Wall construction detection method and device based on laser point cloud and electronic equipment

Abstract

The embodiment of the invention discloses a wall construction detection method and device based on laser point cloud and electronic equipment. A specific embodiment of the method comprises the steps of obtaining point cloud data of a to-be-decorated indoor space scanned by a laser radar; performing point cloud segmentation on the point cloud data to obtain segmented point cloud data; determining the point cloud in each segmentation area corresponding to the wall surface category in the segmentation point cloud data as wall surface point cloud data; performing wall surface information detection on each piece of wall surface point cloud data to obtain wall surface information; according to the wall surface information, performing wall surface decoration process identification on each piece of wall surface point cloud data in the wall surface point cloud data set to obtain indoor decoration process information; determining corresponding indoor construction information according to the indoor decoration process information; and based on a preset construction platform, transmitting the decoration design information, the decoration material information and the construction detail information to a target port so as to transport indoor construction materials. According to the embodiment, waste of manpower, time and building materials can be reduced.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to three-dimensional laser scanning and wall construction detection, and specifically to a wall construction detection method, device and electronic equipment based on laser point cloud. Background Art

[0002] Wall leveling is an important step in building decoration. Different wall conditions correspond to different wall leveling processes. At present, when testing the wall leveling process, the usual method is: manual measurement and judgment, using measuring tools such as tape measures and level rulers to measure various data of the wall, and selecting the corresponding leveling process based on the measured data and personal experience.

[0003] However, when the above method is used to detect the wall leveling process, technical problems often exist. Manual measurement takes a long time, and the efficiency is low when measuring walls with larger areas. In addition, the measurement accuracy is easily limited by the accuracy of the tools and the experience and skill level of the operators. Secondly, it is difficult to ensure the consistency and accuracy of the judgment results when people make subjective judgments on the leveling process, which will lead to the consumption of manpower, time and building materials.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure concept and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art. Summary of the invention

[0005] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0006] Some embodiments of the present disclosure propose a wall construction detection method, device and electronic device based on laser point cloud to solve one or more of the technical problems mentioned in the above background technology section.

[0007] In a first aspect, some embodiments of the present disclosure provide a wall construction detection method based on laser point cloud, the method comprising: obtaining point cloud data of a room to be decorated scanned by a laser radar; performing point cloud segmentation on the point cloud data to obtain segmented point cloud data, wherein the segmented point cloud data includes a plurality of segmented areas, and one segmented area corresponds to one segmented category; determining the point cloud in each segmented area corresponding to the wall category in the segmented point cloud data as wall point cloud data to obtain a wall point cloud data set; performing wall information detection on each wall point cloud data in the wall point cloud data set to obtain wall information, wherein the wall information includes wall information. A flatness information set, a wall verticality information set and indoor squareness information; based on the above wall information, the wall decoration process is identified for each wall point cloud data in the above wall point cloud data set to obtain indoor decoration process information; based on the above indoor decoration process information, the corresponding indoor construction information is determined, wherein the above indoor construction information includes decoration design information, decoration material information and construction detail information; based on a preset construction platform, the decoration design information, decoration material information and construction detail information are transmitted to a target port to transport indoor construction materials, wherein the above target port includes a design department port, a procurement department port or an engineering department port.

[0008] In a second aspect, some embodiments of the present disclosure provide a wall construction detection device based on laser point cloud, the device comprising: an acquisition unit, configured to acquire point cloud data of a room to be decorated scanned by a laser radar; a point cloud segmentation unit, configured to perform point cloud segmentation on the point cloud data to obtain segmented point cloud data, wherein the segmented point cloud data contains a plurality of segmented areas, one segmented area corresponding to one segmented category; a first determination unit, configured to determine the point cloud in each segmented area corresponding to the wall category in the segmented point cloud data as wall point cloud data to obtain a wall point cloud data set; a wall information detection unit, configured to perform wall information detection on each wall point cloud data in the wall point cloud data set to obtain wall information, wherein the wall information It includes a wall flatness information set, a wall verticality information set and indoor squareness information; a wall decoration process identification unit is configured to identify the wall decoration process for each wall point cloud data in the above wall point cloud data set according to the above wall information, so as to obtain indoor decoration process information; a second determination unit is configured to determine the corresponding indoor construction information according to the above indoor decoration process information, wherein the above indoor construction information includes decoration design information, decoration material information and construction detail information; a transmission unit is configured to transmit the above decoration design information, decoration material information and construction detail information to a target port based on a preset construction platform, so as to transport indoor construction materials, wherein the above target port includes a design department port, a procurement department port or an engineering department port.

[0009] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner of the above-mentioned first aspect.

[0010] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner of the above-mentioned first aspect is implemented.

[0011] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the wall construction detection method based on laser point cloud of some embodiments of the present disclosure, the consumption of manpower, time and building materials can be reduced. Specifically, the reasons for the consumption of manpower, time and building materials are: manual measurement takes a long time, the efficiency is low when measuring walls with larger areas, and the measurement accuracy is easily limited by the accuracy of the tool and the experience and skill level of the operator. Secondly, it is difficult to ensure the consistency and accuracy of the judgment results when the human subjectively judges the leveling process, which will lead to the consumption of manpower, time and building materials. Based on this, the wall construction detection method based on laser point cloud of some embodiments of the present disclosure first obtains the point cloud data of the interior to be decorated scanned by laser radar. By replacing the traditional manual measurement method with laser radar scanning technology, the three-dimensional point cloud data of the interior to be decorated can be quickly obtained, which shortens the time of data collection and reduces the impact of different operator skill levels. Secondly, the point cloud data is segmented to obtain segmented point cloud data. Among them, the segmented point cloud data contains multiple segmented areas, and one segmented area corresponds to a segmentation category. Therefore, the above-mentioned complex indoor environment can be segmented into multiple segmented areas that are easy to manage through automated segmentation processing. Afterwards, the point cloud in each segmented area corresponding to the wall category in the segmented point cloud data is determined as the wall point cloud data to obtain the wall point cloud data set. Thus, the point cloud data representing only the wall can be obtained from the original point cloud data. Subsequently, the wall information is detected for each wall point cloud data in the wall point cloud data set to obtain the wall information. Among them, the wall information includes a wall flatness information set, a wall verticality information set and indoor squareness information. Compared with manual judgment, the wall information detection scheme for flatness, verticality and squareness can provide more objective and consistent results, and can also find subtle irregularities and reduce the waste of building materials. Then, according to the wall information, the wall decoration process is identified for each wall point cloud data in the wall point cloud data set to obtain indoor decoration process information. Thus, the deviation caused by human evaluation of the decoration process can be avoided, which is helpful to formulate a more accurate leveling plan. Then, according to the indoor decoration process information, the corresponding indoor construction information is determined. Among them, the indoor construction information includes decoration design information, decoration material information, and construction detail information. In this way, the specific construction details of the interior to be decorated can be accurately obtained. Finally, based on the preset construction platform, the above-mentioned decoration design information, decoration material information and construction details information are transmitted to the target port to transport indoor construction materials. Among them, the above-mentioned target port includes the design department port, the procurement department port or the engineering department port. The indoor construction information is transmitted to each port through the construction platform, which is convenient for each department to prepare construction materials and understand the corresponding construction details in advance. In this way, rework can be reduced, thereby reducing the waste of manpower, time and construction materials. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0013] Figure 1 is a flow chart of some embodiments of the wall construction detection method based on laser point cloud according to the present disclosure;

[0014] Figure 2 It is a structural schematic diagram of some embodiments of the wall construction detection device based on laser point cloud according to the present disclosure;

[0015] Figure 3 is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure;

[0016] Figure 4 is a point cloud lightweight comparison diagram of some embodiments of the wall construction detection method based on laser point cloud according to the present disclosure;

[0017] Figure 5 It is a point cloud segmentation effect diagram according to some embodiments of the wall construction detection method based on laser point cloud disclosed in the present invention;

[0018] Figure 6 is a visualization diagram of flatness detection according to some embodiments of the wall construction detection method based on laser point cloud disclosed in the present invention;

[0019] Figure 7 It is an example diagram of wall leveling according to some embodiments of the wall construction detection method based on laser point cloud disclosed in the present invention. DETAILED DESCRIPTION

[0020] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0021] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0022] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0023] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0024] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0025] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0026] Figure 1 The process 100 of some embodiments of the wall construction detection method based on laser point cloud according to the present disclosure is shown. The wall construction detection method based on laser point cloud includes the following steps:

[0027] Step 101, obtaining point cloud data of the interior to be decorated scanned by a laser radar.

[0028] In some embodiments, the execution subject of the wall construction detection method can obtain point cloud data of the interior to be decorated scanned by a laser radar. The interior to be decorated can be scanned by a laser radar to obtain point cloud data. The above point cloud data contains multiple points, each of which is a coordinate point in three-dimensional space obtained by scanning the laser radar.

[0029] Step 102, performing point cloud segmentation on the point cloud data to obtain segmented point cloud data.

[0030] In some embodiments, the execution entity may perform point cloud segmentation on the point cloud data to obtain segmented point cloud data.

[0031] In some optional implementations of some embodiments, the execution subject performs point cloud segmentation on the point cloud data to obtain segmented point cloud data, which may include the following steps:

[0032] The first step is to perform lightweight processing on the point cloud data to obtain lightweight point cloud data. The point cloud data can be lightweight processed by a preset point cloud sampling algorithm to obtain lightweight point cloud data.

[0033] As an example, the point cloud sampling algorithm may include but is not limited to at least one of the following: a K-means clustering sampling algorithm, a voxel-based sampling algorithm, and the like.

[0034] In practice, point cloud data obtained by point cloud scanning of indoor or large building scenes often contains tens of millions of points. Too large a number of point clouds will lead to high computational complexity, resulting in a waste of computing resources. Therefore, it is necessary to perform lightweight processing on the point cloud data obtained by LiDAR scanning. When the above-mentioned point cloud sampling algorithm is used to perform lightweight processing on the original point cloud data, the points in the original point cloud data are often replaced by clustering or dividing the voxel center, which will change the coordinates of the initial points and cause the geometric features of the object surface to change, resulting in the point cloud data not being able to accurately reflect the actual situation of the wall. Therefore, the following scheme can be used to perform lightweight processing on the point cloud data.

[0035] Optionally, the execution subject performs lightweight processing on the point cloud data to obtain lightweight point cloud data, which may include the following steps:

[0036] In the first sub-step, neighbor point retrieval is performed on each point in the point cloud data to generate a neighbor point list, and a neighbor point list set is obtained. Among them, a preset neighbor point retrieval algorithm can be used to perform neighbor point retrieval on each point in the point cloud data to generate a neighbor point list, and a neighbor point list set is obtained. Secondly, the neighbor point list is a list composed of each neighbor point of a point in the point cloud data. The neighbor point list set is a collection of neighbor point lists of each point in the point cloud data.

[0037] As an example, the neighbor point retrieval algorithm includes but is not limited to at least one of the following: KD-Tree algorithm, OcTree algorithm, etc.

[0038] The second sub-step is to determine the relative weight between each point in the point cloud data and the corresponding neighbor point according to the neighbor point list set to obtain a relative weight set. First, the distance value between the two points can be determined as the corresponding weight to obtain a weight set. Secondly, when the distance between the two points is greater than the preset distance threshold, the weight value between the two points can be set to 0. Here, the distance between each point and its corresponding neighbor point can be determined by the Euclidean distance formula. The preset distance threshold can be 3cm. Finally, the weights in the weight set can be normalized to obtain a relative weight set. Each relative weight in the relative weight set can be used to characterize the relative importance between two points in the point cloud data.

[0039] The third sub-step is to determine the weighted adjacency matrix corresponding to the point cloud data according to the relative weight set. The weighted adjacency matrix is ​​a square matrix with the same number of rows and columns, and the number of rows and columns is the same as the number of point clouds in the point cloud data. Here, the value of the relative weight can be determined as the tuple value of the corresponding position of the weighted adjacency matrix according to the sequence number of the two points corresponding to the relative weight, and the weighted adjacency matrix is ​​obtained.

[0040] In practice, the weight adjacency matrix can be stored in the form of a sparse matrix to reduce the consumption of storage resources.

[0041] The fourth sub-step is to determine the filter matrix corresponding to the weighted adjacency matrix, wherein the filter matrix can be determined as the matrix difference between the weighted adjacency matrix and the corresponding identity matrix.

[0042] The fifth sub-step is to perform the following steps on each point in the point cloud data according to the filter matrix to generate a local importance value and obtain a local importance value set:

[0043] Sub-step 1, according to the above-mentioned neighbor point list set and the above-mentioned filter matrix, determine the filter weight between the above-mentioned point and each neighbor point in the corresponding neighbor point list to obtain a filter weight set. Among them, the corresponding filter weight in the above-mentioned filter matrix can be determined according to the sequence number of the above-mentioned point and its neighbor point. For example, for the i-th point, the sequence number of its neighbor point is j, and the element value of the i-th row and j-th column in the above-mentioned filter matrix can be determined as the filter weight between the i point and the j point. The number of filter weights in the above-mentioned filter weight set is the same as the number of neighbor points in the neighbor point list.

[0044] Sub-step 2, the product between each filter weight in the above filter weight set and the corresponding neighbor point is determined as the filter neighbor point, and the filter neighbor point set is obtained. Among them, first, the coordinates of the neighbor point can be used as a three-dimensional vector used to characterize the neighbor point to obtain the neighbor point vector. Secondly, the product between the above filter weight and the corresponding neighbor point vector can be determined as the filter neighbor point.

[0045] Sub-step three: determining the sum of each filtering neighbor point in the above filtering neighbor point set as the central neighbor point. Wherein, each filtering neighbor point in the above filtering neighbor point set can be a three-dimensional vector.

[0046] Sub-step 4: Determine the distance between the above point and the central neighbor point as the local importance value of the above point. First, the distance value between the above point and the central neighbor point can be determined according to the Euclidean distance formula. Then, the above distance value can be determined as the local importance value corresponding to the above point.

[0047] The sixth sub-step is to sample each local importance value in the above-mentioned local importance value set according to a preset sampling rate to obtain a sampled local importance value set. Among them, the above-mentioned local importance values ​​can be sorted first to obtain a sorted local importance value set. Afterwards, the first n sorted local importance values ​​with the highest corresponding values ​​in the above-mentioned sorted local importance value set can be determined as sampled local importance values ​​according to the preset sampling rate to obtain a sampled local importance value set. The above-mentioned sampling rate can be 30% of the number of point clouds in the above-mentioned point cloud data. The above-mentioned n is the number of points after sampling.

[0048] In the seventh sub-step, the point corresponding to each local importance value in the above-mentioned sampled local importance value set is determined as a sampling point to obtain a sampling point set.

[0049] In the eighth sub-step, each sampling point in the above sampling point set is determined as lightweight point cloud data.

[0050] In practice, the comparison between the above lightweight point cloud data and the above point cloud data (original point cloud data) is shown in the figure below. Figure 4 shown.

[0051] The above-mentioned first to sixth sub-steps and their related contents as the invention points of this application have the following beneficial effects. First, the neighbor point information of each point in the point cloud can be efficiently obtained through neighbor point retrieval, reducing the computational complexity. Then, by determining the relative weight between each point and its neighbor point, a weighted adjacency matrix is ​​constructed. Thus, the relative relationship between any two points in the point cloud can be determined according to the weighted adjacency matrix, and the memory consumption can be significantly reduced and resource utilization can be optimized through the sparse matrix storage method. After that, the corresponding filter matrix is ​​determined according to the weighted adjacency matrix, and the local importance value of each point in the original point cloud is obtained through the filter matrix. Through weighted filtering processing, the relative importance of each point in the point cloud space can be accurately evaluated, thereby reducing the loss of surface geometric features during the lightweight process. Finally, the original point cloud is sampled in the order of local importance values ​​from high to low to generate lightweight point cloud data. Thus, relatively unimportant points can be removed while retaining geometric structure features, thereby achieving lightweight point cloud data, thereby reducing the waste of computing resources and storage resources.

[0052] The second step is to perform surface point cloud segmentation on the above lightweight point cloud data to obtain segmented point cloud data. The surface point cloud segmentation can be performed on the above lightweight point cloud data by a preset point cloud segmentation algorithm to obtain segmented point cloud data. The point cloud segmentation effect diagram of the segmented point cloud data is shown in FIG. Figure 5As shown in the figure, different colors represent different segmentation areas. The segmentation point cloud data includes multiple segmentation areas, and each segmentation area corresponds to a segmentation category. The segmentation categories may include but are not limited to: "ceiling", "wall", "ground", "doors and windows", "pipes", etc.

[0053] As an example, the point cloud segmentation algorithm may include but is not limited to at least one of the following: a region growing point cloud segmentation algorithm, a deep learning-based point cloud segmentation algorithm (such as PointCNN), etc.

[0054] Step 103 : determining the point cloud in each segmented area corresponding to the wall category in the segmented point cloud data as wall point cloud data, and obtaining a wall point cloud data set.

[0055] In some embodiments, the execution entity may determine the point cloud in each segmented area corresponding to the wall category in the segmented point cloud data as wall point cloud data to obtain a wall point cloud data set.

[0056] Step 104 , performing wall information detection on each wall point cloud data in the wall point cloud data set to obtain wall information.

[0057] In some embodiments, the execution subject may perform wall information detection on each wall point cloud data in the wall point cloud data set to obtain wall information, wherein the wall information includes a wall flatness information set, a wall verticality information set and indoor squareness information.

[0058] In some optional implementations of some embodiments, the execution subject performs wall information detection on each wall point cloud data in the wall point cloud data set to obtain the wall information, which may include the following steps:

[0059] In the first step, a flatness detection is performed on each wall point cloud data in the above wall point cloud data set to generate wall flatness information and obtain a wall flatness information set.

[0060] Optionally, the execution subject performs a flatness detection on each wall point cloud data in the wall point cloud data set to generate wall flatness information, and obtains a wall flatness information set, which may include the following steps:

[0061] For each wall point cloud data in the above wall point cloud data set, the following flatness detection steps are performed to generate wall flatness information, thereby obtaining a wall flatness information set:

[0062] Sub-step 1, plane fitting is performed on each wall point in the above-mentioned wall point cloud data to obtain a wall fitting plane. Wherein, a preset point cloud flatness detection algorithm can be used to perform plane fitting on each wall point in the above-mentioned wall point cloud data to obtain a wall fitting plane. The above-mentioned point cloud flatness detection algorithm can be a RANSAC (Random Sample Consensus) algorithm. Wherein, the above-mentioned wall fitting plane can be characterized by a plane formula in three-dimensional space.

[0063] Sub-step 2: determining the plane normal vector of the wall fitting plane. The corresponding plane normal vector can be determined according to the formula of the wall fitting plane.

[0064] Sub-step three, according to the plane normal vector, the distance between each wall point in the wall point cloud data and the fitting plane is determined as the relative elevation difference, and a relative elevation difference set is obtained. According to the relative elevation difference set, the visualization result of the flatness detection of the wall is as follows: Figure 6 shown. Figure 6 Different colors represent different relative elevation differences.

[0065] Sub-step four: determining the difference between the relative elevation difference with the largest corresponding value and the relative elevation difference with the smallest corresponding value in the above relative elevation difference set as the flatness error.

[0066] Sub-step 5: determining the proportion of the relative elevation differences that are smaller than the preset standard elevation difference as the flatness percentage. The standard elevation difference may be 8 mm.

[0067] Sub-step six: determining the flatness error and the flatness percentage as the wall flatness information of the wall point cloud data.

[0068] In the second step, verticality detection is performed on each wall point cloud data in the above wall point cloud data set to generate wall verticality information and obtain a wall verticality information set.

[0069] Optionally, the execution subject performs verticality detection on each wall point cloud data in the wall point cloud data set to generate wall verticality information, and obtains the wall verticality information set, which may include the following steps:

[0070] In the first sub-step, the point cloud in the segmented area corresponding to the ground category in the segmented point cloud data is determined as ground point cloud data.

[0071] The second sub-step is to perform plane fitting on each ground point in the above-mentioned ground point cloud data to obtain a ground fitting plane. Among them, plane fitting can be performed on each ground point in the above-mentioned ground point cloud data to obtain a ground fitting plane. Secondly, multiple standard horizontal planes can also be preset. The above-mentioned standard horizontal plane is a plane parallel to the ground, and the height (z value in the Cartesian coordinate system) of each standard horizontal plane is different. Secondly, the standard horizontal plane among the above-mentioned multiple standard horizontal planes that overlaps the most with the points in the above-mentioned ground point cloud data can be used as the ground fitting plane. The above-mentioned overlap means that the points in the above-mentioned ground point cloud data belong to the standard horizontal plane.

[0072] In the third sub-step, the angle between the wall fitting plane corresponding to each wall point cloud data in the wall point cloud data set and the ground fitting plane is determined as the wall vertical angle to obtain a wall vertical angle set. The angle between the wall fitting plane corresponding to each wall point cloud data in the wall point cloud data set and the ground fitting plane can be determined by calculating the plane angle in three-dimensional space.

[0073] The fourth sub-step is to determine the difference between each wall vertical angle in the wall vertical angle set and the standard vertical angle as a relative vertical angle difference to obtain a relative vertical angle difference set, wherein the standard vertical angle is 90 degrees.

[0074] In a fifth sub-step, each relative vertical angle difference in the relative vertical angle difference set is determined as wall verticality information to obtain a wall verticality information set.

[0075] The third step is to perform squareness detection on each wall point cloud data in the above wall point cloud data set to obtain indoor squareness information.

[0076] Optionally, the execution subject performs squareness detection on each wall point cloud data in the wall point cloud data set to obtain indoor squareness information, which may include the following steps:

[0077] In the first sub-step, according to the wall fitting plane corresponding to each wall point cloud data in the wall point cloud data set, the wall angle between each two adjacent walls is determined to obtain a wall angle set. The wall angle between each two adjacent walls can be determined by calculating the plane angle in three-dimensional space.

[0078] The second sub-step is to determine the difference between each wall angle in the wall angle set and a preset standard angle as a relative angle difference, and obtain a relative angle difference set, wherein the standard angle is 90 degrees.

[0079] The third sub-step is to determine the corresponding indoor squareness information according to the above relative angle degree difference set. Among them, first, a mapping table between relative angle degree difference and indoor squareness can be preset. Secondly, based on the above mapping table, the corresponding indoor squareness can be determined according to the above relative angle degree difference set. For example, if each relative angle degree difference in the above relative angle degree difference set is less than or equal to the preset standard angle degree, the corresponding indoor squareness value is 1. If each relative angle degree difference in the above relative angle degree difference set is greater than the preset standard angle degree, the corresponding indoor squareness value is 0.

[0080] Optionally, the execution subject performs squareness detection on each wall point cloud data in the wall point cloud data set to obtain indoor squareness information, and may also include: first, obtaining a preset horizontal central axis and vertical central axis. The horizontal central axis and vertical central axis are lines on the ground fitting plane of the room to be decorated, and the horizontal central axis and vertical central axis are perpendicular to each other, such as Figure 7 As shown by the dotted line in . Secondly, according to the wall fitting plane corresponding to each wall point cloud data in the above-mentioned wall point cloud data set and the above-mentioned ground fitting plane, the intersection points of the above-mentioned planes can be determined as the four corner points in the above-mentioned interior to be decorated. The coordinates of the above-mentioned four corner points are three-dimensional space coordinates. Next, determine the distance between each two corner points of the above-mentioned four corner points and the corresponding central axis. For example, if two corner points belong to the same wall fitting plane, and the above-mentioned wall fitting plane is horizontal to the horizontal central axis, the distance between the two corner points and the horizontal central axis can be determined, and then the difference between the two distances is calculated as the squareness error. Finally, the four squareness errors obtained are used as the indoor squareness.

[0081] Step 105 , based on the wall information, identify the wall decoration process for each wall point cloud data in the wall point cloud data set to obtain indoor decoration process information.

[0082] In some embodiments, the execution entity may perform wall decoration process identification on each wall point cloud data in the wall point cloud data set according to the wall information to obtain interior decoration process information.

[0083] In some optional implementations of some embodiments, the execution subject performs wall decoration process identification on each wall point cloud data in the wall point cloud data set according to the wall information to obtain indoor decoration process information, which may include the following steps:

[0084] In the first step, in response to the indoor squareness information contained in the wall information being less than or equal to a preset squareness threshold, the following steps are performed on each wall point cloud data in the wall point cloud data set to generate wall process information, thereby obtaining a wall process information set:

[0085] In the first sub-step, in response to the wall verticality information corresponding to the wall point cloud data being less than a preset standard vertical angle, the wall process information corresponding to the wall flatness information corresponding to the wall point cloud data is determined. The wall process information includes no leveling process, wet leveling process, and dry leveling process. The standard vertical angle is 90 degrees.

[0086] Specifically, when the corresponding flatness error is within 1mm, it can be determined that the wall flatness meets the standard, and only a thin layer of putty leveling layer needs to be scraped to directly lay the finishing wallpaper or apply paint finishing materials; when the flatness error is within 1mm to 10mm, it can be directly determined that the wall needs to be leveled. After the wall is leveled by leveling materials such as gypsum-based or cement mortar, that is, wet leveling process, the finishing materials can be laid or rolled; when the flatness error is above 10mm, the system can directly determine that the wall of the space needs to be dry-leveled by the keel before the finishing material can be constructed.

[0087] In the second sub-step, in response to the wall verticality information corresponding to the above-mentioned wall point cloud data being greater than a preset standard vertical angle, the dry leveling process is determined as the wall process information corresponding to the above-mentioned wall point cloud data.

[0088] The second step is to determine the interior decoration process information of the room to be decorated based on the above wall process information set. First, different wall process information can be graded, for example, no leveling process corresponds to level 1, wet leveling process corresponds to level 2, and dry leveling process corresponds to level 3. Then, the wall process information with the highest level in the above wall process information set is determined as the interior decoration process information of the room to be decorated.

[0089] In the third step, in response to the indoor squareness information contained in the wall information being greater than a preset squareness threshold and less than or equal to a preset standard squareness threshold, the wet leveling process is determined as the indoor decoration process information of the room to be decorated. If the squareness error is greater than 5mm, the room wall needs to be dry leveled. When the squareness error is within the range of 5 to 10mm, gypsum-based or cement mortar leveling materials can be used, and the wet leveling process can be adopted.

[0090] Step 4: In response to the indoor squareness information contained in the wall information being greater than the preset standard squareness threshold, dry leveling is determined as the indoor decoration process information of the room to be decorated. When the squareness errors corresponding to the indoor squareness are all within the wall range of 10mm, the wall surface can be dry leveled by the keel. Figure 7 shown. Figure 7 The hollow part in the figure represents the existing wall, and the black part is the wall after leveling.

[0091] Optionally, the execution subject may perform wall decoration process identification on each wall point cloud data in the wall point cloud data set according to the wall information to obtain indoor decoration process information, which may include the following steps:

[0092] In the first step, for each wall point cloud data in the above wall point cloud data set, the following steps are performed to generate wall process information to obtain a wall process information set:

[0093] Based on the preset wall decoration recognition model, the wall craft information of the wall point cloud data is determined according to the wall flatness information and wall verticality information corresponding to the wall point cloud data. The wall flatness information and wall verticality information can be input into the wall decoration recognition model to obtain the wall craft information of the wall point cloud data.

[0094] Optionally, the preset wall construction detection model is trained in the following way:

[0095] The first sub-step is to obtain an initial wall surface construction detection model. The initial wall surface construction detection model may include but is not limited to at least one of the following: a decision tree model and a random forest model.

[0096] The second sub-step is to obtain a wall surface construction sample data set. Each wall surface construction sample data in the wall surface construction sample data set includes wall surface data information and corresponding wall surface technology. The wall surface data information includes wall surface flatness information and wall surface verticality information. The wall surface technology can be determined by expert evaluation.

[0097] In the third sub-step, the wall data information in the above-mentioned wall construction sample data set is used as the input of the initial wall construction detection model, and the above-mentioned wall process is used as the expected output of the initial wall construction detection model, and the above-mentioned initial wall construction detection model is supervised and trained to obtain the wall construction detection model.

[0098] The second step is to determine the interior decoration process information of the room to be decorated according to the above wall process information set and the above indoor squareness information. If the above wall process data corresponds to no leveling required, the interior decoration process data of the room to be decorated is determined according to the indoor squareness. Secondly, if the above wall process data corresponds to a type other than no leveling required, the interior decoration process information can be determined according to the indoor squareness.

[0099] Step 106, determining corresponding indoor construction information according to the indoor decoration process information.

[0100] In some embodiments, the above-mentioned execution entity can determine the corresponding indoor construction information based on the above-mentioned indoor decoration process information. Among them, the above-mentioned indoor construction information includes decoration design information, decoration material information, and construction detail information. The above-mentioned decoration design information may include construction thickness and room net size reduction. The above-mentioned decoration material information may include but is not limited to: putty powder, building glue, gypsum base, building keel, cement mortar, etc. The above-mentioned construction detail information may include construction location information and construction step information. First, the indoor construction information corresponding to the above-mentioned indoor decoration process information can be determined according to the preset process and construction mapping table. The above-mentioned process and construction mapping table is a relationship table between the indoor construction information corresponding to the pre-established indoor decoration process information.

[0101] As an example, when the above-mentioned indoor decoration process information is that no leveling is required, in the above-mentioned process and construction mapping table, the corresponding indoor construction information includes the decoration design information of construction thickness 2mm and room net size reduction of 0 square meters. The above-mentioned decoration material information is putty powder, building glue, etc. The above-mentioned construction detail information includes that the construction location is each wall, and the construction steps are standard plastering steps.

[0102] Step 107, based on the preset construction platform, the decoration design information, decoration material information and construction detail information are transmitted to the target port to transport indoor construction materials.

[0103] In some embodiments, the above-mentioned execution entity can transmit the above-mentioned decoration design information, decoration material information and construction detail information to the target port based on a preset construction platform to transport indoor construction materials. Among them, the above-mentioned construction platform can be embodied as a mobile application, and can also be used as a computer-side software or web-side service platform to achieve efficient communication and information sharing between various departments of wall construction. The above-mentioned target port includes a design department port, a procurement department port or an engineering department port. First, based on the above-mentioned construction platform, the above-mentioned decoration design information, decoration material information and construction detail information can be transmitted to the design department port, the procurement department port or the engineering department port respectively. Afterwards, the design department, the procurement department and the engineering department can prepare and transport construction materials according to the above-mentioned indoor construction information.

[0104] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the wall construction detection method of some embodiments of the present disclosure, the consumption of manpower, time and building materials can be reduced. Specifically, the reasons for the consumption of manpower, time and building materials are: manual measurement takes a long time, the efficiency is low when measuring walls with larger areas, and the measurement accuracy is easily limited by the accuracy of the tool and the experience and skill level of the operator. Secondly, it is difficult to ensure the consistency and accuracy of the judgment results when judging the leveling process subjectively, which will lead to the consumption of manpower, time and building materials. Based on this, the wall construction detection method of some embodiments of the present disclosure first obtains the point cloud data of the interior to be decorated scanned by the laser radar. By replacing the traditional manual measurement method with the laser radar scanning technology, the three-dimensional point cloud data of the interior to be decorated can be quickly obtained, which shortens the time of data collection and reduces the impact of different operator skill levels. Secondly, the point cloud data is segmented to obtain segmented point cloud data. Among them, the segmented point cloud data contains multiple segmented areas, and one segmented area corresponds to a segmentation category. Therefore, the above-mentioned complex indoor environment can be segmented into multiple segmented areas that are easy to manage through automated segmentation processing. Afterwards, the point cloud in each segmented area corresponding to the wall category in the segmented point cloud data is determined as the wall point cloud data to obtain the wall point cloud data set. Thus, the point cloud data representing only the wall can be obtained from the original point cloud data. Subsequently, the wall information is detected for each wall point cloud data in the wall point cloud data set to obtain the wall information. Among them, the wall information includes a wall flatness information set, a wall verticality information set and indoor squareness information. Compared with manual judgment, the wall information detection scheme for flatness, verticality and squareness can provide more objective and consistent results, and can also find subtle irregularities and reduce the waste of building materials. Then, according to the wall information, the wall decoration process is identified for each wall point cloud data in the wall point cloud data set to obtain indoor decoration process information. Thus, the deviation caused by human evaluation of the decoration process can be avoided, which is helpful to formulate a more accurate leveling plan. Then, according to the indoor decoration process information, the corresponding indoor construction information is determined. Among them, the indoor construction information includes decoration design information, decoration material information, and construction detail information. In this way, the specific construction details of the interior to be decorated can be accurately obtained. Finally, based on the preset construction platform, the above-mentioned decoration design information, decoration material information and construction details information are transmitted to the target port to transport indoor construction materials. Among them, the above-mentioned target port includes the design department port, the procurement department port or the engineering department port. The indoor construction information is transmitted to each port through the construction platform, which is convenient for each department to prepare construction materials and understand the corresponding construction details in advance. In this way, rework can be reduced, thereby reducing the waste of manpower, time and construction materials.

[0105] Further references Figure 2 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a wall construction detection device. These device embodiments are similar to Figure 1 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0106] like Figure 2 As shown, some embodiments of the wall construction detection device 200 include: an acquisition unit 201, a point cloud segmentation unit 202, a first determination unit 203, a wall information detection unit 204, a wall decoration process identification unit 205, a second determination unit 206, and a transmission unit 207. The acquisition unit 201 is configured to acquire point cloud data of the interior to be decorated scanned by a laser radar; the point cloud segmentation unit 202 is configured to perform point cloud segmentation on the point cloud data to obtain segmented point cloud data, wherein the segmented point cloud data contains a plurality of segmented areas, one segmented area corresponding to one segmented category; the first determination unit 203 is configured to determine the point cloud in each segmented area corresponding to the wall category in the segmented point cloud data as wall point cloud data to obtain a wall point cloud data set; the wall information detection unit 204 is configured to perform wall information detection on each wall point cloud data in the wall point cloud data set to obtain wall information, wherein the wall information includes a wall flatness information set, a wall verticality information set, and a wall flatness information set. information set and indoor squareness information; a wall decoration process identification unit 205 is configured to perform wall decoration process identification on each wall point cloud data in the above wall point cloud data set according to the above wall information, so as to obtain indoor decoration process information; a second determination unit 206 is configured to determine the corresponding indoor construction information according to the above indoor decoration process information, wherein the above indoor construction information includes decoration design information, decoration material information and construction detail information; a transmission unit 207 is configured to transmit the above decoration design information, decoration material information and construction detail information to a target port based on a preset construction platform, so as to transport indoor construction materials, wherein the above target port includes a design department port, a procurement department port or an engineering department port.

[0107] It is understood that the units described in the device 200 are similar to those described in the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the device 200 and the units included therein, and will not be described in detail here.

[0108] Reference below Figure 3 , which shows a structural schematic diagram of an electronic device (eg, a computing device) 300 suitable for implementing some embodiments of the present disclosure. Figure 3The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0109] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory 302 or a program loaded from a storage device 308 into a random access memory 303. Various programs and data required for the operation of the electronic device 300 are also stored in the random access memory 303. The processing device 301, the read-only memory 302, and the random access memory 303 are connected to each other via a bus 304. An input / output interface 305 is also connected to the bus 304.

[0110] Typically, the following devices may be connected to the I / O interface 305: input devices 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 308 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 309. The communication devices 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0111] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the read-only memory 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the method of some embodiments of the present disclosure are executed.

[0112] It should be noted that the computer-readable medium recorded in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In some embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0113] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (Hyper Text Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0114] The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist independently without being installed in the electronic device. The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: obtains the point cloud data of the interior to be decorated scanned by the laser radar; performs point cloud segmentation on the above-mentioned point cloud data to obtain segmented point cloud data, wherein the above-mentioned segmented point cloud data contains multiple segmentation areas, and one segmentation area corresponds to one segmentation category; determines the point cloud in each segmentation area corresponding to the wall category in the above-mentioned segmented point cloud data as wall point cloud data, and obtains a wall point cloud data set; performs wall information detection on each wall point cloud data in the above-mentioned wall point cloud data set to obtain wall information, wherein the above-mentioned wall information The information includes a wall flatness information set, a wall verticality information set and indoor squareness information; based on the above wall information, the wall decoration process is identified for each wall point cloud data in the above wall point cloud data set to obtain indoor decoration process information; based on the above indoor decoration process information, the corresponding indoor construction information is determined, wherein the above indoor construction information includes decoration design information, decoration material information and construction detail information; based on a preset construction platform, the decoration design information, decoration material information and construction detail information are transmitted to a target port to transport indoor construction materials, wherein the above target port includes a design department port, a procurement department port or an engineering department port.

[0115] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0116] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0117] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The described units may also be provided in a processor, for example, may be described as: a processor including an acquisition unit, a point cloud segmentation unit, a first determination unit, a wall information detection unit, a wall decoration process identification unit, a second determination unit, and a transmission unit. The names of these units do not, in some cases, constitute limitations on the units themselves, for example, the acquisition unit may also be described as a "unit for acquiring point cloud data of the interior to be decorated scanned by a laser radar".

[0118] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0119] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with the technical features with similar functions disclosed in the embodiments of the present disclosure (but not limited to) and the technical solutions formed.

Claims

1. A wall construction detection method based on laser point cloud, comprising: Obtain point cloud data of the interior to be decorated scanned by LiDAR; Performing point cloud segmentation on the point cloud data to obtain segmented point cloud data, wherein the segmented point cloud data includes a plurality of segmented regions, and each segmented region corresponds to a segmentation category; Determine the point cloud in each segmented area corresponding to the wall category in the segmented point cloud data as wall point cloud data to obtain a wall point cloud data set; Performing wall information detection on each wall point cloud data in the wall point cloud data set to obtain wall information, wherein the wall information includes a wall flatness information set, a wall verticality information set and indoor squareness information; According to the wall information, wall decoration process identification is performed on each wall point cloud data in the wall point cloud data set to obtain indoor decoration process information; Determine the corresponding indoor construction information according to the indoor decoration process information, wherein the indoor construction information includes decoration design information, decoration material information, and construction detail information; Based on a preset construction platform, the decoration design information, decoration material information and construction detail information are transmitted to a target port to transport indoor construction materials, wherein the target port includes a design department port, a procurement department port or an engineering department port.

2. The method according to claim 1, wherein: The step of performing point cloud segmentation on the point cloud data to obtain segmented point cloud data includes: Performing lightweight processing on the point cloud data to obtain lightweight point cloud data; Surface point cloud segmentation is performed on the lightweight point cloud data to obtain segmented point cloud data.

3. The method according to claim 1, wherein: The performing wall information detection on each wall point cloud data in the wall point cloud data set to obtain wall information includes: Performing flatness detection on each wall point cloud data in the wall point cloud data set to generate wall flatness information, thereby obtaining a wall flatness information set; Performing verticality detection on each wall point cloud data in the wall point cloud data set to generate wall verticality information, thereby obtaining a wall verticality information set; The squareness of each wall point cloud data in the wall point cloud data set is detected to obtain indoor squareness information.

4. The method according to claim 3, wherein: The step of performing flatness detection on each wall point cloud data in the wall point cloud data set to generate wall flatness information and obtain a wall flatness information set includes: For each wall point cloud data in the wall point cloud data set, the following flatness detection steps are performed to generate wall flatness information, thereby obtaining a wall flatness information set: Performing plane fitting on each wall point in the wall point cloud data to obtain a wall fitting plane; Determining a plane normal vector of the wall fitting plane; According to the plane normal vector, the distance between each wall point in the wall point cloud data and the fitting plane is determined as a relative elevation difference to obtain a relative elevation difference set; The difference between the relative elevation difference with the largest corresponding value and the relative elevation difference with the smallest corresponding value in the relative elevation difference set is determined as the flatness error; The proportion of the relative elevation differences in the relative elevation difference concentration that are smaller than the preset standard elevation difference is determined as a flatness percentage; The flatness error and the flatness percentage are determined as the wall flatness information of the wall point cloud data.

5. The method according to claim 4, wherein: The step of performing verticality detection on each wall point cloud data in the wall point cloud data set to generate wall verticality information and obtain a wall verticality information set includes: Determine the point cloud in the segmented area corresponding to the ground category in the segmented point cloud data as ground point cloud data; Performing plane fitting on each ground point in the ground point cloud data to obtain a ground fitting plane; Determine the angle between the wall fitting plane corresponding to each wall point cloud data in the wall point cloud data set and the ground fitting plane as the wall vertical angle, and obtain a wall vertical angle set; Determine the difference between each wall vertical angle in the wall vertical angle set and the standard vertical angle as a relative vertical angle difference, and obtain a relative vertical angle difference set; Each relative vertical angle difference in the relative vertical angle difference set is determined as wall verticality information to obtain a wall verticality information set.

6. The method according to claim 4, wherein: The performing squareness detection on each wall point cloud data in the wall point cloud data set to obtain indoor squareness information includes: According to the wall fitting plane corresponding to each wall point cloud data in the wall point cloud data set, the degree of the wall angle between every two adjacent walls is determined to obtain a wall angle degree set; Determine the difference between each wall angle in the wall angle set and a preset standard angle as a relative angle difference, and obtain a relative angle difference set; According to the relative angle degree difference set, corresponding indoor squareness information is determined.

7. The method according to claim 1, wherein: According to the wall information, wall decoration process identification is performed on each wall point cloud data in the wall point cloud data set to obtain indoor decoration process information, including: In response to the indoor squareness information included in the wall information being less than or equal to a preset squareness threshold, performing the following steps on each wall point cloud data in the wall point cloud data set to generate wall process information to obtain a wall process information set: In response to the wall verticality information corresponding to the wall point cloud data being less than a preset standard vertical angle, determining the wall process information corresponding to the wall flatness information corresponding to the wall point cloud data, wherein the wall process information includes a process without leveling, a wet leveling process, and a dry leveling process; In response to the wall verticality information corresponding to the wall point cloud data being greater than a preset standard vertical angle, determining the dry leveling process as the wall process information corresponding to the wall point cloud data; Determine the interior decoration process information of the room to be decorated according to the wall process information set; in response to the indoor squareness information contained in the wall information being greater than a preset squareness threshold and less than or equal to a preset standard squareness threshold, determine the wet leveling process as the interior decoration process information of the room to be decorated; In response to the indoor squareness information included in the wall information being greater than a preset standard squareness threshold, the dry leveling process is determined as the indoor decoration process information of the room to be decorated.

8. A wall construction detection device based on laser point cloud, comprising: An acquisition unit is configured to acquire point cloud data of the interior of the room to be decorated scanned by a laser radar; A point cloud segmentation unit is configured to perform point cloud segmentation on the point cloud data to obtain segmented point cloud data, wherein the segmented point cloud data includes a plurality of segmentation areas, and each segmentation area corresponds to a segmentation category; A first determining unit is configured to determine the point cloud in each segmented area corresponding to the wall category in the segmented point cloud data as wall point cloud data to obtain a wall point cloud data set; A wall information detection unit is configured to perform wall information detection on each wall point cloud data in the wall point cloud data set to obtain wall information, wherein the wall information includes a wall flatness information set, a wall verticality information set and indoor squareness information; A wall decoration process identification unit is configured to perform wall decoration process identification on each wall point cloud data in the wall point cloud data set according to the wall information to obtain indoor decoration process information; A second determining unit is configured to determine corresponding indoor construction information according to the indoor decoration process information, wherein the indoor construction information includes decoration design information, decoration material information, and construction detail information; The transmission unit is configured to transmit the decoration design information, decoration material information and construction detail information to the target port based on a preset construction platform to transport indoor construction materials, wherein the target port includes a design department port, a procurement department port or an engineering department port.

9. An electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer readable medium having a computer program stored thereon, wherein: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images