data measured by hand is used to position each structure on the surface of the steel bar to obtain structured data of the steel bar, which results in poor accuracy of the structured data.

[0005] Therefore, the present application is proposed. SUMMARY

[0006] The present application provides a method and device for data structuring of deformed steel bar based on laser point cloud to solve the technical problem of poor accuracy of structured data caused by manual measurement of deformed steel bar data in the prior art.

[0007] According to a first aspect of the present application, a method for structuring a laser point cloud based threaded steel data is provided, comprising: obtaining a three-dimensional structure point cloud of a threaded steel; unfolding the three-dimensional structure point cloud to obtain an unfolded point cloud; generating an unfolded depth map of the threaded steel based on the unfolded point cloud; identifying positions of different structures in the unfolded depth map; and obtaining a plurality of groups of point clouds from the three-dimensional structure point cloud based on the positions of the different structures in the unfolded depth map, wherein each group of point clouds has the same structure type.

[0008] Further, the structure type includes a threaded steel transverse rib, a threaded steel longitudinal rib, and a threaded steel surface.

[0009] Further, the unfolded depth map is a pseudo-color depth map, and generating the unfolded depth map of the threaded steel based on the unfolded point cloud includes: performing single-channel image calculation on the unfolded point cloud to obtain a threaded steel initial depth map; calculating a transverse gradient map and a longitudinal gradient map of the threaded steel initial depth map; and superimposing the threaded steel initial depth map, the transverse gradient map, and the longitudinal gradient map to obtain the pseudo-color depth map.

[0010] Further, generating the unfolded depth map of the threaded steel based on the unfolded point cloud includes: converting each point in the unfolded point cloud according to a second preset conversion relationship to obtain the unfolded depth map; and unfolding the three-dimensional structure point cloud to obtain the unfolded point cloud, including converting the three-dimensional structure point cloud according to a first preset conversion relationship to obtain the unfolded point cloud, wherein obtaining a plurality of groups of point clouds from the three-dimensional structure point cloud based on the positions of the different structures in the unfolded depth map includes:

[0011] converting the positions of the different structures in the unfolded depth map according to the second preset conversion relationship to obtain the positions of the different structures on the unfolded point cloud; grouping the point clouds on the unfolded point cloud according to the positions of the different structures on the unfolded point cloud, wherein each group of point clouds on the unfolded point cloud has the same structure type; and converting each group of point clouds on the unfolded point cloud according to the first preset conversion relationship to obtain a plurality of groups of point clouds on the three-dimensional structure point cloud.

[0012] Further, the second preset conversion relationship is a conversion relationship between the spatial position of each point cloud on the unfolded point cloud and the pixel value in the unfolded depth map, and the second preset conversion relationship is constructed by the following formula, including:

[0013]

[0014] Wherein, x is the spatial position of a point cloud in the unfolded point cloud, xmax is the maximum value of the horizontal coordinate in the unfolded point cloud, xmin is the minimum value of the horizontal coordinate in the unfolded point cloud, 255 is a preset mapping ratio, and p is the pixel value corresponding to the spatial position of the unfolded point cloud x in the unfolded depth map.

[0015] Further, the first preset relationship is constructed, including: generating a target angle based on the spatial position coordinates of each point in the three-dimensional structure point cloud; and constructing the first preset conversion relationship according to the target angle and the distance between each point and an axis in the three-dimensional structure point cloud.

[0016] Further, the method further includes: obtaining a measurement instruction of the threaded steel; determining a target measurement structure type of the threaded steel from the measurement instruction; extracting a target point cloud from the multiple groups of point clouds based on the target measurement structure type; and measuring the target point cloud according to the measurement instruction.

[0017] Further, the three-dimensional structure point cloud is a cylindrical point cloud fitted by an initial point cloud of the threaded steel, and the distance between each point and the axis in the three-dimensional structure point cloud is the radius of the cylindrical point cloud.

[0018] According to a second aspect of the present application, a device for structuring data of a threaded steel based on a laser point cloud is provided, including: an obtaining unit configured to obtain a three-dimensional structure point cloud of the threaded steel; an unfolding unit configured to unfold the three-dimensional structure point cloud to obtain an unfolded point cloud; a generating unit configured to generate an unfolded depth map of the threaded steel by using the unfolded point cloud; an identifying unit configured to identify the unfolded depth map to obtain the positions of different structures in the unfolded depth map; and a structuring unit configured to obtain multiple groups of point clouds from the three-dimensional structure point cloud based on the positions of different structures in the unfolded depth map, wherein each group of point clouds has the same structure type.

[0019] The present application provides a method and a device for structuring data of a threaded steel, which includes: obtaining a three-dimensional structure point cloud of the threaded steel; unfolding the three-dimensional structure point cloud to obtain an unfolded point cloud; generating an unfolded depth map of the threaded steel by using the unfolded point cloud; identifying the unfolded depth map to obtain the positions of different structures in the unfolded depth map; and obtaining multiple groups of point clouds from the three-dimensional structure point cloud based on the positions of different structures in the unfolded depth map, wherein each group of point clouds has the same structure type. The technical problem of poor accuracy of structured data caused by manual measurement of data of a threaded steel in the prior art is solved. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to make the above and other features and advantages of the present application more concrete, further descriptions will be made with reference to the accompanying drawings as follows. It should be understood that the specific examples given herein are intended to be illustrative only and not restrictive.

[0021] Figure 1 is a flow chart of a method for structuring data of a threaded steel based on a laser point cloud provided by the present application.

[0022] Figure 2 is a schematic diagram of a three-dimensional structure point cloud of a threaded steel provided by the present application.

[0023] Figures 3(a) to 3(b) is a schematic diagram of an unfolded point cloud under different perspectives provided by the present application.

[0024] Figure 4 is a schematic diagram of a separated part structure point cloud of a threaded steel surface point cloud provided by the present application.

[0025] Figure 5 is a result schematic diagram of segmentation of an unfolded depth map.

[0026] Figure 6 is a schematic diagram of an apparatus for structuring data of a threaded steel based on a laser point cloud provided by the present application. DETAILED DESCRIPTION

[0027] In order to make the above and other features and advantages of the present application more concrete, further descriptions will be made with reference to the accompanying drawings as follows. It should be understood that the specific examples given herein are intended to be illustrative only and not restrictive.

[0028] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. It will be apparent, however, to one of ordinary skill in the art that the present application can be practiced without the specific details. In other instances, well-known steps or operations are not described in detail in order to avoid obscuring the present application.

[0029] Embodiment One

[0030] The present application provides a method for structuring data of a threaded steel based on a laser point cloud, as shown in Figure 1 , comprising:

[0031] Step S11, obtaining a three-dimensional structure point cloud of a threaded steel.

[0032] Specifically, this solution can be implemented by a server or other data processing device. The aforementioned 3D point cloud of the rebar can be obtained by pre-capturing images of the rebar from multiple angles using multiple LiDAR sensors. Figure 2 This is a schematic diagram of the three-dimensional point cloud structure of the aforementioned rebar.

[0033] Step S13: Unfold the three-dimensional structure point cloud to obtain the unfolded point cloud.

[0034] Specifically, this solution can unfold the above three-dimensional structure to obtain a schematic diagram of the unfolded point cloud. Figures 3(a) and 3(b) are unfolded point clouds from different perspectives. The structure of all surface positions of the rebar can be seen from one perspective on the unfolded point cloud.

[0035] Optionally, this solution can follow... Figure 2 The central axis of the three-dimensional structural point cloud is used to unfold the three-dimensional structural point cloud to obtain the unfolded point cloud in Figure 3(a) and Figure 3(b).

[0036] Step S15: Generate the unfolded depth map of the rebar using the unfolded point cloud.

[0037] Specifically, this solution can generate a depth map of an unfolded point cloud. In this unfolded depth map, the pixel values ​​represent the depth (height) in space. It should be noted that the depth map is a two-dimensional image. This solution transforms the problem of classifying point cloud elements in three-dimensional space into a problem of classifying image pixels in two-dimensional space, thus reducing the dimensionality and difficulty of the classification problem.

[0038] Step S17: Identify the unfolded depth map and obtain the positions of different structures in the unfolded depth map.

[0039] Specifically, this solution can use image segmentation algorithms to identify the unfolded depth map in order to obtain the position coordinates of different structures in the unfolded depth map.

[0040] Optionally, this solution can use a fully convolutional network trained on manually labeled data to segment the unfolded depth map, with the segmentation result as follows: Figure 5 As shown, this scheme can also be segmented using other artificial intelligence methods.

[0041] Step S19: Based on the positions of different structures in the unfolded depth map, obtain multiple sets of point clouds from the three-dimensional structure point cloud, wherein each set of point clouds has the same structure type.

[0042] Specifically, after obtaining the position coordinates of different structures on the unfolded depth map, this scheme then classifies the point clouds of different types of structures from the original 3D structural point cloud based on the position coordinates of different structures determined on the unfolded depth map. Optionally, the structural types include: rebar transverse ribs, rebar longitudinal ribs, and rebar surface. In other words, through the above multiple steps, this scheme can structuralize the data of rebar transverse ribs, rebar longitudinal ribs, and rebar surface from the 3D structural point cloud of the rebar. In subsequent rebar inspection operations, workers can extract any desired point cloud from the digitized and structured multiple sets of point clouds for processing, such as measuring various structural parameters of the rebar based on the multiple sets of point clouds in the 3D structural point cloud.

[0043] It should be noted that this solution differs from existing technologies that use manual contact measurements to digitize rebar. Instead, it first obtains the three-dimensional point cloud structure of the rebar, and then generates a two-dimensional depth map from the three-dimensional point cloud structure. This transforms the problem of classifying point cloud elements in three-dimensional space into a problem of classifying image pixels in two-dimensional space, reducing the dimensionality of the problem and greatly reducing the amount of computation, while improving the accuracy and reliability of the calculation. The method of this patent can accurately extract the key structures on the surface of the rebar, providing a reliable foundation for automated quality inspection. Based on this patent, various structural parameters of the rebar can be measured very conveniently.

[0044] Optionally, the unfolded depth map can be a pseudo-color depth map, wherein step S15, generating the unfolded depth map of the rebar from the unfolded point cloud, includes:

[0045] Step S151: Perform single-channel image calculation on the unfolded point cloud to obtain the initial depth map of the rebar.

[0046] Specifically, this solution can generate a depth map from the point cloud developed through the above process, with the X-axis as the depth direction, the Z-axis as the height, and the Y-axis as the width.

[0047] Step S152: Calculate the transverse gradient map and the longitudinal gradient map of the initial depth map of the rebar.

[0048] Step S153: The initial depth map, transverse gradient map, and longitudinal gradient map of the rebar are superimposed to obtain the pseudo-color depth map.

[0049] Specifically, the initial depth map of the aforementioned rebar is a single-channel depth map. This scheme calculates the image gradients in both the horizontal and vertical directions of the single-channel depth map, and then superimposes the horizontal gradient map, depth map, and vertical gradient map as the red, green, and blue channels, respectively, to form a pseudo-color depth map. It should be noted that the pseudo-color depth map contains more prior information such as depth variations and edge strength, which helps improve the accuracy of subsequent structured processing.

[0050] Specifically, generating a unfolded depth map of the rebar from the unfolded point cloud includes: transforming each point in the unfolded point cloud according to a second preset transformation relationship to obtain the unfolded depth map; unfolding the three-dimensional structural point cloud to obtain an unfolded point cloud includes transforming the three-dimensional structural point cloud according to a first preset transformation relationship to obtain the unfolded point cloud, wherein step S19 obtains multiple sets of point clouds from the three-dimensional structural point cloud based on the positions of different structures in the unfolded depth map, including:

[0051] Step S191: The positions of different structures in the unfolded depth map are reverse-converted according to the second preset conversion relationship to obtain the positions of different structures on the unfolded point cloud.

[0052] Specifically, after obtaining the position coordinates of different structures in the unfolded depth map, this scheme can obtain the position coordinates of different structures on the unfolded point cloud by following the reverse process of "unfolding point cloud - unfolding depth map".

[0053] Step S192: Group the point cloud on the unfolded point cloud according to the position of different structures on the unfolded point cloud (divided into horizontal ribs, vertical ribs and surfaces), wherein each group of point cloud structures on the unfolded point cloud has the same structure type.

[0054] Step S193: Perform inverse transformation on each group of point clouds on the unfolded point cloud according to the first preset transformation relationship to obtain multiple groups of point clouds on the three-dimensional structure point cloud.

[0055] Specifically, after obtaining the position coordinates of different structures on the unfolded point cloud, this scheme groups the point cloud on the unfolded point cloud according to the position of the different structures on the unfolded point cloud. Each group of point cloud on the unfolded point cloud has the same structure type. Then, this scheme can obtain multiple groups of point clouds on the three-dimensional structure point cloud by following the reverse process of "three-dimensional structure point cloud - unfolded point cloud".

[0056] It should be noted that, through step S193 above, this scheme restores the original shape of the rebar from the classified point cloud, that is, completes the data structuring processing of the point cloud on the surface of the rebar, and obtains the separated structures of each part, as shown in the figure. Figure 4 As shown.

[0057] Optionally, the second preset transformation relationship is the transformation relationship between the spatial position of each point cloud in the unfolded point cloud and the pixel value in the unfolded depth map. The second preset transformation relationship is constructed through the following process:

[0058] First, scale the coordinates of each point to a range of 512*256 (establish a proportional relationship between the physical spatial location and the pixel position in the image space), and record the scaling factor and offset factor.

[0059] Then, the pixel value P corresponding to the spatial position of the unfolded point cloud x in the unfolded depth map is calculated using the following formula:

[0060]

[0061] Where x is the spatial position of a point in the unfolded point cloud, xmax is the maximum x-coordinate in the unfolded point cloud, xmin is the minimum x-coordinate in the unfolded point cloud, and 255 is the preset mapping ratio.

[0062] Optionally, constructing the first preset relationship includes:

[0063] Step S51: Generate the target angle based on the spatial coordinates of each point in the three-dimensional point cloud.

[0064] Step S52: Construct the first preset transformation relationship based on the target angle and the distance between each point and the central axis of the three-dimensional structure point cloud.

[0065] Specifically, for each point (X,Y,Z) on the three-dimensional structural point cloud, the corresponding spatial position after unfolding is (x,y,z). Steps S51 to S52 above are to establish a first preset transformation relationship between each point (X,Y,Z) on the three-dimensional structural point cloud and the corresponding spatial position (x,y,z) after unfolding.

[0066] More specifically, in the aforementioned first preset transformation relationship,

[0067] z = Z

[0068]

[0069]

[0070]

[0071] y = angle * r

[0072] Wherein, angle is the target angle, and r is the distance between each point and the central axis of the three-dimensional point cloud.

[0073] Optionally, before step S51 above, this scheme may further include: translating and rotating the cylindrical point cloud according to the 3D point cloud structure axis vector and the 3D point cloud structure center point, so that the 3D point cloud structure center point is at the coordinate origin, and the 3D point cloud structure axis coincides with the coordinate axis Z. The standardization of the 3D point cloud position is for the convenience of subsequent calculations.

[0074] Optionally, the three-dimensional structural point cloud is a cylindrical point cloud obtained by fitting the initial point cloud of the rebar, and the distance between each point and the central axis of the three-dimensional structural point cloud is the radius of the cylindrical point cloud.

[0075] It should be noted that this solution can transform the 3D structural point cloud into a cylindrical structural point cloud through cylindrical fitting, which better matches the cylindrical shape of rebar, facilitates subsequent calculations, and increases the accuracy of the calculations.

[0076] Optionally, the method further includes:

[0077] Receive the measurement command for the rebar;

[0078] The target measurement structure type for the rebar is determined from the measurement instructions;

[0079] Based on the target measurement structure type, target point clouds are extracted from multiple sets of point clouds;

[0080] The target point cloud is measured according to the measurement command.

[0081] Optionally, after structuring and classifying the rebar using this solution, the solution can extract the target point cloud from multiple point clouds according to its own needs, and then measure the target point cloud according to the measurement command.

[0082] In summary, this solution proposes a structured processing method for rebar point clouds. It involves unfolding the point cloud along its central axis to generate a depth map, transforming the three-dimensional point cloud element classification problem into a two-dimensional image pixel classification problem. This reduces the dimensionality of the problem, significantly decreases the computational load, and simultaneously improves the accuracy and reliability of the calculations. The method described in this patent can accurately extract key structures from the surface of rebar, providing a reliable foundation for automated quality inspection. Based on this patent, various structural parameters of rebar can be easily measured.

[0083] Example 2

[0084] This application also provides a device for structuring rebar data based on laser point clouds. This device can be used to execute the method described in Embodiment 1 above, in conjunction with... Figure 6 ,include:

[0085] Acquisition unit 60 is used to acquire the three-dimensional structural point cloud of the rebar.

[0086] The unfolding unit 62 is used to unfold the three-dimensional structure point cloud to obtain an unfolded point cloud.

[0087] The generation unit 64 is used to generate a depth map of the rebar through the unfolded point cloud.

[0088] The identification unit 66 is used to identify the unfolded depth map and obtain the positions of different structures in the unfolded depth map.

[0089] The structuring unit 68 is used to obtain multiple sets of point clouds from the three-dimensional structure point cloud based on the positions of different structures in the unfolded depth map, wherein each set of point clouds has the same structure type.

[0090] This solution differs from existing technologies that use manual contact measurements to digitize rebar. Instead, it first acquires the three-dimensional point cloud structure of the rebar, and then generates a two-dimensional depth map from the three-dimensional point cloud structure. This transforms the problem of classifying point cloud elements in three-dimensional space into a problem of classifying image pixels in two-dimensional space, reducing the dimensionality of the problem and greatly reducing the amount of computation, while improving the accuracy and reliability of the calculation. The method of this patent can accurately extract the key structures on the surface of the rebar, providing a reliable foundation for automated quality inspection. Based on this patent, various structural parameters of the rebar can be measured very conveniently.

[0091] It should be understood that the specific features, operations, and details described above regarding the method of the present invention can also be similarly applied to the apparatus and system of the present invention, or vice versa. Furthermore, each step of the method of the present invention described above can be performed by a corresponding component or unit of the apparatus or system of the present invention.

[0092] It should be understood that the various modules / units of the device of the present invention can be implemented entirely or partially by software, hardware, firmware, or a combination thereof. Each module / unit can be embedded in the processor of a computer device in hardware or firmware form, or can be stored in the memory of a computer device in software form for the processor to call and execute the operation of the module / unit. Each module / unit can be implemented as an independent component or module, or two or more modules / units can be implemented as a single component or module.

[0093] In one embodiment, a computer device (electronic device) is provided, including a memory and a processor. The memory stores computer instructions executable by the processor, which, when executed by the processor, instruct the processor to perform steps of the methods of embodiments of the present invention. The computer device can be broadly categorized as a server, terminal, or any other electronic device with the necessary computing and / or processing capabilities. In one embodiment, the computer device may include a processor, memory, network interface, communication interface, etc., connected via a system bus. The processor of the computer device can be used to provide the necessary computing, processing, and / or control capabilities. The memory of the computer device may include a non-volatile storage medium and internal memory. The non-volatile storage medium may store an operating system, computer programs, etc. The internal memory can provide an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface and communication interface of the computer device can be used to connect and communicate with external devices via a network. When the computer program is executed by the processor, it performs the steps of the methods of the present invention.

[0094] This invention can be implemented as a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, causes the steps of the methods of embodiments of the invention to be performed. In one embodiment, the computer program is distributed across multiple network-coupled computer devices or processors, such that the computer program is stored, accessed, and executed in a distributed manner by one or more computer devices or processors. A single method step / operation, or two or more method steps / operations, may be executed by a single computer device or processor or by two or more computer devices or processors. One or more method steps / operations may be executed by one or more computer devices or processors, and one or more other method steps / operations may be executed by one or more other computer devices or processors. One or more computer devices or processors may execute a single method step / operation, or execute two or more method steps / operations.

[0095] Those skilled in the art will understand that the method steps of this invention can be performed by a computer program instructing related hardware, such as a computer device or processor, to perform the steps of this invention when executed. Depending on the context, any references herein to memory, storage, databases, or other media may include non-volatile and / or volatile memory. Examples of non-volatile memory include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid-state drive, etc. Examples of volatile memory include random access memory (RAM), external cache memory, etc.

[0096] The technical features described above can be combined arbitrarily. Although not all possible combinations of these technical features are described, any combination of these technical features should be considered to be covered by this specification, provided that such combination does not contain contradictions.

[0097] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for structuring rebar data based on laser point clouds, characterized in that, include: Obtain the three-dimensional structural point cloud of the rebar; The three-dimensional point cloud is unfolded to obtain the unfolded point cloud; The unfolded point cloud is used to generate an unfolded depth map of the rebar. Identify the unfolded depth map to obtain the positions of different structures in the unfolded depth map; Based on the positions of different structures in the unfolded depth map, multiple sets of point clouds are obtained from the three-dimensional structure point cloud, wherein each set of point clouds has the same structure type; The process of generating a depth map of the rebar from the unfolded point cloud includes: transforming each point in the unfolded point cloud according to a second preset transformation relationship to obtain the depth map; and unfolding the three-dimensional structural point cloud to obtain an unfolded point cloud, which includes transforming the three-dimensional structural point cloud according to a first preset transformation relationship to obtain the unfolded point cloud. The second preset transformation relationship is the transformation relationship between the spatial position of each point in the unfolded point cloud and the pixel value in the unfolded depth map. The second preset transformation relationship is constructed by the following formula, including: Where x is the spatial position of a point in the unfolded point cloud, xmax is the maximum x-coordinate value in the unfolded point cloud, xmin is the minimum x-coordinate value in the unfolded point cloud, 255 is the preset mapping ratio, and p is the pixel value corresponding to the spatial position of x in the unfolded point cloud in the unfolded depth map. Constructing the first preset relationship includes: The target angle is generated based on the spatial coordinates of each point in the three-dimensional point cloud. The first preset transformation relationship is constructed based on the target angle and the distance between each point and the central axis of the three-dimensional point cloud.

2. The method for structuring rebar data based on laser point clouds according to claim 1, characterized in that, The structure types include: The transverse ribs, longitudinal ribs, and surface of the rebar.

3. The method for structuring rebar data based on laser point clouds according to claim 1, characterized in that, The unfolded depth map is a pseudo-color depth map, wherein generating the unfolded depth map of the rebar from the unfolded point cloud includes: The unfolded point cloud is used for single-channel image calculation to obtain the initial depth map of the rebar. The transverse gradient map and longitudinal gradient map of the initial depth map of the rebar were calculated; The initial depth map, transverse gradient map, and longitudinal gradient map of the rebar are superimposed to obtain the pseudo-color depth map.

4. The method for structuring rebar data based on laser point clouds according to claim 1, characterized in that, Multiple sets of point clouds are obtained from the 3D structure point cloud based on the positions of different structures in the unfolded depth map, including: The positions of different structures in the unfolded depth map are inversely transformed according to the second preset transformation relationship to obtain the positions of different structures on the unfolded point cloud. The point cloud on the unfolded point cloud is grouped according to the position of different structures on the unfolded point cloud, wherein each group of point cloud on the unfolded point cloud has the same structure type; Each group of point clouds on the unfolded point cloud is inversely transformed according to the first preset transformation relationship to obtain multiple groups of point clouds on the three-dimensional structure point cloud.

5. The method for structuring rebar data based on laser point clouds according to claim 1, characterized in that, The method further includes: Receive the measurement command for the rebar; The target measurement structure type for the rebar is determined from the measurement instructions; Based on the target measurement structure type, target point clouds are extracted from multiple sets of point clouds; The target point cloud is measured according to the measurement command.

6. The method for structuring rebar data based on laser point clouds according to claim 1, characterized in that, include: The three-dimensional structural point cloud is a cylindrical point cloud obtained by fitting the initial point cloud of the rebar, and the distance between each point and the central axis of the three-dimensional structural point cloud is the radius of the cylindrical point cloud.

7. A device for structuring rebar data based on laser point clouds, characterized in that, include: The acquisition unit is used to acquire the three-dimensional structural point cloud of the rebar. The unfolding unit is used to unfold the three-dimensional structure point cloud to obtain an unfolded point cloud; A generation unit is used to generate a depth map of the rebar from the unfolded point cloud; The identification unit is used to identify the unfolded depth map and obtain the positions of different structures in the unfolded depth map; A structured unit is used to obtain multiple sets of point clouds from the three-dimensional structured point cloud based on the positions of different structures in the unfolded depth map, wherein each set of point clouds has the same structure type. The process of generating a depth map of the rebar from the unfolded point cloud includes: transforming each point in the unfolded point cloud according to a second preset transformation relationship to obtain the depth map; and unfolding the three-dimensional structural point cloud to obtain an unfolded point cloud, which includes transforming the three-dimensional structural point cloud according to a first preset transformation relationship to obtain the unfolded point cloud. The second preset transformation relationship is the transformation relationship between the spatial position of each point in the unfolded point cloud and the pixel value in the unfolded depth map. The second preset transformation relationship is constructed by the following formula, including: Where x is the spatial position of a point in the unfolded point cloud, xmax is the maximum x-coordinate value in the unfolded point cloud, xmin is the minimum x-coordinate value in the unfolded point cloud, 255 is the preset mapping ratio, and p is the pixel value corresponding to the spatial position of x in the unfolded point cloud in the unfolded depth map. Constructing the first preset relationship includes: The target angle is generated based on the spatial coordinates of each point in the three-dimensional point cloud. The first preset transformation relationship is constructed based on the target angle and the distance between each point and the central axis of the three-dimensional point cloud.

Images