A method and device for generating graphics of land for demolition based on intelligence

Abstract

The present invention discloses a method and device for generating graphics of land for demolition based on intelligence. The method obtains point cloud data of land for demolition based on the principle of laser measurement, and pre-processes the point cloud data; performs local maximum point detection on the pre-processed point cloud data, and performs Gaussian surface fitting and distance clustering in sequence to generate corresponding three-dimensional point cloud data; performs multiple feature extractions on the three-dimensional point cloud data to generate corresponding multiple point cloud sets and point clouds to be simplified; utilizes a grid method to segment the point clouds to be simplified, and utilizes an octree method to simplify the segmented point clouds to obtain simplified point cloud sets; fuses the simplified point cloud set and multiple point cloud sets, and constructs a corresponding three-dimensional graphic in combination with the acquired color information, first generates corresponding three-dimensional point cloud data, and then performs simplification, so as to ensure the accuracy of the obtained three-dimensional image of the land for demolition.

Description

Technical Field

[0001] The present invention relates to the technical field of land surveying and mapping, and in particular to a method and device for generating graphics of land for intelligent demolition. Background Art

[0002] At present, for land demolition, it usually takes a lot of manpower and material resources to conduct multiple field surveys and measurements of the demolition land, and according to the recorded measurement results, the corresponding three-dimensional model is mapped out through three-dimensional software. This not only consumes a lot of manpower and material resources, but also cannot guarantee the accuracy of the generated demolition land graphics. Summary of the invention

[0003] The purpose of the present invention is to provide a method and device for generating graphics of land for demolition based on intelligence, so as to improve the accuracy of the graphics of the generated land for demolition.

[0004] To achieve the above objectives, in a first aspect, the present invention provides a method for generating a demolition land graph based on intelligence, comprising the following steps:

[0005] Acquire point cloud data of the demolition land based on the laser measurement principle, and pre-process the point cloud data;

[0006] Performing local maximum point detection on the preprocessed point cloud data, and performing Gaussian surface fitting and distance clustering in sequence to generate corresponding three-dimensional point cloud data;

[0007] Performing multiple feature extractions on the three-dimensional point cloud data to generate corresponding multiple point cloud sets and point clouds to be simplified;

[0008] Using a grid method to segment the point cloud to be simplified, and using an octree method to simplify the segmented point cloud to be simplified, to obtain a simplified point cloud set;

[0009] The simplified point cloud set and the plurality of point cloud sets are fused, and the corresponding three-dimensional graphics are constructed in combination with the acquired color information.

[0010] The pre-processed point cloud data is subjected to local maximum point detection, and Gaussian surface fitting and distance clustering are performed in sequence to generate corresponding three-dimensional point cloud data, including:

[0011] According to the recognition order from bottom to top, the pre-processed point cloud data is detected using a window of a set size until the corresponding extreme value point is obtained;

[0012] Performing Gaussian surface fitting on the pre-processed point cloud data, and calculating the location of the single demolition land using the steepest descent method;

[0013] The location of the single demolition land is taken as the center line, and all the point cloud data based on the center line are calculated using the minimum two-dimensional Euclidean distance to obtain corresponding three-dimensional point cloud data.

[0014] The three-dimensional point cloud data is subjected to multiple feature extractions to generate corresponding multiple point cloud sets and point clouds to be simplified, including:

[0015] Downsampling the three-dimensional point cloud data, and constructing a corresponding topological tree to search for multiple neighboring points for any of the three-dimensional point cloud data;

[0016] Based on the edge point distribution uniformity criterion, the coordinate values ​​of the corresponding projection points of the plurality of neighboring points on the least squares plane are compared to extract the edge point cloud and save it as an edge point cloud set;

[0017] Extracting features from the three-dimensional point cloud data based on local distribution density and saving the data as a non-feature point cloud set;

[0018] The point cloud data except the edge point cloud set and the non-feature point cloud set in the three-dimensional point cloud data are screened, and combined with the edge point cloud set to obtain the point cloud to be simplified.

[0019] The point cloud data except the edge point cloud set and the non-feature point cloud set in the three-dimensional point cloud data are screened, and combined with the edge point cloud set to obtain the point cloud to be simplified, including:

[0020] Obtaining the corresponding feature measurement factor to construct a feature evaluation function, and inputting the screened point cloud data into the feature evaluation function, extracting the corresponding point cloud data greater than a set threshold, and saving them with the feature point cloud set;

[0021] The point cloud data that is less than or equal to the set threshold is merged with the edge point cloud data to obtain the point cloud to be simplified.

[0022] The point cloud to be simplified is segmented by a grid method, and the segmented point cloud to be simplified is simplified by an octree method to obtain a simplified point cloud set, including:

[0023] Constructing a minimum bounding box based on the point cloud to be simplified, dividing the minimum bounding box by using a grid method, and dividing each obtained sub-grid again by using an octree method to obtain a sub-cube;

[0024] Simplifying and deleting the point cloud to be simplified in each of the sub-cubes based on a set simplification rule;

[0025] Until all the point clouds to be simplified are simplified, the point cloud data obtained after simplification are saved as a simplified point cloud set.

[0026] The simplified point cloud set and the plurality of point cloud sets are merged, and the corresponding three-dimensional graphics are constructed in combination with the acquired color information, including:

[0027] Acquire color information corresponding to the point cloud data based on the principle of photogrammetry;

[0028] The simplified point cloud set, the feature point cloud set and the non-feature point cloud set are fused, and the color information is assigned to the fused point cloud data based on the location of the single demolition land to obtain a corresponding three-dimensional graphic.

[0029] In a second aspect, the present invention provides a device for generating a graph based on intelligent demolition land, which is applicable to a method for generating a graph based on intelligent demolition land as described in the first aspect.

[0030] The intelligent demolition land graphics generation device comprises a point cloud data acquisition module, a three-dimensional point cloud data generation module, a feature extraction module, a point cloud simplification module and a graphics generation module, wherein the point cloud data acquisition module, the three-dimensional point cloud data generation module, the feature extraction module, the point cloud simplification module and the graphics generation module are connected in sequence;

[0031] The point cloud data acquisition module is used to acquire point cloud data of the demolition land based on the laser measurement principle and pre-process the point cloud data;

[0032] The three-dimensional point cloud data generation module is used to detect local maximum points on the pre-processed point cloud data, and perform Gaussian surface fitting and distance clustering in sequence to generate corresponding three-dimensional point cloud data;

[0033] The feature extraction module is used to perform multiple feature extractions on the three-dimensional point cloud data to generate corresponding multiple point cloud sets and point clouds to be simplified;

[0034] The point cloud simplification module is used to segment the point cloud to be simplified by using a grid method, and to simplify the segmented point cloud to be simplified by using an octree method to obtain a simplified point cloud set;

[0035] The graphics generation module is used to fuse the simplified point cloud set with multiple point cloud sets, and construct corresponding three-dimensional graphics in combination with the acquired color information.

[0036] The present invention provides a method and device for generating graphics of land for demolition based on intelligence. Point cloud data of land for demolition is obtained based on the principle of laser measurement, and the point cloud data is preprocessed; local maximum point detection is performed on the preprocessed point cloud data, and Gaussian surface fitting and distance clustering are performed in sequence to generate corresponding three-dimensional point cloud data; multiple feature extractions are performed on the three-dimensional point cloud data to generate corresponding multiple point cloud sets and point clouds to be simplified; the point cloud to be simplified is segmented by a grid method, and the segmented point cloud to be simplified is simplified by an octree method to obtain a simplified point cloud set; the simplified point cloud set and multiple point cloud sets are fused, and a corresponding three-dimensional graphic is constructed in combination with the acquired color information. The three-dimensional graphic fuses the corresponding color information, and the corresponding three-dimensional point cloud data is generated first and then simplified, so as to ensure the accuracy of the obtained three-dimensional image of the land for demolition. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1 It is a schematic diagram of the steps of a method for generating graphics of land for demolition based on intelligence provided by the present invention.

[0039] Figure 2 It is a flow chart of a method for generating graphics of land for demolition based on intelligence provided by the present invention.

[0040] Figure 3 It is a structural schematic diagram of a device for generating graphics of land for intelligent demolition provided by the present invention.

[0041] 1-Point cloud data acquisition module, 2-3D point cloud data generation module, 3-Feature extraction module, 4-Point cloud simplification module, 5-Graphics generation module. DETAILED DESCRIPTION

[0042] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0043] In the description of the present invention, “plurality” means two or more than two, unless otherwise clearly and specifically defined.

[0044] See also Figures 1 to 3 The present invention provides a method for generating a demolition land graphic based on intelligence, comprising the following steps:

[0045] S101. Acquire point cloud data of the demolition land based on the laser measurement principle, and pre-process the point cloud data.

[0046] Specifically, based on the laser measurement principle, the corresponding laser scanning equipment is used to scan the corresponding demolition land to obtain corresponding point cloud data, including three-dimensional coordinates (XYZ) and laser reflection intensity (Intensity).

[0047] Then the point cloud data is preprocessed, including:

[0048] Based on the point cloud data, the point cloud data is divided into ground data and non-ground data, and the two are interpolated and then subtracted to obtain a corresponding operation model; the operation model is morphologically opened to construct a corresponding replacement model; the replacement model is then Gaussian filtered to obtain a corresponding Gaussian model, and the preprocessing of the point cloud data is completed. In order to further ensure the accuracy of the final result, the accuracy of the laser scanning equipment can be adjusted and the demolition can be divided into multiple surveying and mapping areas. For example, the laser scanning equipment scans the multiple surveying and mapping areas in turn, and then the point cloud data are connected according to the scanning path.

[0049] S102 , performing local maximum point detection on the pre-processed point cloud data, and performing Gaussian surface fitting and distance clustering in sequence to generate corresponding three-dimensional point cloud data.

[0050] Specifically, in a recognition order from bottom to top, a window of the device size is used to detect the preprocessed point cloud data, and during the detection process, the recognition range of the window does not overlap or intersect, until all point cloud data in the Gaussian model are detected, and the local maximum point at the corresponding coordinate point can be obtained.

[0051] Based on the grid points in the Gaussian model, Gaussian surface fitting is performed on the point cloud data, wherein the grid points can be the window range used during detection, and the fitted Gaussian model is calculated using the steepest descent method to obtain a mixed Gaussian model. The value of the obtained mixed Gaussian model is the location of the single demolition land, that is, the location of the demolition land corresponding to the current point cloud data.

[0052] Next, the single demolition land is taken as the center line, and all the point cloud data whose spatial straight-line distance between any point cloud data and the center line is less than or equal to the set distance value are summarized, and based on the two-dimensional Euclidean distance formula, the summarized point cloud data are screened, and the point cloud data that meet the distance requirement are extracted until the point cloud data that meets the requirements is extracted, so as to obtain three-dimensional point cloud data based on the center line, wherein the set distance value and distance requirement can be specifically set according to the actual demolition surveying and mapping requirements, and no specific limitation is made here.

[0053] S103 , performing feature extraction on the three-dimensional point cloud data for multiple times to generate corresponding multiple point cloud sets and point clouds to be simplified.

[0054] Specifically, the three-dimensional point cloud data is downsampled, and a corresponding topological tree is constructed to search for multiple neighboring points for any of the three-dimensional point cloud data. The initial simplification of the three-dimensional point cloud data is achieved through point cloud downsampling processing, and the simplification efficiency can be effectively improved while effectively maintaining the model characteristics.

[0055] Based on the edge point distribution uniformity criterion, the coordinate values ​​of the corresponding projection points of the plurality of neighboring points on the least squares plane are compared to extract the edge point cloud and save it as an edge point cloud set, specifically:

[0056] The k nearest neighbors obtained through the search are then constructed with the least squares plane and the neighbor points are projected onto the plane. Three reference planes xpy, xpz and ypz are created for the sample point (any 3D point cloud data) p, and they are parallel to the xoy, xoz and yoz planes respectively. The difference in the number of projection points corresponding to the k nearest neighbors on both sides of the reference plane and the ratio of the number of k nearest neighbors are compared with the set threshold to determine whether the sample point is an edge point. If the ratio is greater than the set threshold, the point is judged as an edge point cloud, and the edge point cloud is extracted and saved in the edge point cloud set.

[0057] The local distribution density of the three-dimensional point cloud data is calculated, and numerical analysis is performed using a statistical histogram. An appropriate threshold is set according to the actual distribution of the demolition land to accurately extract non-feature points of the three-dimensional point cloud data and save them in a non-feature point cloud set.

[0058] The point cloud data except the edge point cloud set and the non-feature point cloud set in the three-dimensional point cloud data are screened, and combined with the edge point cloud set to obtain the point cloud to be simplified, specifically:

[0059] Obtain the corresponding feature measurement factor to construct a feature evaluation function, and input the screened point cloud data into the feature evaluation function, extract the corresponding point cloud data greater than the set threshold, and save it with the feature point cloud set; fuse the point cloud data less than or equal to the set threshold with the edge point cloud data to obtain the point cloud to be simplified. Use the classic principal component analysis method (PCA) to calculate the point cloud normal vector, and then calculate and define the curvature, average projection distance, average spatial distance and local distribution density as feature measurement factors; select appropriate feature measurement factors to construct a feature evaluation function, that is, use the curvature, average projection distance and average spatial distance to construct a feature evaluation function, obtain the point cloud feature significance value, and compare it with the corresponding set threshold, extract the corresponding point cloud data greater than the set threshold, and save it with the feature point cloud set, and fuse the point cloud data less than or equal to the set threshold with the edge point cloud data to obtain the point cloud to be simplified.

[0060] S104, using a grid method to segment the point cloud to be simplified, and using an octree method to simplify the segmented point cloud to be simplified, to obtain a simplified point cloud set.

[0061] Specifically, a minimum bounding box that can enclose the point cloud to be simplified is generated, and a hybrid partitioning method based on the grid method and the octree is used to partition the bounding box spatially. The grid method is used for initial segmentation to obtain many small grids, and a judgment is made based on whether the grid contains the point cloud to be simplified. If the small grid contains the point cloud to be simplified, it is marked and partitioned using the octree to obtain each sub-cube. The detailed process is as follows:

[0062] Suppose a minimum bounding box is generated to enclose the point cloud to be simplified, and the length, width, and height of the bounding box are L, W, and H respectively, the volume is V, and the surface area is S.

[0063]

[0064]

[0065] The maximum values ​​of the point cloud to be simplified in the x, y, and z axes are: , , , , , , then:

[0066]

[0067] The grid method is used for the initial subdivision, and many side lengths are obtained evenly. A small grid is formed, and the grid is marked according to whether the point cloud to be simplified is contained in the grid. If the small grid contains part of the point cloud to be simplified, it is marked.

[0068] From the point cloud distribution of the 3D model, we can see that the point cloud only exists on the surface of the model, so most of the space inside the bounding box has no point cloud or very few point clouds. If the point cloud density is estimated by volume V, the side length of the small grid obtained by grid division is There will be a large deviation. Therefore, the present invention uses the surface area S instead of the volume V to calculate the distribution density. The point cloud density is calculated by formula (10): , calculate the side length of the small grid N is the total number of point clouds in the oral model, and M is the number of point clouds in each grid.

[0069]

[0070]

[0071] The octree termination condition is set to the number of point clouds in the cube is less than u. The marked small grid is divided by the octree, and each sub-cube can be obtained according to the continuous division criterion.

[0072] The point cloud simplification rule is set as follows: when the average curvature of the point cloud in the subcube Greater than the average curvature of the point cloud to be simplified When , the cube gets a smaller point cloud simplification factor and retains more point clouds; conversely, the cube gets a larger point cloud simplification factor and retains fewer point clouds;

[0073] Calculate the average curvature of the point cloud in each sub-cube The average curvature of the point cloud to be simplified , and compare the two, and determine the point cloud simplification factor of the cube according to the point cloud simplification rule. Calculate the average curvature of all point clouds in the cube, and determine the position of the point cloud closest to the average curvature among all point clouds in the cube. Prioritize simplifying the point cloud far from the average curvature point cloud, and use the simplification factor to simplify the corresponding number of non-feature points. If Less than , then the sub-cube is identified as having a certain amount of weak feature points, and a lower point cloud simplification factor is determined to simplify a certain amount of non-feature points; otherwise, a higher simplification factor is determined for the sub-cube to simplify more non-feature point clouds until all the point clouds to be simplified are simplified, and the point cloud data obtained after simplification is saved as a simplified point cloud set.

[0074] S105: Fusing the simplified point cloud set with the plurality of point cloud sets, and combining the acquired color information to construct a corresponding three-dimensional graphic.

[0075] Specifically, the point cloud obtained according to the principle of photogrammetry includes three-dimensional coordinates (XYZ) and color information (RGB); the simplified point cloud set, the feature point cloud set and the non-feature point cloud set are fused, and the color information is assigned to the fused point cloud data based on the location of the single demolition land to obtain the corresponding three-dimensional graphics.

[0076] The present invention first establishes corresponding three-point cloud data to represent the corresponding three-dimensional model, and then simplifies the point cloud data. In this way, the influence of excessive other point cloud data on the imaging of the three-dimensional model can be reduced on the obtained more accurate three-dimensional model, and the problem of data missing caused by simplification and then modeling can be avoided. The accurate main three-dimensional model is retained, and color is assigned to the lost three-dimensional model in combination with color information. It can clearly distinguish whether the current demolition land belongs to forest land, cultivated land or other types, and can also distinguish the height and coverage area of ​​the corresponding objects on the current demolition land, thereby reducing the time and cost of surveying and mapping the demolition land with manpower and material resources, and also reducing the errors generated in the process of data acquisition and recording, thereby further improving the accuracy of the obtained three-dimensional image.

[0077] See also Figure 3 The present invention provides a device for generating a graphic of a demolished land based on intelligence, which is applicable to a method for generating a graphic of a demolished land based on intelligence as described in the first aspect.

[0078] The intelligent demolition land graphics generation device comprises a point cloud data acquisition module 1, a three-dimensional point cloud data generation module 2, a feature extraction module 3, a point cloud simplification module 4 and a graphics generation module 5, wherein the point cloud data acquisition module 1, the three-dimensional point cloud data generation module 2, the feature extraction module 3, the point cloud simplification module 4 and the graphics generation module 5 are connected in sequence;

[0079] The point cloud data acquisition module 1 is used to acquire the point cloud data of the demolition land based on the laser measurement principle and pre-process the point cloud data;

[0080] The three-dimensional point cloud data generation module 2 is used to detect the local maximum point of the pre-processed point cloud data, and perform Gaussian surface fitting and distance clustering in sequence to generate corresponding three-dimensional point cloud data;

[0081] The feature extraction module 3 is used to perform multiple feature extractions on the three-dimensional point cloud data to generate corresponding multiple point cloud sets and point clouds to be simplified;

[0082] The point cloud simplification module 4 is used to segment the point cloud to be simplified by using a grid method, and to simplify the segmented point cloud to be simplified by using an octree method to obtain a simplified point cloud set;

[0083] The graphics generation module 5 is used to fuse the simplified point cloud set with the multiple point cloud sets, and construct a corresponding three-dimensional graphic in combination with the acquired color information.

[0084] In this embodiment, the specific definition of a device for generating a demolition land graph based on intelligence can be found in the above definition of a method for generating a demolition land graph based on intelligence, which will not be repeated here. Each module in the above-mentioned device for generating a demolition land graph based on intelligence can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0085] The present invention provides a method and device for generating graphics of land for demolition based on intelligence. Point cloud data of land for demolition is obtained based on the principle of laser measurement, and the point cloud data is preprocessed; local maximum point detection is performed on the preprocessed point cloud data, and Gaussian surface fitting and distance clustering are performed in sequence to generate corresponding three-dimensional point cloud data; multiple feature extractions are performed on the three-dimensional point cloud data to generate corresponding multiple point cloud sets and point clouds to be simplified; the point cloud to be simplified is segmented by a grid method, and the segmented point cloud to be simplified is simplified by an octree method to obtain a simplified point cloud set; the simplified point cloud set and multiple point cloud sets are fused, and a corresponding three-dimensional graphic is constructed in combination with the acquired color information. The three-dimensional graphic fuses the corresponding color information, and the corresponding three-dimensional point cloud data is generated first and then simplified, so as to ensure the accuracy of the obtained three-dimensional image of the land for demolition.

[0086] What is disclosed above is only a preferred embodiment of the present invention, and it certainly cannot be used to limit the scope of rights of the present invention. Ordinary technicians in this field can understand that all or part of the processes of the above embodiment and equivalent changes made according to the claims of the present invention still fall within the scope of the invention.

Claims

1. A method for generating a demolition land graphic based on intelligence, characterized in that: The following steps are involved: Acquire point cloud data of the demolition land based on the laser measurement principle, and pre-process the point cloud data; Performing local maximum point detection on the preprocessed point cloud data, and performing Gaussian surface fitting and distance clustering in sequence to generate corresponding three-dimensional point cloud data; Performing multiple feature extractions on the three-dimensional point cloud data to generate corresponding multiple point cloud sets and point clouds to be simplified; Using a grid method to segment the point cloud to be simplified, and using an octree method to simplify the segmented point cloud to be simplified, to obtain a simplified point cloud set; The simplified point cloud set and the plurality of point cloud sets are fused, and the corresponding three-dimensional graphics are constructed in combination with the acquired color information.

2. The method for generating a demolition land graph based on intelligence as claimed in claim 1, characterized in that: The pre-processed point cloud data is subjected to local maximum point detection, and Gaussian surface fitting and distance clustering are performed in sequence to generate corresponding three-dimensional point cloud data, including: According to the recognition order from bottom to top, the pre-processed point cloud data is detected using a window of a set size until the corresponding extreme value point is obtained; Performing Gaussian surface fitting on the pre-processed point cloud data, and calculating the location of the single demolition land using the steepest descent method; The location of the single demolition land is taken as the center line, and all the point cloud data based on the center line are calculated using the minimum two-dimensional Euclidean distance to obtain corresponding three-dimensional point cloud data.

3. The method for generating a demolition land graph based on intelligence as claimed in claim 1, characterized in that: Performing multiple feature extractions on the three-dimensional point cloud data to generate corresponding multiple point cloud sets and point clouds to be simplified, including: Downsampling the three-dimensional point cloud data, and constructing a corresponding topological tree to search for multiple neighboring points for any of the three-dimensional point cloud data; Based on the edge point distribution uniformity criterion, the coordinate values ​​of the corresponding projection points of the plurality of neighboring points on the least squares plane are compared to extract the edge point cloud and save it as an edge point cloud set; Extracting features from the three-dimensional point cloud data based on local distribution density and saving the data as a non-feature point cloud set; The point cloud data except the edge point cloud set and the non-feature point cloud set in the three-dimensional point cloud data are screened, and combined with the edge point cloud set to obtain the point cloud to be simplified.

4. The method for generating a demolition land graph based on intelligence as claimed in claim 3, characterized in that: The point cloud data except the edge point cloud set and the non-feature point cloud set in the three-dimensional point cloud data are screened, and combined with the edge point cloud set to obtain a point cloud to be simplified, including: Obtaining the corresponding feature measurement factor to construct a feature evaluation function, and inputting the screened point cloud data into the feature evaluation function, extracting the corresponding point cloud data greater than a set threshold, and saving them with the feature point cloud set; The point cloud data that is less than or equal to the set threshold is merged with the edge point cloud data to obtain the point cloud to be simplified.

5. The method for generating a demolition land graph based on intelligence as claimed in claim 1, characterized in that: The point cloud to be simplified is segmented by a grid method, and the segmented point cloud to be simplified is simplified by an octree method to obtain a simplified point cloud set, including: Constructing a minimum bounding box based on the point cloud to be simplified, dividing the minimum bounding box by using a grid method, and dividing each obtained sub-grid again by using an octree method to obtain a sub-cube; Simplifying and deleting the point cloud to be simplified in each of the sub-cubes based on a set simplification rule; Until all the point clouds to be simplified are simplified, the point cloud data obtained after simplification are saved as a simplified point cloud set.

6. The method for generating a demolition land graph based on intelligence as claimed in claim 1, characterized in that: The simplified point cloud set is merged with the plurality of point cloud sets, and the corresponding three-dimensional graphics are constructed in combination with the acquired color information, including: Acquire color information corresponding to the point cloud data based on the principle of photogrammetry; The simplified point cloud set, the feature point cloud set and the non-feature point cloud set are fused, and the color information is assigned to the fused point cloud data based on the location of the single demolition land to obtain a corresponding three-dimensional graphic.

7. A device for generating a graph of land for demolition based on intelligence, applicable to a method for generating a graph of land for demolition based on intelligence as claimed in any one of claims 1 to 6, characterized in that: The intelligent demolition land graphics generation device comprises a point cloud data acquisition module, a three-dimensional point cloud data generation module, a feature extraction module, a point cloud simplification module and a graphics generation module, wherein the point cloud data acquisition module, the three-dimensional point cloud data generation module, the feature extraction module, the point cloud simplification module and the graphics generation module are connected in sequence; The point cloud data acquisition module is used to acquire point cloud data of the demolition land based on the laser measurement principle and pre-process the point cloud data; The three-dimensional point cloud data generation module is used to detect local maximum points on the pre-processed point cloud data, and perform Gaussian surface fitting and distance clustering in sequence to generate corresponding three-dimensional point cloud data; The feature extraction module is used to perform multiple feature extractions on the three-dimensional point cloud data to generate corresponding multiple point cloud sets and point clouds to be simplified; The point cloud simplification module is used to segment the point cloud to be simplified by using a grid method, and to simplify the segmented point cloud to be simplified by using an octree method to obtain a simplified point cloud set; The graphics generation module is used to fuse the simplified point cloud set with multiple point cloud sets, and construct corresponding three-dimensional graphics in combination with the acquired color information.

Images