AI artificial intelligence-based real digital scene hybrid construction method and system

Abstract

The invention discloses a real digital scene hybrid construction method based on AI artificial intelligence, and relates to the technical field of scene construction, and the construction method comprises the steps: carrying out the scanning recognition of a traffic intersection through an unmanned plane, and obtaining three-dimensional point cloud data; preprocessing the collected data, uploading the data to modeling software, constructing an intersection, and constructing the intersection in a computer; obtaining the traffic flow condition of the current traffic intersection, and obtaining the occurrence frequency of the container lorry based on the traffic flow condition; according to the frequency of the container lorry. The invention also discloses an AI artificial intelligence-based real digital scene hybrid construction system. According to the method, the traffic flow of the current intersection is predicted based on the established intersection scene, the actual intersection is adjusted, controlled and reduced in time according to the predicted traffic flow, the crack scene of the road surface can be effectively established, details in the intersection can be perfected, people can be better helped to control and assist traffic, and convenience is provided.

Description

Technical Field

[0001] The present invention relates to the technical field of scene construction, and in particular to a method and system for hybrid construction of realistic digital scenes based on AI artificial intelligence. Background Art

[0002] The construction of digital scenes is a comprehensive process, which involves the integration of multiple technologies and fields. It aims to transform and upgrade traditional physical scenes through digital technology to improve efficiency, reduce costs and improve user experience. Application cases of digital scene construction include: using the Internet of Things, big data and artificial intelligence technologies to digitally transform and upgrade urban transportation, public safety, environmental protection and other fields, to achieve optimal allocation and efficient management of urban resources, and improve the quality of life and happiness of urban residents; through virtual reality, three-dimensional modeling and other technical means, to create immersive tourism experience scenes; tourists can experience the beautiful scenery and cultural atmosphere of the tourist destination at home, which improves the attractiveness and satisfaction of tourism; using the Internet of Things and artificial intelligence technologies to achieve remote monitoring and intelligent diagnosis of medical equipment, improve the efficiency and quality of medical services, and reduce medical costs and risks; In the process of hybrid construction of traffic intersections, people often only build the scene information of the buildings and some obstacles at the traffic intersections, and then simulate the traffic flow at the traffic intersections after the construction is completed, but often ignore some details, such as potholes and cracks on the road surface. The potholes and cracks on the road surface are caused by the fact that there are container trucks passing through the traffic intersections all year round, and the road surface cannot withstand the crushing of container trucks for a long time, resulting in cracks and potholes on the road surface. When cracks and potholes appear on the road surface, it often affects the current traffic flow at the intersection. Therefore, we proposed a hybrid construction method and system based on AI artificial intelligence reality digital scene. Summary of the invention

[0003] In order to solve the above technical problems, a method and system for hybrid construction of realistic digital scenes based on AI artificial intelligence are provided. This technical solution solves the above problems.

[0004] To achieve the above objectives, the technical solution adopted by the present invention is: a hybrid construction method of realistic digital scenes based on AI artificial intelligence, the construction method includes: Use drones to scan and identify traffic intersections to obtain three-dimensional point cloud data; Preprocess the collected data, upload the data to the modeling software, construct the intersection, and build the intersection in the computer; Obtain the current traffic flow at the intersection, and based on the traffic flow, obtain the frequency of trucks; According to the frequency of truck collection, the stress condition of the road surface is calculated, and the corresponding road potholes and cracks are constructed on the road surface of the traffic intersection model according to the stress condition; Based on the constructed digital intersection scene, the traffic flow and road potholes at the intersection are simulated and predicted, and adjustments are made in the real environment.

[0005] Preferably, the drone is equipped with a three-dimensional laser scanner. The drone flies above the intersection and uses the three-dimensional laser scanner to scan the intersection. Based on measuring the position of the intersection point between the laser beam and the surface of the object, the three-dimensional point cloud data of the intersection is obtained, the obtained data is preprocessed, and the processed data is uploaded to the modeling software to construct the intersection. The three-dimensional point cloud data preprocessing includes point cloud filtering, point cloud key point extraction and point cloud registration.

[0006] Preferably, the intersection construction processes the processed data based on the Poisson reconstruction algorithm, constructs it in the modeling software, constructs an octree according to the density of the point cloud data, and defines a function for the octree, and the function form is: Where X(q) is an indicator function used to define whether a point q in space is located on the surface of an object M, q is a point in the three-dimensional point cloud data space, and M is the measured object; Construct a vector field through point cloud data, use the vector field to solve Poisson's equation, extract isosurfaces, and complete reconstruction; The vector field formula is: Where V is the normal vector of all P in the point cloud data A collection of, p is a point in the point cloud, w is a point element, is the normal vector of point P, n is the domain, that is, other sets in the spatial range around point P. The extracted isosurface is integrated with the original point data to form a complete three-dimensional intersection model.

[0007] Preferably, based on the intersection monitoring, the traffic flow data of the historical intersection is obtained, and the traffic flow data of the monitored intersection is obtained by image analysis. The number of times the truck collection appears at the current intersection in a unit time is counted, and this data is used as the first group of data. Multiple groups of data samples are obtained as the data set, and the average value of the truck collection in the data set is obtained. The frequency calculation formula is: Where L is the frequency of the truck, i is the number of times the truck appears, and t is the unit time.

[0008] Preferably, the pressure value caused by a container truck on the road surface is calculated. Before the calculation, the weight of the container truck when fully loaded is obtained in advance, and an estimate is made based on the load limit of the container truck. The calculation formula is: F=G=mo Where G is gravity, m is mass, o is the speed of the truck passing over the road, o is based on the average speed of the truck passing over the road, and F is the pressure on the road; The formula for calculating the pressure on the road surface is: P is the pressure on the road surface, F is the pressure on the road surface, and S is the force area, where the force area is the area of ​​the road surface rolled over by the tire. The contact surface between the tire and the ground is a rectangle or ellipse, and the force area is calculated based on the width of the tire and the predicted contact length.

[0009] Preferably, the situation of cracks and potholes on the road surface is estimated, wherein the factors causing potholes on the road surface include the material structure coefficient of the road surface, the frequency of the occurrence of container trucks at the traffic intersection and the construction quality coefficient, wherein the material structure influencing factors of the road surface are obtained based on the construction standard criteria of the road surface, and the pothole assessment formula is: Among them, R is the coefficient of the road material's pressure resistance, L is the frequency of trucks, P is the pressure on the road surface, B is the construction quality coefficient, and H is the probability of potholes on the road surface. The road texture effects are constructed based on modeling software, including cracks and potholes.

[0010] Preferably, a deep learning algorithm is used in a computer to construct crack and pothole effects on a traffic road surface based on the obtained pothole probability, and the constructed crack and pothole effects are verified to check whether the constructed crack and pothole effects are consistent with the actual scenario.

[0011] Preferably, different data set features are verified, and the verification formula is: Where Z is a given feature Under the condition of , whether the pavement input data set belongs to the normal crack analogy, is the distance threshold between cracks and potholes on the road and the roadside in the actual scene, The parameter vector of the model is used to input the characteristics of the road surface crack and pothole effect dataset to determine whether the currently established road surface effect is consistent with the actual situation.

[0012] Based on AI artificial intelligence reality digital scene hybrid construction system, the scene hybrid construction system includes: modeling module, road force analysis module, prediction module and acquisition module, among which the modeling module uses computer as the carrier to carry out hybrid construction of scenes, the road force analysis module analyzes the force of the road surface, the prediction module predicts and analyzes the actual intersection conditions based on the constructed digital scene, and the acquisition module obtains the data of the actual intersection and constructs it into a data set.

[0013] Preferably, the acquisition module collects the conditions of the traffic intersection in real time based on the drone, and obtains the three-dimensional point cloud data of the intersection. The acquisition module also obtains the image data of the intersection based on the monitoring of the intersection, and processes the collected images based on the image analysis method.

[0014] Compared with the prior art, the present invention has the following beneficial effects: The present invention uses a drone to scan three-dimensional point cloud data of a traffic intersection, uploads it to a computer to build a scene for the current intersection, and obtains the frequency of appearance of trucks at the current intersection, analyzes the pressure on the current road surface in real time, and combines the analyzed data to simulate the scene of cracks and potholes in the actual scene in the built intersection scene. Based on the built intersection scene, the traffic flow at the current intersection is predicted, and according to the predicted traffic flow, the actual intersection is adjusted and controlled in time to reduce the traffic flow. The crack scene of the road surface can be effectively built, the details in the exit can be improved, and people can better control auxiliary traffic and provide convenience. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 Build a method flow chart for the present invention; Figure 2 Build a step flow chart for the scenario of the present invention; Figure 3 The present invention is a flow chart for calculating the pavement stress condition; Figure 4 This is a flow chart of predicting traffic flow at an intersection according to the present invention; Figure 5 This is a block diagram of the system for hybrid construction of the scenarios of the present invention. DETAILED DESCRIPTION

[0016] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0017] Reference Figure 1 As shown, a hybrid construction method of a reality digital scene based on AI artificial intelligence is provided, and the construction method includes: Use drones to scan and identify traffic intersections to obtain three-dimensional point cloud data; Preprocess the collected data, upload the data to the modeling software, construct the intersection, and build the intersection in the computer; Obtain the current traffic flow at the intersection, and based on the traffic flow, obtain the frequency of trucks; According to the frequency of truck collection, the stress condition of the road surface is calculated, and the corresponding road potholes and cracks are constructed on the road surface of the traffic intersection model according to the stress condition; Based on the constructed digital intersection scene, the traffic flow and road potholes at the intersection are simulated and predicted, and adjustments are made in the real environment.

[0018] This application predicts road damage, such as potholes and cracks, based on vehicle frequency and force analysis, and can perform maintenance in a timely manner to avoid traffic accidents and intersection congestion caused by road deterioration. This preventive maintenance can significantly extend the service life of the road and reduce maintenance costs. The prediction can help identify potential hidden dangers. Based on the prediction results, the traffic management department can make scientific and reasonable decisions to manage traffic intersections and promote the intelligent management of urban traffic.

[0019] Reference Figure 2 As shown, the UAV is equipped with a 3D laser scanner. The UAV flies above the intersection and uses the 3D laser scanner to scan the intersection. Based on measuring the position of the intersection point between the laser beam and the surface of the object, the 3D point cloud data of the intersection is obtained, the obtained data is preprocessed, and the processed data is uploaded to the modeling software to construct the intersection. The 3D point cloud data preprocessing includes point cloud filtering, point cloud key point extraction and point cloud registration.

[0020] The intersection construction is based on the Poisson reconstruction algorithm. The processed data is processed and constructed in the modeling software. According to the density of the point cloud data, an octree is constructed and a function is defined for the octree. The function form is: Where X(q) is an indicator function used to define whether a point q in space is located on the surface of an object M, q is a point in the three-dimensional point cloud data space, and M is the measured object; Construct a vector field through point cloud data, use the vector field to solve Poisson's equation, extract isosurfaces, and complete reconstruction; The vector field formula is: Where V is the normal vector of all P in the point cloud data A collection of, p is a point in the point cloud, w is a point element, is the normal vector of point P, n is the domain, that is, other sets in the spatial range around point P. The extracted isosurface is integrated with the original point data to form a complete three-dimensional intersection model.

[0021] In this application, the three-dimensional point cloud data is a vector combination set in a three-dimensional coordinate system, which has high flexibility and variability in data density. It is scanned by a three-dimensional laser scanner configured on a drone, and the method of processing the three-dimensional point cloud data is a prior art, which will not be elaborated on here. The Poisson reconstruction algorithm is essentially an implicit function surface reconstruction algorithm, which uses a surface to distinguish between inside and outside in space, which can be intuitively understood as outside and inside of the surface, and the inner and outer surfaces are represented by 0 and 1, that is, if an element belongs to this set, it is 1, and if an element does not belong to this set, it is 0. The function is used to realize gradient calculation of all indicator functions inside the space, and the Poisson equation is solved to extract the isosurface to obtain the surface of the object. Solving the Poisson equation using a vector field is a prior art, which will not be elaborated on here.

[0022] Reference Figure 3 As shown, based on the intersection monitoring, the traffic flow data of the historical intersection is obtained, and the traffic flow data of the monitored intersection is obtained by image analysis. In a unit time, the number of times the truck collection appears at the current intersection is counted. This data is used as the first group of data, and multiple groups of data samples are obtained as the data set. The average value of the truck collection in the data set is obtained, and the frequency calculation formula is: Where L is the frequency of the truck, i is the number of times the truck appears, and t is the unit time.

[0023] Calculate the pressure value caused by a container truck on the road. Before calculation, obtain the weight of the fully loaded container truck in advance and make an estimate based on the load limit of the container truck. The calculation formula is: F=G=mo Where G is gravity, m is mass, o is the speed of the truck passing over the road, o is based on the average speed of the truck passing over the road, and F is the pressure on the road; The formula for calculating the pressure on the road surface is: P is the pressure on the road surface, F is the pressure on the road surface, and S is the force area, where the force area is the area of ​​the road surface rolled over by the tire. The contact surface between the tire and the ground is a rectangle or ellipse, and the force area is calculated based on the width of the tire and the predicted contact length.

[0024] Estimate the occurrence of cracks and potholes on the road surface. The factors causing potholes include the material structure coefficient of the road surface, the frequency of the appearance of container trucks at the traffic intersection, and the construction quality coefficient. The material structure influencing factors of the road surface are obtained based on the construction standard criteria of the road surface. The pothole assessment formula is: Among them, R is the coefficient of the road material's pressure resistance, L is the frequency of trucks, P is the pressure on the road surface, B is the construction quality coefficient, and H is the probability of potholes on the road surface. The road texture effects are constructed based on modeling software, including cracks and potholes.

[0025] In the present application, since container trucks include many types and a wide range of categories, and the situations involved are different, the container trucks involved in the present application are all uniformly conceived as trucks for transporting construction materials, wherein the parameters of the container trucks can be changed according to the actual scene conditions, and the image analysis method is a prior art and will not be elaborated on here, and the speed of the container trucks passing through the road surface is obtained based on traffic monitoring, and the speed of the container trucks passing through the intersection is less than 15km / h. By accurately simulating the cracks and potholes on the real road surface, the complexity and diversity of the actual roads can be highly restored, making the simulated environment closer to the real scene, and the realistic road surface effect can enhance the observer's visual experience. In the road maintenance stage, by simulating the development process of road surface diseases, the evolution trend of the diseases can be predicted, providing a scientific basis for formulating reasonable maintenance plans, and improving maintenance efficiency and effectiveness.

[0026] Using deep learning algorithms in computers, we construct crack and pothole effects on traffic roads based on the obtained pothole probability, and verify the constructed crack and pothole effects to see whether they are consistent with the actual scene. Select the deep learning network architecture according to the task requirements, use the training set and validation set to train the model, monitor the changes in the loss function and accuracy index during the training process, use the test set to evaluate the performance of the model, and use GANs to generate images similar to real cracks and potholes to further expand the training data set. GANs consists of a generator and a discriminator, and generates high-quality images through adversarial training. The obtained road pothole probability is simulated and constructed to build the road crack and pothole effect data set characteristics under different scenarios. Verify the characteristics of different data sets, and the verification formula is: Where Z is a given feature Under the condition of , whether the pavement input data set belongs to the normal crack analogy, is the distance threshold between cracks and potholes on the road and the roadside in the actual scene, The parameter vector of the model is used to input the characteristics of the road surface crack and pothole effect dataset to determine whether the currently established road surface effect is consistent with the actual situation.

[0027] In this application, the constructed road surface crack and pothole effects are randomly generated. On the road surface, since the vehicle is located in the middle motor vehicle road, and the two sides of the road are roads for non-motor vehicles, the probability of cracks and potholes on both sides of the road is extremely low and is not considered in this application. The distance threshold to the roadside is the width value of the non-motor vehicle lanes on both sides. The randomly generated road surface crack and pothole effects are verified to see whether they conform to the actual road conditions.

[0028] Reference Figure 4 As shown, a traffic flow prediction model is constructed, and the data is analyzed based on the real-time traffic flow data. The calculation formula for traffic flow is: U=A*D Among them, U is the traffic flow data of the current intersection, A is the traffic flow of the intersection under natural environment, that is, the total number of vehicles passing through the intersection per unit time, and D is the external influencing factor; External factors include rush hour, weather, accidents, road construction at intersections and potholes. The traffic volume during rush hour is higher than the average, while the traffic volume increases during rainy and snowy days. Accidents, road construction at intersections and potholes cause the traffic volume to decrease. The calculation formula of the external influencing factor is: D=J 时间 *J 天气 *J 事故 *J 施工 *H Among them J 时间 is the time factor, J 天气 is the weather factor, J 事故 is the accident factor, J 施工 is the construction factor, H is the road surface probability, and the obtained traffic flow data set is substituted into the model for verification.

[0029] Based on the constructed traffic flow prediction model, the traffic flow situation is simulated in the digital scene. Based on the simulation results, the traffic flow at the current intersection is controlled and adjusted. The traffic flow is proportional to the occurrence of accidents. The more vehicles there are, the more likely traffic accidents are to occur. During the time period of heavy traffic, commanders are deployed to direct traffic to reduce the probability of accidents, and the road surface is constructed during the time period of light traffic.

[0030] In this application, the traffic flow prediction model can be used to predict the traffic flow in the future in real time. In the time period when the traffic flow is predicted to increase significantly, the traffic management department can take measures in advance, such as increasing the timing of traffic lights, adjusting lane allocation, setting temporary traffic signs, etc., to ease traffic pressure and reduce the probability of traffic accidents. According to the traffic flow prediction results, the traffic management department can reasonably allocate police resources to ensure that there are enough police forces to patrol the road and deal with emergencies during peak traffic hours. Through scientific traffic control measures, the signal light timing and lane allocation at the intersection can be optimized, the road traffic efficiency can be improved, and the waiting time of vehicles can be reduced, thereby alleviating traffic congestion. The influencing factors of the road include traffic load, environmental factors, material quality and design and construction. Among them, the traffic load factor is the most important reason affecting the quality of the road. Other influencing factors have been considered and measured in the process of road planning, design and construction, and the impact is low. Therefore, they are not considered in this article. During road driving, it is impossible to measure the situation of container trucks running. If container trucks run frequently, the road is more likely to be damaged.

[0031] Reference Figure 5 As shown, a system for hybrid construction of realistic digital scenes based on AI artificial intelligence is provided. The system for hybrid construction of scenes includes: a modeling module, a pavement force analysis module, a prediction module and a collection module. The modeling module performs hybrid construction of scenes based on a computer as a carrier, the pavement force analysis module analyzes the pavement force, the prediction module predicts and analyzes the actual intersection conditions based on the constructed digital scenes, and the collection module obtains the data of the actual intersections for collection and constructs a data set.

[0032] The acquisition module collects the conditions of traffic intersections in real time based on drones and obtains three-dimensional point cloud data of the intersections. The acquisition module also obtains image data of the intersection based on intersection monitoring and processes the collected images based on image analysis.

[0033] The acquisition module of this application uses drones to collect the conditions of traffic intersections in real time, and can quickly obtain three-dimensional point cloud data of intersections. This acquisition method is not only efficient, but also can cover a wider area and capture more details, providing rich data support for subsequent modeling and prediction. It also obtains image data through the monitoring equipment at the intersection and processes the image based on image analysis technology. This method can reflect the traffic conditions at the intersection in real time and provide an intuitive and accurate basis for traffic management. The collected three-dimensional point cloud data and monitoring image data complement each other to form a multi-dimensional description of the intersection conditions. This data combination method improves the accuracy and comprehensiveness of the data. The pavement force analysis module conducts an in-depth analysis of the pavement's force conditions, can evaluate the pavement's bearing capacity and stability, and realize rapid data acquisition, processing and analysis.

[0034] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A hybrid construction method for realistic digital scenes based on AI artificial intelligence, characterized in that: The construction methods include: Use drones to scan and identify traffic intersections to obtain three-dimensional point cloud data; Preprocess the collected data, upload the data to the modeling software, construct the intersection, and build the intersection in the computer; Obtain the current traffic flow at the intersection, and based on the traffic flow, obtain the frequency of trucks; According to the frequency of truck collection, the stress condition of the road surface is calculated, and the corresponding road potholes and cracks are constructed on the road surface of the traffic intersection model according to the stress condition; Based on the constructed digital intersection scene, the traffic flow and road potholes at the intersection are simulated and predicted, and adjustments are made in the real environment.

2. The method for hybrid construction of AI artificial intelligence reality digital scene according to claim 1 is characterized in that: The drone is equipped with a 3D laser scanner. The drone flies above the intersection and uses the 3D laser scanner to scan the intersection. Based on measuring the position of the intersection point between the laser beam and the surface of the object, the 3D point cloud data of the intersection is obtained. The obtained data is preprocessed and uploaded to the modeling software to construct the intersection. The 3D point cloud data preprocessing includes point cloud filtering, point cloud key point extraction and point cloud registration.

3. The method for hybrid construction of AI artificial intelligence reality digital scene according to claim 2 is characterized in that: The intersection construction is based on the Poisson reconstruction algorithm. The processed data is processed and constructed in the modeling software. According to the density of the point cloud data, an octree is constructed and a function is defined for the octree. The function form is: Where X(q) is an indicator function used to define whether a point q in space is located on the surface of an object M, q is a point in the three-dimensional point cloud data space, and M is the measured object; Construct a vector field through point cloud data, use the vector field to solve Poisson's equation, extract isosurfaces, and complete reconstruction; The vector field formula is: Where V is the normal vector of all P in the point cloud data A collection of, p is a point in the point cloud, w is a point element, is the normal vector of point P, n is the domain, that is, other sets in the spatial range around point P. The extracted isosurface is integrated with the original point data to form a complete three-dimensional intersection model.

4. The method for hybrid construction of AI-based real-world digital scenes according to claim 1 is characterized in that: Based on the intersection monitoring, the traffic flow data of the historical intersection is obtained. The traffic flow data of the monitored intersection is obtained by image analysis. The number of times the trucks appear at the current intersection in a unit time is counted. This data is used as the first set of data. Multiple sets of data samples are obtained as the data set. The average value of the trucks appearing in the data set is obtained. The frequency calculation formula is: Where L is the frequency of the truck, i is the number of times the truck appears, and t is the unit time.

5. The method for hybrid construction of AI artificial intelligence reality digital scene according to claim 4 is characterized in that: Calculate the pressure value caused by a container truck on the road. Before calculation, obtain the weight of the fully loaded container truck in advance and make an estimate based on the load limit of the container truck. The calculation formula is: F=G=mo Where G is gravity, m is mass, o is the speed of the truck passing over the road, o is based on the average speed of the truck passing over the road, and F is the pressure on the road; The formula for calculating the pressure on the road surface is: P is the pressure on the road surface, F is the pressure on the road surface, and S is the force area, where the force area is the area of ​​the road surface rolled over by the tire. The contact surface between the tire and the ground is a rectangle or ellipse, and the force area is calculated based on the width of the tire and the predicted contact length.

6. The method for hybrid construction of AI-based reality digital scenes according to claim 5 is characterized in that: Estimate the occurrence of cracks and potholes on the road surface. The factors causing potholes include the material structure coefficient of the road surface, the frequency of the appearance of container trucks at the traffic intersection, and the construction quality coefficient. The material structure influencing factors of the road surface are obtained based on the construction standard criteria of the road surface. The pothole assessment formula is: Among them, R is the coefficient of the road material's pressure resistance, L is the frequency of trucks, P is the pressure on the road surface, B is the construction quality coefficient, and H is the probability of potholes on the road surface. The road texture effects are constructed based on modeling software, including cracks and potholes.

7. The method for hybrid construction of AI-based real-world digital scenes according to claim 1 is characterized in that: A deep learning algorithm is used in computers to construct the crack and pothole effects on the traffic road based on the obtained pothole probability. The constructed crack and pothole effects are then verified to see whether they are consistent with the actual scenario.

8. The method for hybrid construction of AI-based reality digital scenes according to claim 7 is characterized in that: Verify the characteristics of different data sets, and the verification formula is: Where Z is a given feature Under the condition of , whether the pavement input data set belongs to the normal crack analogy, is the distance threshold between cracks and potholes on the road and the roadside in the actual scene, The parameter vector of the model is used to input the characteristics of the road surface crack and pothole effect dataset to determine whether the currently established road surface effect is consistent with the actual situation.

9. Based on AI artificial intelligence reality digital scene hybrid construction system, it is characterized by: The scene hybrid construction system includes: a modeling module, a pavement force analysis module, a prediction module and a collection module. The modeling module uses a computer as a carrier to perform hybrid construction of scenes, the pavement force analysis module analyzes the pavement force, the prediction module predicts and analyzes the actual intersection conditions based on the constructed digital scene, and the collection module obtains the data of the actual intersection and constructs it into a data set.

10. The AI ​​artificial intelligence-based reality digital scene hybrid construction system according to claim 9 is characterized in that: The acquisition module collects the conditions of traffic intersections in real time based on drones and obtains three-dimensional point cloud data of the intersections. The acquisition module also obtains image data of the intersection based on intersection monitoring and processes the collected images based on image analysis.

Images