A data recognition method and system for laser point cloud modeling

Abstract

The present invention relates to the technical field of data recognition for laser point cloud modeling, and discloses a data recognition method and system for laser point cloud modeling, the method comprising: acquiring laser point cloud modeling data to be recognized; performing data cleaning on the laser point cloud modeling data to be recognized, and extracting quality information of the laser point cloud modeling data after data cleaning; performing quality scoring on the laser point cloud modeling data to be recognized according to the quality information of the laser point cloud modeling data; determining the quality level of the laser point cloud modeling data according to the relationship between the quality score of the laser point cloud modeling data and the preset quality score of the laser point cloud modeling data; and identifying whether the laser point cloud modeling data can be used according to the relationship between the quality level of the laser point cloud modeling data and the preset quality level. The method comprehensively improves the recognition quality of the laser point cloud modeling data, and can effectively understand the data credibility intuitively and quantitatively.

Description

Background Art

[0002] Laser point cloud modeling is a 3D environment modeling method based on LiDAR technology. It uses laser sensors to collect point cloud data in the environment, and then uses these discrete laser point clouds to restore and present the 3D structure of objects, scenes or terrain. This modeling technology is widely used in autonomous driving, robot navigation, virtual reality, urban planning and other fields. Laser point cloud modeling generates a large amount of discrete point cloud data by measuring the reflection or scattering of the laser beam, and each point represents a surface point in space. These point cloud data can be used to generate highly accurate and detailed 3D models, providing a high-resolution representation of the environment and objects.

[0003] At present, there are some significant problems in the traditional laser point cloud modeling technology, mainly manifested in the lack of specialized means to identify and process potential low-quality or invalid data. This technical limitation can easily lead to many problems, including modeling distortion, missed or false detection of targets, etc. Especially in the fields of autonomous driving and robot navigation, this lack of accurate identification of high-quality data has become particularly prominent. However, traditional methods have failed to effectively deal with the quality issues of laser point cloud data, which may lead to inaccurate understanding of the environment, endangering the decision-making and operational safety of autonomous driving and robot navigation.

[0004] Therefore, there is an urgent need to invent a technology for data recognition of laser point cloud modeling to solve the problem of effectively identifying low-quality or invalid data in the data of laser point cloud modeling in traditional technologies. Summary of the invention

[0005] The purpose of the present invention is to provide a data recognition method and system for laser point cloud modeling, which is used to solve the problem of effectively identifying low-quality or invalid data in the data of laser point cloud modeling in traditional technologies.

[0006] On the one hand, an embodiment of the present invention provides a data recognition method for laser point cloud modeling, comprising:

[0007] Obtain laser point cloud modeling data to be identified;

[0008] Performing data cleaning on the laser point cloud modeling data to be identified, and extracting quality information of the laser point cloud modeling data after data cleaning, wherein the quality information of the laser point cloud modeling data includes the completeness of the laser point cloud modeling data, the resolution of the laser point cloud modeling data, and the point cloud density of the laser point cloud modeling data;

[0009] Performing a quality score on the laser point cloud modeling data to be identified according to the quality information of the laser point cloud modeling data;

[0010] Determining the quality level of the laser point cloud modeling data according to a relationship between the quality score of the laser point cloud modeling data and a preset quality score of the laser point cloud modeling data;

[0011] According to the relationship between the quality level of the laser point cloud modeling data and a preset quality level, identifying whether the laser point cloud modeling data can be used includes:

[0012] Acquire the quality level Q of the laser point cloud modeling data, and determine whether the laser point cloud modeling data can be used according to the relationship between the quality level Q of the laser point cloud modeling data and the preset quality level Q0 of the laser point cloud modeling data;

[0013] When Q≥Q0, it is judged that the quality level of the laser point cloud modeling data is higher than or equal to the preset quality level of the laser point cloud modeling data, and it is judged that the laser point cloud modeling data can be used;

[0014] When Q<Q0, it is determined that the quality level of the laser point cloud modeling data is lower than the preset quality level of the laser point cloud modeling data, and it is determined that the laser point cloud modeling data cannot be used.

[0015] Furthermore, when the laser point cloud modeling data to be identified is cleaned and quality information of the laser point cloud modeling data after the data cleaning is extracted, it includes:

[0016] Clearing abnormal data cloud points in the laser point cloud modeling data to be identified;

[0017] The laser point cloud modeling data and the boundary of the laser point cloud modeling data after removing abnormal data cloud points are obtained, and the laser point cloud modeling data that is not within the boundary of the laser point cloud modeling data in the laser point cloud modeling data is eliminated according to the boundary of the laser point cloud modeling data.

[0018] Furthermore, when performing a quality score on the laser point cloud modeling data to be identified according to the quality information of the laser point cloud modeling data, it includes:

[0019] Obtain the current completeness L of the laser point cloud modeling data after data cleaning, and determine whether the laser point cloud modeling data after data cleaning is complete based on the relationship between the current completeness L and the preset completeness L0:

[0020] When L≥L0, it is judged that the integrity of the laser point cloud modeling data is greater than or equal to the preset integrity, and it is judged that the laser point cloud modeling data after the data cleaning is complete;

[0021] When L<L0, it is judged that the integrity of the laser point cloud modeling data is less than the preset integrity, and the laser point cloud modeling data after the data cleaning is judged to be incomplete, and the quality of the laser point cloud modeling data is scored according to the relationship between the current integrity L and the preset integrity L0.

[0022] Further, when determining that the laser point cloud modeling data after the data cleaning is incomplete and performing a quality score on the laser point cloud modeling data according to the relationship between the current completeness L and the preset completeness L0, it includes:

[0023] Obtaining a completeness difference ΔL between the current completeness L and a preset completeness L0, ΔL=L-L0, performing a comparison between the completeness difference ΔL and the preset completeness difference, and selecting a corresponding quality score according to the comparison result, and performing a quality score on the laser point cloud modeling data;

[0024] Wherein, a first preset completeness difference △L1 and a second preset completeness difference △L2 are preset, a first preset quality score M1, a second preset quality score M2 and a third preset quality score M3 are preset, and △L1<△L2, M1<M2<M3;

[0025] When △L≤△L1, the first preset quality score M1 is selected to perform quality scoring on the laser point cloud modeling data;

[0026] When △L1<△L≤△L2, the second preset quality score M2 is selected to perform quality scoring on the laser point cloud modeling data;

[0027] When △L>△L2, the third preset quality score M3 is selected to perform quality scoring on the laser point cloud modeling data;

[0028] When the i-th preset quality score Mi is selected to perform quality scoring on the laser point cloud modeling data, i=1, 2, 3, and the quality score of the laser point cloud modeling data is determined to be E1, and E1=E*M i is set, where E is the initial quality score of the laser point cloud modeling data.

[0029] Further, when the i-th preset quality score Mi is selected to perform quality scoring on the laser point cloud modeling data, and the quality score of the laser point cloud modeling data is determined to be E1, the method includes:

[0030] Acquire the current resolution K of the laser point cloud modeling data, and determine whether the laser point cloud modeling data is clear according to the relationship between the current resolution K of the laser point cloud modeling data and the preset resolution K0 of the laser point cloud modeling data;

[0031] When K≥K0, it is judged that the resolution of the laser point cloud modeling data is greater than or equal to the preset resolution of the laser point cloud modeling data, and the laser point cloud modeling data is judged to be clear;

[0032] When K<K0, it is judged that the resolution of the laser point cloud modeling data is less than the preset resolution of the laser point cloud modeling data, and the laser point cloud modeling data is judged to be unclear, and the quality score E1 of the laser point cloud modeling data is adjusted according to the relationship between the current resolution K of the laser point cloud modeling data and the preset resolution K0 of the laser point cloud modeling data.

[0033] Further, when it is determined that the laser point cloud modeling data is unclear and the laser point cloud modeling data quality score E1 is adjusted according to the relationship between the current resolution K of the laser point cloud modeling data and the preset resolution K0 of the laser point cloud modeling data, it includes:

[0034] Obtaining a resolution difference △K between a current resolution K of the laser point cloud modeling data and a preset resolution K0 of the laser point cloud modeling data, △K=K-K0, performing a comparison between the resolution difference △K and the preset resolution difference, and selecting a corresponding adjustment coefficient according to the comparison result to adjust the quality score E1 of the laser point cloud modeling data;

[0035] Wherein, a first preset resolution difference △K1 and a second preset resolution difference △K2 are preset, a first preset adjustment coefficient N1, a second preset adjustment coefficient N2 and a third preset adjustment coefficient N3 are preset, and △K1<△K2, 0<N1<N2<N3<0.5;

[0036] When △K≤△K1, the first preset adjustment coefficient N1 is selected to adjust the laser point cloud modeling data quality score E1;

[0037] When △K1<△K≤△K2, the second preset adjustment coefficient N2 is selected to adjust the laser point cloud modeling data quality score E1;

[0038] When △K>△K2, the third preset adjustment coefficient N3 is selected to adjust the laser point cloud modeling data quality score E1;

[0039] When the i-th preset adjustment coefficient Ni is selected to adjust the laser point cloud modeling data quality score E1, i=1, 2, 3, and the adjusted laser point cloud modeling data quality score is determined to be E2, and E2=E1*Ni.

[0040] Further, when the i-th preset adjustment coefficient Ni is selected to adjust the laser point cloud modeling data quality score E1, and the adjusted laser point cloud modeling data quality score is determined to be E2, it includes:

[0041] The real-time point cloud density J of the laser point cloud modeling data is obtained, and according to the relationship between the real-time point cloud density J of the laser point cloud modeling data and the preset point cloud density J0 of the laser point cloud modeling data, it is determined whether the structure in the laser point cloud modeling data is specific:

[0042] When J≥J0, it is determined that the point cloud density of the laser point cloud modeling data is greater than or equal to the preset point cloud density of the laser point cloud modeling data, and it is determined that the structure in the laser point cloud modeling data is specific;

[0043] When J<J0, it is judged that the point cloud density of the laser point cloud modeling data is less than the preset point cloud density of the laser point cloud modeling data, and the structure in the laser point cloud modeling data is judged to be not specific, and according to the relationship between the real-time point cloud density J of the laser point cloud modeling data and the preset point cloud density J0 of the laser point cloud modeling data, the adjusted quality score E2 of the laser point cloud modeling data is corrected.

[0044] Further, when it is determined that the structure in the laser point cloud modeling data is not specific, and according to the relationship between the real-time point cloud density J of the laser point cloud modeling data and the preset point cloud density J0 of the laser point cloud modeling data, the adjusted laser point cloud modeling data quality score E2 is corrected, including:

[0045] Obtaining a point cloud density difference △J between the real-time point cloud density J of the laser point cloud modeling data and the preset point cloud density J0 of the laser point cloud modeling data, △J=J-J0, performing a comparison between the point cloud density difference △J and the preset point cloud density difference, and selecting a corresponding correction coefficient according to the comparison result to correct the adjusted laser point cloud modeling data quality score E2;

[0046] Wherein, a first preset point cloud density difference △J1 and a second preset point cloud density difference △J2 ​​are preset, a first correction coefficient B1, a second preset correction coefficient B2 and a third preset correction coefficient B3 are preset, and △J1<△J2, 0.15<B1<B2<B3<0.3;

[0047] When △J≤△J1, the first preset correction coefficient B1 is selected to correct the adjusted laser point cloud modeling data quality score E2;

[0048] When △J1<△J≤△J2, the second preset correction coefficient B2 is selected to correct the adjusted laser point cloud modeling data quality score E2;

[0049] When △J>△J2, the third preset correction coefficient B3 is selected to correct the adjusted laser point cloud modeling data quality score E2;

[0050] When the i-th preset correction coefficient Bi is selected to correct the adjusted laser point cloud modeling data quality score E2, i=1, 2, 3, and the corrected laser point cloud modeling data quality score is determined to be E3, and E3=E2*Bi is set.

[0051] Furthermore, according to the relationship between the quality score of the laser point cloud modeling data and the preset quality score of the laser point cloud modeling data, determining the quality level of the laser point cloud modeling data includes:

[0052] Obtain the corrected laser point cloud modeling data quality score E3,

[0053] Preset a first preset quality score T1 and a second preset quality score T2, preset a first preset quality level Q1, a second preset quality level Q2 and a third preset quality level Q3, and T1<T2, Q1<Q2<Q3;

[0054] Compare the corrected laser point cloud modeling data quality score E3 with each preset quality score, and select a corresponding preset quality level as the laser point cloud modeling data quality level according to the comparison result;

[0055] When E3≤T1, the first preset quality level Q1 is selected as the laser point cloud modeling data quality level;

[0056] When T1<E3≤T2, the second preset quality level Q2 is selected as the laser point cloud modeling data quality level;

[0057] When E3>T2, the third preset quality level Q3 is selected as the laser point cloud modeling data quality level;

[0058] When the i-th preset quality level Qi is selected as the laser point cloud modeling data quality level, i=1, 2, 3, and the laser point cloud modeling data quality level is determined to be Q, and Q=Q1, Q2, Q3...Qi.

[0059] In another aspect, an embodiment of the present invention further provides a data recognition system for laser point cloud modeling, which is applicable to a data recognition method for laser point cloud modeling in each of the above-mentioned embodiments of the present invention, and includes:

[0060] A data acquisition module is electrically connected to the database, and is used to acquire laser point cloud modeling data to be identified.

[0061] A data cleaning module, electrically connected to the data acquisition module, the data cleaning module is used to clean the laser point cloud modeling data to be identified, and extract quality information of the laser point cloud modeling data after data cleaning, wherein the quality information of the laser point cloud modeling data includes the integrity of the laser point cloud modeling data, the resolution of the laser point cloud modeling data and the point cloud density of the laser point cloud modeling data;

[0062] A scoring module, electrically connected to the data cleaning module, and configured to score the quality of the laser point cloud modeling data to be identified according to the quality information of the laser point cloud modeling data;

[0063] A central control module is electrically connected to the scoring module, and is used to determine the quality level of the laser point cloud modeling data based on the relationship between the quality score of the laser point cloud modeling data and a preset quality score of the laser point cloud modeling data. The central control module is also used to identify whether the laser point cloud modeling data can be used based on the relationship between the quality level of the laser point cloud modeling data and a preset quality level.

[0064] Compared with the prior art, the data recognition method and system for laser point cloud modeling in the embodiment of the present invention have the beneficial effect that: by acquiring laser point cloud modeling data, the original data basis is provided for subsequent processing. Subsequently, through the data cleaning step, possible noise and invalid information are eliminated, and the quality of the data is improved. Further, the key quality information of the laser point cloud modeling data is extracted from aspects such as completeness, resolution and point cloud density, providing a comprehensive basis for quality assessment. Through quality scoring, the system quantitatively measures the overall quality of the laser point cloud modeling data, so that users can clearly understand the credibility of the data. The subsequent quality level division further simplifies the judgment of data quality. By comparing with the preset quality level, the laser point cloud modeling data is divided into two categories: usable and unusable. This classification intuitively informs the user of the applicability of the data and provides an important basis for decision-making. The whole process emphasizes the attention to the quality of laser point cloud modeling data, which is beneficial to improving the credibility of the data and ensuring accurate and reliable results in subsequent applications. At the same time, through clear judgment criteria, users can more effectively decide whether to use these data, thereby achieving better data management and utilization in various application scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 It is a flowchart of a data recognition method for laser point cloud modeling according to an embodiment of the present invention.

[0066] Figure 2 This is a structural connection block diagram of a data recognition system for laser point cloud modeling according to an embodiment of the present invention. DETAILED DESCRIPTION

[0067] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary 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 limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, in the absence of conflict, the embodiments of the present invention and the features described in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0068] like Figure 1 As shown, a data recognition method for laser point cloud modeling according to an embodiment of the present invention includes:

[0069] Step S100: Acquire laser point cloud modeling data to be identified.

[0070] Step S200, cleaning the laser point cloud modeling data to be identified, and extracting quality information of the laser point cloud modeling data after data cleaning, wherein the quality information of the laser point cloud modeling data includes the completeness of the laser point cloud modeling data, the resolution of the laser point cloud modeling data, and the point cloud density of the laser point cloud modeling data.

[0071] Step S300: performing a quality score on the laser point cloud modeling data to be identified according to the quality information of the laser point cloud modeling data.

[0072] Step S400: determining the quality level of the laser point cloud modeling data according to the relationship between the quality score of the laser point cloud modeling data and the preset quality score of the laser point cloud modeling data.

[0073] Step S500: Identify whether the laser point cloud modeling data can be used according to the relationship between the quality level of the laser point cloud modeling data and the preset quality level.

[0074] It can be understood that in step S100, the laser point cloud modeling data to be identified is obtained, and the raw data is provided for subsequent processing. Then, in step S200, the data is preprocessed by data cleaning, possible noise and invalid information are eliminated, and key quality information of the data, including completeness, resolution and point cloud density, is extracted, thereby improving the quality of the data. Next, in step S300, the quality of the laser point cloud modeling data is scored, and the overall quality level of the data is measured in a quantitative manner, so that the user can accurately understand the credibility of the data. Finally, steps S400 and S500 further strengthen the management and application of data quality. By comparing the quality score with the preset quality score in S400, the quality level of the data is determined, and the data is divided into different quality categories, which simplifies the user's judgment of the data quality. Finally, in S500, based on the relationship between the quality level and the preset level, it is identified whether the laser point cloud modeling data can be used safely, providing users with a clear guide to help users decide whether to use these data in subsequent applications.

[0075] Specifically, in some embodiments of the present invention, according to the relationship between the quality level of the laser point cloud modeling data and the preset quality level, identifying whether the laser point cloud modeling data can be used includes: obtaining the quality level Q of the laser point cloud modeling data, and judging whether the laser point cloud modeling data can be used according to the relationship between the quality level Q of the laser point cloud modeling data and the preset quality level Q0 of the laser point cloud modeling data: when Q≥Q0, it is judged that the quality level of the laser point cloud modeling data is higher than or equal to the preset quality level of the laser point cloud modeling data, and it is judged that the laser point cloud modeling data can be used. When Q<Q0, it is judged that the quality level of the laser point cloud modeling data is lower than the preset quality level of the laser point cloud modeling data, and it is judged that the laser point cloud modeling data cannot be used.

[0076] Specifically, in some embodiments of the present invention, when cleaning the laser point cloud modeling data to be identified and extracting the quality information of the laser point cloud modeling data after cleaning, it includes: removing abnormal data cloud points in the laser point cloud modeling data to be identified. Obtaining the laser point cloud modeling data after removing the abnormal data cloud points and the boundary of the laser point cloud modeling data, and removing the laser point cloud modeling data that is not within the boundary of the laser point cloud modeling data from the laser point cloud modeling data according to the boundary of the laser point cloud modeling data.

[0077] It can be understood that by clearing the abnormal data cloud points, the abnormal noise or invalid data that may exist in the laser point cloud modeling data is successfully eliminated, thereby improving the accuracy and quality of the data. This helps to avoid interference with abnormal data in subsequent analysis and application processes, ensuring that the data is more in line with the actual scene. Secondly, by obtaining the laser point cloud modeling data after clearing the abnormal data cloud points and the boundaries of the laser point cloud modeling data, a clear control of the data boundaries is achieved. By eliminating the parts of the laser point cloud modeling data that are not within the data boundaries, the data that may be affected by the external environment is further reduced, ensuring that the remaining data is more accurate and reliable. This helps to improve the practicality of the data and make it more in line with the needs of specific application scenarios.

[0078] Specifically, in some embodiments of the present invention, when performing quality scoring on the laser point cloud modeling data to be identified based on the quality information of the laser point cloud modeling data, it includes: obtaining the current completeness L of the laser point cloud modeling data after data cleaning, and judging whether the laser point cloud modeling data after data cleaning is complete based on the relationship between the current completeness L and the preset completeness L0: when L≥L0, it is judged that the completeness of the laser point cloud modeling data is greater than or equal to the preset completeness, and the laser point cloud modeling data after data cleaning is judged to be complete; when L<L0, it is judged that the completeness of the laser point cloud modeling data is less than the preset completeness, and the laser point cloud modeling data after data cleaning is judged to be incomplete, and the quality scoring of the laser point cloud modeling data is performed based on the relationship between the current completeness L and the preset completeness L0.

[0079] Specifically, in some embodiments of the present invention, when judging that the laser point cloud modeling data after data cleaning is incomplete, and performing a quality score on the laser point cloud modeling data according to the relationship between the current completeness L and the preset completeness L0, it includes: obtaining the completeness difference △L between the current completeness L and the preset completeness L0, △L=L-L0, comparing the completeness difference △L with the preset completeness difference, and selecting a corresponding quality score according to the comparison result, and performing a quality score on the laser point cloud modeling data: wherein a first preset completeness difference △L1 and a second preset completeness difference △L2 are preset, a first preset quality score M1, a second preset quality score M2 and a third preset quality score M3 are preset, and △L1<△L2, M1<M2<M3.

[0080] When △L≤△L1, the first preset quality score M1 is selected to perform quality scoring on the laser point cloud modeling data.

[0081] When △L1<△L≤△L2, the second preset quality score M2 is selected to perform quality scoring on the laser point cloud modeling data.

[0082] When △L>△L2, the third preset quality score M3 is selected to perform quality scoring on the laser point cloud modeling data.

[0083] When the i-th preset quality score Mi is selected to perform quality scoring on the laser point cloud modeling data, i=1, 2, 3, and the quality score of the laser point cloud modeling data is determined to be E1, and E1=E*Mi is set, where E is the initial quality score of the laser point cloud modeling data.

[0084] It can be understood that by judging whether the laser point cloud modeling data after data cleaning is complete, the system can effectively identify the possible missing or incomplete data. This helps to reduce the misuse of incomplete data in subsequent analysis and application, and improves the reliability and practicality of the data. Secondly, the concept of completeness difference is introduced, and the corresponding quality score is selected based on the comparison between the completeness difference and the preset completeness difference. This difference comparison mechanism makes the quality score more flexible and can more accurately reflect the overall situation of the data. Different completeness differences correspond to different quality scores, which enhances the differentiated evaluation of data integrity. Finally, by scoring the quality of the laser point cloud modeling data according to the selected preset quality score, dynamic adjustment of the data quality is achieved. This dynamic adjustment mechanism enables the system to flexibly adjust the quality score according to the actual situation, and more accurately reflect the overall quality level of the laser point cloud modeling data.

[0085] Specifically, in some embodiments of the present invention, when the i-th preset quality score Mi is selected to perform quality scoring on the laser point cloud modeling data, and the quality score of the laser point cloud modeling data is determined to be E1, it includes: obtaining the current resolution K of the laser point cloud modeling data, and judging whether the laser point cloud modeling data is clear according to the relationship between the current resolution K of the laser point cloud modeling data and the preset resolution K0 of the laser point cloud modeling data; when K≥K0, judging that the resolution of the laser point cloud modeling data is greater than or equal to the preset resolution of the laser point cloud modeling data, judging that the laser point cloud modeling data is clear. When K<K0, judging that the resolution of the laser point cloud modeling data is less than the preset resolution of the laser point cloud modeling data, judging that the laser point cloud modeling data is not clear, and adjusting the quality score E1 of the laser point cloud modeling data according to the relationship between the current resolution K of the laser point cloud modeling data and the preset resolution K0 of the laser point cloud modeling data.

[0086] Specifically, in some embodiments of the present invention, when judging that the laser point cloud modeling data is unclear and adjusting the laser point cloud modeling data quality score E1 according to the relationship between the current resolution K of the laser point cloud modeling data and the preset resolution K0 of the laser point cloud modeling data, it includes: obtaining the resolution difference △K between the current resolution K of the laser point cloud modeling data and the preset resolution K0 of the laser point cloud modeling data, △K=K-K0, comparing the resolution difference △K with the preset resolution difference, and selecting the corresponding adjustment coefficient according to the comparison result to adjust the laser point cloud modeling data quality score E1: wherein, a first preset resolution difference △K1 and a second preset resolution difference △K2 are pre-set, a first preset adjustment coefficient N1, a second preset adjustment coefficient N2 and a third preset adjustment coefficient N3 are pre-set, and △K1<△K2, 0<N1<N2<N3<0.5.

[0087] When △K≤△K1, the first preset adjustment coefficient N1 is selected to adjust the laser point cloud modeling data quality score E1.

[0088] When △K1<△K≤△K2, the second preset adjustment coefficient N2 is selected to adjust the laser point cloud modeling data quality score E1.

[0089] When △K>△K2, the third preset adjustment coefficient N3 is selected to adjust the laser point cloud modeling data quality score E1.

[0090] When the i-th preset adjustment coefficient Ni is selected to adjust the laser point cloud modeling data quality score E1, i=1, 2, 3, and the adjusted laser point cloud modeling data quality score is determined to be E2, and E2=E1*Ni.

[0091] It can be understood that by judging the clarity of the laser point cloud modeling data, the system can effectively identify situations where there may be blurred or unclear data. This helps to reduce the misuse of unclear data in subsequent applications and improves the visualization and interpretability of the data. Secondly, the concept of resolution difference is introduced. The resolution difference is compared with the preset resolution difference, and the corresponding adjustment coefficient is selected to adjust the quality score of the laser point cloud modeling data. This difference comparison mechanism makes the adjustment of the quality score more flexible and can more accurately reflect the overall clarity of the data. Different resolution differences correspond to different adjustment coefficients, which enhances the differentiated evaluation of data clarity. Finally, by adjusting the quality score of the laser point cloud modeling data according to the selected preset adjustment coefficient, dynamic adjustment of data quality is achieved. This dynamic adjustment mechanism enables the system to flexibly adjust the quality score according to the actual situation and more accurately reflect the overall clarity level of the laser point cloud modeling data.

[0092] Specifically, in some embodiments of the present invention, when the i-th preset adjustment coefficient Ni is selected to adjust the laser point cloud modeling data quality score E1, and the adjusted laser point cloud modeling data quality score is determined to be E2, it includes: obtaining the real-time point cloud density J of the laser point cloud modeling data, and judging whether the structure in the laser point cloud modeling data is specific according to the relationship between the real-time point cloud density J of the laser point cloud modeling data and the preset point cloud density J0 of the laser point cloud modeling data: when J≥J0, it is judged that the point cloud density of the laser point cloud modeling data is greater than or equal to the preset point cloud density of the laser point cloud modeling data, and the structure in the laser point cloud modeling data is specific. When J<J0, it is judged that the point cloud density of the laser point cloud modeling data is less than the preset point cloud density of the laser point cloud modeling data, and the structure in the laser point cloud modeling data is not specific, and according to the relationship between the real-time point cloud density J of the laser point cloud modeling data and the preset point cloud density J0 of the laser point cloud modeling data, the adjusted laser point cloud modeling data quality score E2 is corrected.

[0093] Specifically, in some embodiments of the present invention, when judging that the structure in the laser point cloud modeling data is not specific, and correcting the adjusted laser point cloud modeling data quality score E2 according to the relationship between the real-time point cloud density J of the laser point cloud modeling data and the preset point cloud density J0 of the laser point cloud modeling data, it includes: obtaining the point cloud density difference △J between the real-time point cloud density J of the laser point cloud modeling data and the preset point cloud density J0 of the laser point cloud modeling data, △J=J-J0, comparing the point cloud density difference △J with the preset point cloud density difference, and selecting a corresponding correction coefficient according to the comparison result to correct the adjusted laser point cloud modeling data quality score E2: wherein a first preset point cloud density difference △J1 and a second preset point cloud density difference △J2 ​​are pre-set, a first correction coefficient B1, a second preset correction coefficient B2 and a third preset correction coefficient B3 are pre-set, and △J1<△J2, 0.15<B1<B2<B3<0.3.

[0094] When △J≤△J1, the first preset correction coefficient B1 is selected to correct the adjusted laser point cloud modeling data quality score E2.

[0095] When △J1<△J≤△J2, the second preset correction coefficient B2 is selected to correct the adjusted laser point cloud modeling data quality score E2.

[0096] When △J>△J2, the third preset correction coefficient B3 is selected to correct the adjusted laser point cloud modeling data quality score E2.

[0097] When the i-th preset correction coefficient Bi is selected to correct the adjusted laser point cloud modeling data quality score E2, i=1, 2, 3, and the corrected laser point cloud modeling data quality score is determined to be E3, and E3=E2*Bi is set.

[0098] It is understandable that by judging whether the structure in the laser point cloud modeling data is specific, the system can more accurately understand the actual characteristics of the data. This is of great significance for scenarios that require accurate structural information in subsequent applications, such as autonomous driving or robot navigation, and can avoid the misuse of data with unclear structures. Secondly, the concept of point cloud density difference is introduced, and the density difference is compared with the preset density difference, and the corresponding correction coefficient is selected for adjustment. This difference comparison mechanism makes the correction of the quality score more flexible and can more accurately reflect the structural characteristics of the laser point cloud modeling data. Different density differences correspond to different correction coefficients, which enhances the differentiated evaluation of the data structure characteristics. Finally, by correcting the quality score of the laser point cloud modeling data according to the selected preset correction coefficient, dynamic adjustment of the data quality is achieved. This dynamic adjustment mechanism enables the system to flexibly adjust the quality score according to the actual situation, and more accurately reflect the overall structural characteristics of the laser point cloud modeling data.

[0099] Specifically, in some embodiments of the present invention, when determining the quality level of the laser point cloud modeling data according to the relationship between the quality score of the laser point cloud modeling data and the preset quality score of the laser point cloud modeling data, the method includes: obtaining a revised quality score E3 of the laser point cloud modeling data. Preset a first preset quality score T1 and a second preset quality score T2, and preset a first preset quality level Q1, a second preset quality level Q2, and a third preset quality level Q3, and T1<T2, Q1<Q2<Q3. Compare the revised quality score E3 of the laser point cloud modeling data with each preset quality score, and select the corresponding preset quality level as the quality level of the laser point cloud modeling data according to the comparison result: when E3≤T1, the first preset quality level Q1 is selected as the quality level of the laser point cloud modeling data. When T1<E3≤T2, the second preset quality level Q2 is selected as the quality level of the laser point cloud modeling data. When E3>T2, the third preset quality level Q3 is selected as the quality level of the laser point cloud modeling data. When the i-th preset quality level Qi is selected as the laser point cloud modeling data quality level, i=1, 2, 3, and the laser point cloud modeling data quality level is determined to be Q, and Q=Q1, Q2, Q3…Q i.

[0100] In summary, the embodiment of the present invention provides a data recognition method for laser point cloud modeling, which provides the original data basis for subsequent processing by acquiring laser point cloud modeling data. Subsequently, through the data cleaning step, possible noise and invalid information are eliminated, thereby improving the quality of the data. Further, the key quality information of the laser point cloud modeling data is extracted from aspects such as completeness, resolution and point cloud density, providing a comprehensive basis for quality assessment. Through quality scoring, the system quantitatively measures the overall quality of the laser point cloud modeling data, so that users can clearly understand the credibility of the data. The subsequent quality level division further simplifies the judgment of data quality. By comparing with the preset quality level, the laser point cloud modeling data is divided into two categories: usable and unusable. This classification intuitively informs users of the applicability of the data and provides an important basis for decision-making. The entire process emphasizes the attention to the quality of laser point cloud modeling data, which is beneficial to improving the credibility of the data and ensuring accurate and reliable results in subsequent applications. At the same time, through clear judgment criteria, users can more effectively decide whether to use these data, thereby achieving better data management and utilization in various application scenarios.

[0101] See also Figure 2 As shown, in some embodiments of the present invention, a data recognition system for laser point cloud modeling is provided, which is applicable to a data recognition method for laser point cloud modeling in each of the above-mentioned invention embodiments, and includes: a data acquisition module, a data cleaning module, a scoring module and a central control module. The data acquisition module is electrically connected to the database, and the data acquisition module is used to acquire the laser point cloud modeling data to be identified. The data cleaning module is electrically connected to the data acquisition module, and the data cleaning module is used to clean the laser point cloud modeling data to be identified, and extract the quality information of the laser point cloud modeling data after data cleaning, wherein the quality information of the laser point cloud modeling data includes the completeness of the laser point cloud modeling data, the resolution of the laser point cloud modeling data and the point cloud density of the laser point cloud modeling data; the scoring module is electrically connected to the data cleaning module, and the scoring module is used to perform quality scoring on the laser point cloud modeling data to be identified according to the quality information of the laser point cloud modeling data; the central control module is electrically connected to the scoring module, and the central control module is used to determine the quality level of the laser point cloud modeling data according to the relationship between the quality score of the laser point cloud modeling data and the preset quality score of the laser point cloud modeling data, and the central control module is also used to identify whether the laser point cloud modeling data can be used according to the relationship between the quality level of the laser point cloud modeling data and the preset quality level.

[0102] It can be understood that a data recognition system for laser point cloud modeling in an embodiment of the present invention is applicable to a data recognition method for laser point cloud modeling in the above-mentioned embodiments of the invention. Therefore, a data recognition system for laser point cloud modeling in the above-mentioned embodiments of the invention has the same beneficial effects as a data recognition method for laser point cloud modeling, and therefore will not be described in detail.

[0103] The above is only an example of implementation of the present invention, but it cannot be used to limit the scope of the present invention. Any structural changes made according to the present invention should be regarded as falling within the protection scope of the present invention and subject to restrictions as long as they do not lose the essence of the present invention.

[0104] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process and related instructions of the system described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0105] It should be noted that the system provided in the above embodiment is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the modules or steps in the embodiments of the present invention can be decomposed or combined. For example, the modules in the above embodiments can be combined into one module, or further divided into multiple sub-modules to complete all or part of the functions described above. The names of the modules and steps involved in the embodiments of the present invention are only for distinguishing the modules or steps, and are not regarded as improper limitations of the present invention.

[0106] Those skilled in the art should be able to appreciate that the modules and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software or a combination of the two, and the programs corresponding to the software modules and method steps can be placed in random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in the technical field. In order to clearly illustrate the interchangeability of electronic hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are performed in electronic hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0107] The term "comprise" or any other similar term is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus / device that includes a list of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article, or apparatus / device.

[0108] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0109] The above are only preferred embodiments of the present invention and are not intended to limit the protection scope of the present invention.

Claims

1. A data recognition method for laser point cloud modeling, characterized in that: include: Obtain laser point cloud modeling data to be identified; Performing data cleaning on the laser point cloud modeling data to be identified, and extracting quality information of the laser point cloud modeling data after data cleaning, wherein the quality information of the laser point cloud modeling data includes the completeness of the laser point cloud modeling data, the resolution of the laser point cloud modeling data, and the point cloud density of the laser point cloud modeling data; It is determined that the laser point cloud modeling data after the data cleaning is incomplete, and the quality score of the laser point cloud modeling data is scored according to the relationship between the current completeness L and the preset completeness L0. It is then determined that the laser point cloud modeling data is unclear, and the quality score of the laser point cloud modeling data is adjusted according to the relationship between the current resolution K of the laser point cloud modeling data and the preset resolution K0 of the laser point cloud modeling data. It is then determined that the structure in the laser point cloud modeling data is not specific, and the adjusted quality score of the laser point cloud modeling data is corrected according to the relationship between the real-time point cloud density J of the laser point cloud modeling data and the preset point cloud density J0 of the laser point cloud modeling data. Determining the quality level of the laser point cloud modeling data according to a relationship between the quality score of the laser point cloud modeling data and a preset quality score of the laser point cloud modeling data; According to the relationship between the quality level of the laser point cloud modeling data and a preset quality level, identifying whether the laser point cloud modeling data can be used includes: Acquire the quality level Q of the laser point cloud modeling data, and determine whether the laser point cloud modeling data can be used according to the relationship between the quality level Q of the laser point cloud modeling data and the preset quality level Q0 of the laser point cloud modeling data; When Q≥Q0, it is judged that the quality level of the laser point cloud modeling data is higher than or equal to the preset quality level of the laser point cloud modeling data, and it is judged that the laser point cloud modeling data can be used; When Q<Q0, it is determined that the quality level of the laser point cloud modeling data is lower than the preset quality level of the laser point cloud modeling data, and it is determined that the laser point cloud modeling data cannot be used.

2. The data recognition method for laser point cloud modeling according to claim 1, characterized in that: When the laser point cloud modeling data to be identified is cleaned, and quality information of the laser point cloud modeling data after the data cleaning is extracted, it includes: Clearing abnormal data cloud points in the laser point cloud modeling data to be identified; The laser point cloud modeling data and the boundary of the laser point cloud modeling data after removing abnormal data cloud points are obtained, and the laser point cloud modeling data that is not within the boundary of the laser point cloud modeling data in the laser point cloud modeling data is eliminated according to the boundary of the laser point cloud modeling data.

3. The data recognition method for laser point cloud modeling according to claim 1, characterized in that: It is determined that the laser point cloud modeling data after the data cleaning is incomplete, and the quality score of the laser point cloud modeling data is scored according to the relationship between the current completeness L and the preset completeness L0. It is determined that the laser point cloud modeling data is not clear, and the quality score of the laser point cloud modeling data is adjusted according to the relationship between the current resolution K of the laser point cloud modeling data and the preset resolution K0 of the laser point cloud modeling data. It is determined that the structure in the laser point cloud modeling data is not specific, and the adjusted quality score of the laser point cloud modeling data is corrected according to the relationship between the real-time point cloud density J of the laser point cloud modeling data and the preset point cloud density J0 of the laser point cloud modeling data, including: Obtain the current completeness L of the laser point cloud modeling data after data cleaning, and determine whether the laser point cloud modeling data after data cleaning is complete based on the relationship between the current completeness L and the preset completeness L0: When L≥L0, it is judged that the integrity of the laser point cloud modeling data is greater than or equal to the preset integrity, and it is judged that the laser point cloud modeling data after the data cleaning is complete; When L<L0, it is judged that the integrity of the laser point cloud modeling data is less than the preset integrity, and the laser point cloud modeling data after the data cleaning is judged to be incomplete, and the quality of the laser point cloud modeling data is scored according to the relationship between the current integrity L and the preset integrity L0.

4. The data recognition method for laser point cloud modeling according to claim 3, characterized in that: When judging that the laser point cloud modeling data after the data cleaning is incomplete, and performing a quality score on the laser point cloud modeling data according to the relationship between the current completeness L and the preset completeness L0, it includes: Obtaining a completeness difference ΔL between the current completeness L and a preset completeness L0, ΔL=L-L0, performing a comparison between the completeness difference ΔL and the preset completeness difference, and selecting a corresponding quality score according to the comparison result, and performing a quality score on the laser point cloud modeling data; Wherein, a first preset completeness difference △L1 and a second preset completeness difference △L2 are preset, a first preset quality score M1, a second preset quality score M2 and a third preset quality score M3 are preset, and △L1<△L2, M1<M2<M3; When △L≤△L1, the first preset quality score M1 is selected to perform quality scoring on the laser point cloud modeling data; When △L1<△L≤△L2, the second preset quality score M2 is selected to perform quality scoring on the laser point cloud modeling data; When △L>△L2, the third preset quality score M3 is selected to perform quality scoring on the laser point cloud modeling data; When the i-th preset quality score Mi is selected to perform quality scoring on the laser point cloud modeling data, i=1, 2, 3, and the quality score of the laser point cloud modeling data is determined to be E1, and E1=E*Mi is set, where E is the initial quality score of the laser point cloud modeling data.

5. The data recognition method for laser point cloud modeling according to claim 4, characterized in that: When the i-th preset quality score Mi is selected to perform quality scoring on the laser point cloud modeling data, and the quality score of the laser point cloud modeling data is determined to be E1, the method includes: Acquire the current resolution K of the laser point cloud modeling data, and determine whether the laser point cloud modeling data is clear according to the relationship between the current resolution K of the laser point cloud modeling data and the preset resolution K0 of the laser point cloud modeling data; When K≥K0, it is judged that the resolution of the laser point cloud modeling data is greater than or equal to the preset resolution of the laser point cloud modeling data, and the laser point cloud modeling data is judged to be clear; When K<K0, it is judged that the resolution of the laser point cloud modeling data is less than the preset resolution of the laser point cloud modeling data, and the laser point cloud modeling data is judged to be unclear, and the quality score E1 of the laser point cloud modeling data is adjusted according to the relationship between the current resolution K of the laser point cloud modeling data and the preset resolution K0 of the laser point cloud modeling data.

6. The data recognition method for laser point cloud modeling according to claim 5, characterized in that: When determining that the laser point cloud modeling data is unclear and adjusting the laser point cloud modeling data quality score E1 according to the relationship between the current resolution K of the laser point cloud modeling data and the preset resolution K0 of the laser point cloud modeling data, the method includes: Obtaining a resolution difference △K between a current resolution K of the laser point cloud modeling data and a preset resolution K0 of the laser point cloud modeling data, △K=K-K0, performing a comparison between the resolution difference △K and the preset resolution difference, and selecting a corresponding adjustment coefficient according to the comparison result to adjust the quality score E1 of the laser point cloud modeling data; Wherein, a first preset resolution difference △K1 and a second preset resolution difference △K2 are preset, a first preset adjustment coefficient N1, a second preset adjustment coefficient N2 and a third preset adjustment coefficient N3 are preset, and △K1<△K2, 0<N1<N2<N3<0.5; When △K≤△K1, the first preset adjustment coefficient N1 is selected to adjust the laser point cloud modeling data quality score E1; When △K1<△K≤△K2, the second preset adjustment coefficient N2 is selected to adjust the laser point cloud modeling data quality score E1; When △K>△K2, the third preset adjustment coefficient N3 is selected to adjust the laser point cloud modeling data quality score E1; When the i-th preset adjustment coefficient Ni is selected to adjust the laser point cloud modeling data quality score E1, i=1, 2, 3, and the adjusted laser point cloud modeling data quality score is determined to be E2, and E2=E1*Ni is set.

7. The data recognition method for laser point cloud modeling according to claim 6, characterized in that: When the i-th preset adjustment coefficient Ni is selected to adjust the laser point cloud modeling data quality score E1, and the adjusted laser point cloud modeling data quality score is determined to be E2, including: The real-time point cloud density J of the laser point cloud modeling data is obtained, and according to the relationship between the real-time point cloud density J of the laser point cloud modeling data and the preset point cloud density J0 of the laser point cloud modeling data, it is determined whether the structure in the laser point cloud modeling data is specific: When J≥J0, it is determined that the point cloud density of the laser point cloud modeling data is greater than or equal to the preset point cloud density of the laser point cloud modeling data, and it is determined that the structure in the laser point cloud modeling data is specific; When J<J0, it is judged that the point cloud density of the laser point cloud modeling data is less than the preset point cloud density of the laser point cloud modeling data, and the structure in the laser point cloud modeling data is judged to be not specific, and according to the relationship between the real-time point cloud density J of the laser point cloud modeling data and the preset point cloud density J0 of the laser point cloud modeling data, the adjusted quality score E2 of the laser point cloud modeling data is corrected.

8. The data recognition method for laser point cloud modeling according to claim 7, characterized in that: When determining that the structure in the laser point cloud modeling data is not specific and correcting the adjusted laser point cloud modeling data quality score E2 according to the relationship between the real-time point cloud density J of the laser point cloud modeling data and the preset point cloud density J0 of the laser point cloud modeling data, the method includes: Obtaining a point cloud density difference △J between the real-time point cloud density J of the laser point cloud modeling data and the preset point cloud density J0 of the laser point cloud modeling data, △J=J-J0, performing a comparison between the point cloud density difference △J and the preset point cloud density difference, and selecting a corresponding correction coefficient according to the comparison result to correct the adjusted laser point cloud modeling data quality score E2; Wherein, a first preset point cloud density difference △J1 and a second preset point cloud density difference △J2 ​​are preset, a first preset correction coefficient B1, a second preset correction coefficient B2 and a third preset correction coefficient B3 are preset, and △J1<△J2, 0.15<B1<B2<B3<0.3; When △J≤△J1, the first preset correction coefficient B1 is selected to correct the adjusted laser point cloud modeling data quality score E2; When △J1<△J≤△J2, the second preset correction coefficient B2 is selected to correct the adjusted laser point cloud modeling data quality score E2; When △J>△J2, the third preset correction coefficient B3 is selected to correct the adjusted laser point cloud modeling data quality score E2; When the i-th preset correction coefficient Bi is selected to correct the adjusted laser point cloud modeling data quality score E2, i=1, 2, 3, and the corrected laser point cloud modeling data quality score is determined to be E3, and E3=E2*Bi is set.

9. The data recognition method for laser point cloud modeling according to claim 8, characterized in that: Determining the quality level of the laser point cloud modeling data according to the relationship between the quality score of the laser point cloud modeling data and the preset quality score of the laser point cloud modeling data includes: Obtain the corrected laser point cloud modeling data quality score E3, Preset a first preset quality score T1 and a second preset quality score T2, preset a first preset quality level Q1, a second preset quality level Q2 and a third preset quality level Q3, and T1<T2, Q1<Q2<Q3; Compare the corrected laser point cloud modeling data quality score E3 with each preset quality score, and select a corresponding preset quality level as the laser point cloud modeling data quality level according to the comparison result; When E3≤T1, the first preset quality level Q1 is selected as the laser point cloud modeling data quality level; When T1<E3≤T2, the second preset quality level Q2 is selected as the laser point cloud modeling data quality level; When E3>T2, the third preset quality level Q3 is selected as the laser point cloud modeling data quality level; When the i-th preset quality level Qi is selected as the laser point cloud modeling data quality level, i=1, 2, 3, and the laser point cloud modeling data quality level is determined to be Q, and Q=Q1, Q2, Q3...Qi.

10. A data recognition system for laser point cloud modeling, applicable to the data recognition method for laser point cloud modeling as claimed in any one of claims 1 to 9, characterized in that: include: A data acquisition module, electrically connected to the database, and used to acquire laser point cloud modeling data to be identified; A data cleaning module, electrically connected to the data acquisition module, the data cleaning module is used to clean the laser point cloud modeling data to be identified, and extract quality information of the laser point cloud modeling data after data cleaning, wherein the quality information of the laser point cloud modeling data includes the integrity of the laser point cloud modeling data, the resolution of the laser point cloud modeling data and the point cloud density of the laser point cloud modeling data; A scoring module, electrically connected to the data cleaning module, and configured to score the quality of the laser point cloud modeling data to be identified according to the quality information of the laser point cloud modeling data; A central control module is electrically connected to the scoring module, and is used to determine the quality level of the laser point cloud modeling data based on the relationship between the quality score of the laser point cloud modeling data and a preset quality score of the laser point cloud modeling data. The central control module is also used to identify whether the laser point cloud modeling data can be used based on the relationship between the quality level of the laser point cloud modeling data and a preset quality level.

Images