Traffic signal lamp control analogue simulation method, system and device and storage medium

Abstract

The invention relates to the technical field of intelligent traffic, and discloses a traffic signal lamp control analogue simulation method, system and device and a storage medium. The method comprises the following steps: acquiring oblique photography image data and road traffic data, and carrying out data preprocessing to obtain processed data; performing feature extraction and recognition on the processed data based on a 3D Gauss mask technology and a deep learning technology to obtain geometric features and size information of the signal lamp; constructing a signal lamp timing model, and training the signal lamp timing model through a preset optimization algorithm; and performing intersection traffic three-dimensional analogue simulation according to the geometrical characteristics, the size information and the trained signal lamp timing model. According to the invention, the accuracy of signal lamp identification is improved through the 3D Gauss mask technology, and the intelligent level of signal lamp control is enhanced by adopting the deep learning technology to carry out signal lamp identification. The traffic flow efficiency and safety of traffic management are improved through construction and optimization of the signal lamp timing model.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation technology, and in particular to a traffic light control simulation method, system, device and storage medium. Background Art

[0002] Oblique photogrammetry is a method of obtaining three-dimensional information of the earth's surface using oblique photography technology. It is widely used in urban planning, environmental monitoring, disaster management, construction engineering, and cultural heritage protection. It generates high-precision three-dimensional models and terrain data by photographing ground objects at different angles and combining computer vision and image processing technology. The importance of oblique photogrammetry lies in its efficiency and accuracy. It can quickly obtain data from a large area, support the development of smart cities, and provide intuitive three-dimensional visualization for decision-making, promoting sustainable development.

[0003] Traffic light control simulation is an indispensable tool in urban traffic management, and its necessity is reflected in many aspects. First, through simulation, the configuration and control strategy of traffic lights can be evaluated under different traffic flow and road conditions, thereby optimizing traffic flow and reducing congestion and accidents. Secondly, simulation provides a safe experimental environment for traffic engineers to test new technologies and control algorithms without high-risk experiments on actual roads. In addition, simulation results can provide data support, achieve more scientific traffic management decisions, and improve the efficiency and safety of urban transportation systems. However, the current relevant traffic light control simulation technology still has problems such as low accuracy of signal light recognition and difficulty in improving the overall efficiency and safety of urban transportation systems. Summary of the invention

[0004] The main purpose of the present invention is to provide a traffic light control simulation method, system, device and storage medium, aiming to solve at least one of the above-mentioned technical problems.

[0005] To achieve the above object, the present invention provides a traffic light control simulation method, comprising:

[0006] Obtain oblique photography image data and road traffic data;

[0007] Performing data preprocessing on the oblique photography image data and the road traffic data to obtain processed data;

[0008] Based on 3D Gauss mask technology combined with deep learning technology, feature extraction and recognition are performed on the processed data to obtain geometric features and size information of the traffic light;

[0009] Constructing a traffic light timing model, and training the traffic light timing model through a preset optimization algorithm;

[0010] A three-dimensional simulation of intersection traffic is performed based on the geometric features and size information and the trained signal light timing model.

[0011] In some embodiments, the acquiring of oblique photography image data and road traffic data includes:

[0012] Obtain oblique photography image data based on oblique photogrammetry technology;

[0013] Obtaining three-dimensional point cloud data according to the oblique photography image data;

[0014] Collecting traffic light location information, traffic light status data, and road and traffic flow data;

[0015] The location information of the traffic light, the state data of the traffic light, and the road and traffic flow data are used as road traffic data.

[0016] In some embodiments, the data preprocessing of the oblique photography image data and the road traffic data includes:

[0017] Performing denoising, correction and enhancement processing on the oblique photography image data;

[0018] Cleaning, correcting and formatting the road traffic data;

[0019] Perform denoising, filtering, coordinate transformation and region segmentation on 3D point cloud data.

[0020] In some embodiments, the 3D Gauss mask technology combined with deep learning technology is used to extract and identify features of the processed data to obtain geometric features and size information of the signal light, including:

[0021] Based on the 3D Gauss mask technology, the traffic light is subjected to individual processing according to the processed data to obtain a traffic light model;

[0022] Deep learning technology is used to identify the type and direction of the traffic light model to obtain the geometric characteristics and size information of the traffic light.

[0023] In some embodiments, constructing a traffic light timing model and training the traffic light timing model using a preset optimization algorithm includes:

[0024] Construct a signal light timing model based on the preset timing strategy;

[0025] A preset optimization algorithm is used to adjust the parameters of the traffic light timing model to train the traffic light timing model.

[0026] In some embodiments, the signal light timing model includes: a fixed signal light timing model, a dynamic signal light timing model, and an adaptive signal light timing model.

[0027] In some embodiments, the three-dimensional simulation of intersection traffic based on the geometric features and size information and the trained signal light timing model includes:

[0028] Constructing a three-dimensional model of the intersection based on the geometric features and dimensional information based on simulation software;

[0029] The traffic flow and signal light timing parameters of the three-dimensional model of the intersection are set according to the trained signal light timing model to perform three-dimensional simulation of intersection traffic.

[0030] In addition, to achieve the above-mentioned purpose, the present invention also proposes a traffic light control simulation system, comprising:

[0031] Data acquisition module, used to obtain oblique photography image data and road traffic data;

[0032] A data preprocessing module, used to perform data preprocessing on the oblique photography image data and the road traffic data to obtain processed data;

[0033] A feature extraction and recognition module, used to extract and recognize features of the processed data based on 3D Gauss mask technology combined with deep learning technology to obtain geometric features and size information of the signal light;

[0034] A signal light timing module, used to construct a signal light timing model and train the signal light timing model through a preset optimization algorithm;

[0035] The three-dimensional simulation module is used to perform three-dimensional simulation of intersection traffic based on the geometric features and size information and the trained signal light timing model.

[0036] In addition, to achieve the above-mentioned purpose, the present invention also proposes an electronic device, which includes: a memory, a processor, and a traffic light control simulation program stored in the memory and executable on the processor, wherein the traffic light control simulation program is configured to implement the traffic light control simulation method as described above.

[0037] In addition, to achieve the above-mentioned purpose, the present invention also proposes a storage medium, which stores a traffic light control simulation program, and the traffic light control simulation program is used to enable the processor to implement the traffic light control simulation method described above when executing it.

[0038] The present invention provides a traffic light control simulation method, comprising: obtaining oblique photography image data and road traffic data; performing data preprocessing on the oblique photography image data and road traffic data to obtain processed data; performing feature extraction and recognition on the processed data based on 3D Gauss mask technology combined with deep learning technology to obtain geometric features and size information of the traffic light; constructing a traffic light timing model, and training the traffic light timing model through a preset optimization algorithm; and performing three-dimensional simulation of intersection traffic according to the geometric features and size information and the trained traffic light timing model. The present invention effectively extracts and enhances the features of the traffic light through 3D Gauss mask technology, improves the accuracy of traffic light recognition, can reduce unnecessary details while retaining important structural information, uses deep learning technology to identify the type of traffic light entity and calculate the direction, and enhances the intelligent level of traffic light control. The traffic flow efficiency and safety of traffic management are improved through the construction and optimization of the traffic light timing model, the realization of three-dimensional simulation provides a safe experimental environment, and the simulation results provide data support for traffic management decisions, which is conducive to improving the overall efficiency and safety of the urban transportation system. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A schematic diagram of the structure of an electronic device in a hardware operating environment involved in an embodiment of the present invention;

[0040] Figure 2 A schematic diagram of a flow chart of an embodiment of a traffic light control simulation method of the present invention;

[0041] Figure 3 This is an example flow chart of an embodiment of the present invention;

[0042] Figure 4 This is a schematic diagram showing the effect before image processing involved in the embodiment of the present invention;

[0043] Figure 5 A schematic diagram showing the effect of image processing involved in an embodiment of the present invention;

[0044] Figure 6 A schematic diagram of a traffic light model in oblique photography according to an embodiment of the present invention;

[0045] Figure 7 A schematic diagram of a signal light timing model involved in an embodiment of the present invention;

[0046] Figure 8 A schematic diagram of a three-dimensional simulation involved in an embodiment of the present invention;

[0047] Fig. 9 This is a structural block diagram of an embodiment of a traffic signal light control simulation system of the present invention.

[0048] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0051] In addition, the descriptions of "first", "second", etc. in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in the field to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0052] Reference Figure 1 , Figure 1 The figure is a schematic diagram of the structure of an electronic device of the hardware operating environment involved in the embodiment of the present invention.

[0053] like Figure 1As shown, the electronic device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM memory) or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0054] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the electronic device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0055] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a traffic light control simulation program.

[0056] exist Figure 1 In the electronic device shown, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the electronic device of the present invention can be set in the electronic device, and the electronic device calls the traffic light control simulation program stored in the memory 1005 through the processor 1001, and executes the traffic light control simulation method provided in an embodiment of the present invention.

[0057] The present invention provides a traffic light control simulation method, system, device and storage medium.

[0058] The embodiment of the present invention provides a traffic signal light control simulation method, referring to Figure 2 , Figure 2 It is a flow chart of an embodiment of a traffic light control simulation method of the present invention.

[0059] like Figure 2As shown, the traffic light control simulation method includes:

[0060] Step S100: Obtaining oblique photography image data and road traffic data;

[0061] Step S200: performing data preprocessing on the oblique photography image data and the road traffic data to obtain processed data;

[0062] Step S300: extracting and identifying features of the processed data based on 3D Gauss mask technology combined with deep learning technology to obtain geometric features and size information of the traffic light;

[0063] Step S400: constructing a traffic light timing model, and training the traffic light timing model through a preset optimization algorithm;

[0064] Step S500: Perform three-dimensional intersection traffic simulation based on the geometric features and size information and the trained traffic light timing model.

[0065] It should be noted that the execution subject in this embodiment may be an electronic device, which may be a computer device with data processing functions, or other devices that can achieve the same or similar functions. This embodiment does not limit this. In this embodiment, a computer device is used as an example for explanation.

[0066] It is understandable that this embodiment is explained by taking the simulation of traffic light control based on oblique photogrammetry data as an example. Applied to the field of intelligent transportation system (ITS) and computer vision technology, the three-dimensional spatial information of traffic lights is obtained by oblique photography, and combined with the principles of traffic engineering and simulation technology, traffic signal control can be efficiently analyzed and optimized, thereby improving the efficiency and safety of traffic flow management. At the same time, combined with artificial intelligence and machine learning technology, the intelligence of signal control strategies can be further enhanced, which will help modernize urban traffic management. The method described in this embodiment is explained below in conjunction with specific steps.

[0067] In one embodiment, obtaining oblique photography image data and road traffic data includes: obtaining oblique photography image data based on oblique photography measurement technology; obtaining three-dimensional point cloud data based on the oblique photography image data; collecting location information of traffic lights, status data of traffic lights, and road and traffic flow data; and using the location information of traffic lights, status data of traffic lights, and road and traffic flow data as road traffic data.

[0068] Specifically, Figure 3As shown in the figure, data preparation: collect various types of data, including high-resolution oblique photography images, 3D point cloud data, location information of traffic lights, status data, and road and traffic flow data, etc. These data provide the basis for subsequent analysis and modeling. It should be noted that oblique photogrammetry technology supports efficient data processing and visualization by obtaining 3D surface information, providing a basis for the configuration of traffic lights and optimization of control strategies.

[0069] Exemplarily, oblique photogrammetry is an advanced aerial photography technology that combines aerial photography and oblique photogrammetry principles to collect ground images from different angles (including vertical and oblique) through a multi-angle camera system mounted on a drone or other aerial platform. The oblique photography images collected by this technology can provide richer ground information, especially the side details and three-dimensional structure of buildings. For example, oblique photogrammetry technology usually uses multiple high-resolution digital cameras that shoot at a certain angle (usually between 15 and 45 degrees) relative to the ground, and also includes one or more vertical cameras. These cameras work synchronously to obtain image data of the same scene from multiple angles, and use multi-angle image data to generate three-dimensional point cloud data.

[0070] In one embodiment, data preprocessing is performed on the oblique photography image data and the road traffic data, including: denoising, correcting and enhancing the oblique photography image data; cleaning, correcting and formatting the road traffic data; and denoising, filtering, coordinate transformation and region segmentation of the three-dimensional point cloud data.

[0071] Specifically, Figure 3 As shown in Figure 1, data preprocessing: the collected data is cleaned, corrected and formatted to ensure high data quality. For example, image data (oblique photography data) is processed by denoising, correction and enhancement, and point cloud data is processed by denoising, filtering, coordinate transformation and region segmentation.

[0072] For example, the oblique photography image data processing may include denoising, correction, registration, etc. to ensure image quality, generate three-dimensional point cloud data using multi-angle image data, and then perform texture mapping to finally construct a three-dimensional model with real texture. It is understandable that if Figure 4 and Figure 5 As shown in the figure, the image effect is clearer after data preprocessing.

[0073] In one embodiment, feature extraction and recognition are performed on the processed data based on 3D Gauss mask technology combined with deep learning technology to obtain geometric features and size information of the traffic light, including: singulating the traffic light according to the processed data based on 3D Gauss mask technology to obtain a traffic light model; and identifying the type and direction of the traffic light model using deep learning technology to obtain the geometric features and size information of the traffic light.

[0074] Specifically, Figure 3 As shown in the figure, feature extraction and model construction: the 3D Gauss mask method is used to individually process the traffic lights, and the deep learning technology is combined to identify the type and direction of the traffic lights, and the following can be obtained: Figure 6 The traffic light model in the oblique photography shown. The geometric features and size information of the traffic light are extracted by training a deep neural network.

[0075] For example, the 3D Gauss mask technology is used to perform individual processing on the traffic lights, and the identification and segmentation of the traffic lights in the image processing process are optimized. The following steps can be used: acquiring an image based on the processed oblique photography image data, and performing denoising, contrast enhancement and other processing on the image to improve the accuracy of subsequent processing; converting the image from the RGB color space to a color space more suitable for processing traffic lights, such as HSV or Lab; applying 3D The Gauss masking technique processes the image to smooth the signal light area in the image; defines the color threshold range of the red and green signal lights, and divides the smoothed image into different areas; uses contour detection algorithms (such as the Canny operator) to find the outline of the signal light in the segmented image; applies morphological operations (such as dilation and erosion) to optimize the segmentation results, remove small objects and fill holes; extracts the contours of the segmented image to find the possible location of the signal light; filters out the contours of non-signal lights based on the size, shape and other features of the contour, and selects the real signal light contour; performs individualization processing on each detected signal light contour, that is, determines the boundary of the signal light and extracts a separate signal light object; marks the identified and segmented signal light area on the original image, and adds corresponding text labels. Through the above steps, the signal light can be individually processed using the 3D Gauss masking technique, which can improve the accuracy and stability of signal light recognition, especially in complex scenes, and can effectively smooth the image, reduce noise and edge artifacts, so as to better identify and segment the signal light.

[0076] It should be noted that in this embodiment, 3D Gauss mask technology is used to perform individual processing on the traffic lights. The application of 3D Gauss mask technology can effectively extract and enhance the characteristics of traffic lights, improve the accuracy of traffic light recognition, and reduce unnecessary details while retaining important structural information. In addition, a deep learning model is designed in combination with deep learning technology for traffic light entity type recognition and direction calculation, providing technical support for the realization of intelligent transportation systems and enhancing the intelligent level of traffic light control.

[0077] In one embodiment, a traffic light timing model is constructed and trained by a preset optimization algorithm, including: constructing a traffic light timing model based on a preset timing strategy; and adjusting parameters of the traffic light timing model by a preset optimization algorithm to train the traffic light timing model.

[0078] In one embodiment, the traffic light timing model includes: a fixed traffic light timing model, a dynamic traffic light timing model and an adaptive traffic light timing model.

[0079] Specifically, Figure 7 As shown, the signal light timing model: construct a signal light timing model, select a suitable timing strategy (such as fixed, dynamic, adaptive), and adjust the model parameters through a preset optimization algorithm to improve traffic flow efficiency. In one example, the preset optimization algorithm includes but is not limited to a genetic optimization algorithm. By constructing a signal light timing model and using a genetic optimization algorithm to improve traffic flow efficiency.

[0080] It should be noted that the signal light timing model is a mathematical model or algorithm used in the field of traffic engineering to determine the duration of each phase (such as green light, red light, and yellow light) of traffic lights in different time periods. The purpose is to optimize traffic flow, reduce vehicle waiting time, improve road capacity, and ensure traffic safety. The key elements of the signal light timing model include signal cycle length, phase difference, green light time, red light time, and yellow light time. Traffic light timing models usually include the following types: fixed timing model: the timing of the traffic lights in this model is fixed and does not change with the change of traffic flow. It is suitable for intersections with little change in traffic flow; adaptive timing model: this model dynamically adjusts the timing of the traffic lights according to the changes in traffic flow monitored in real time. Common adaptive timing models adjust the timing of the traffic lights according to the number and speed of detected vehicles in vehicle sensing; traffic prediction model: uses historical data and machine learning algorithms to predict future traffic flow and adjust the timing of the traffic lights accordingly; intelligent timing model: combines advanced intelligent transportation system (ITS) technologies such as automatic vehicle identification, the Internet of Things and cloud computing to achieve more intelligent and refined signal timing. The effectiveness of the signal light timing model is crucial to improving traffic efficiency, reducing traffic congestion and improving traffic safety. Through the intelligent regulation of traffic lights, urban traffic conditions can be greatly improved.

[0081] Exemplarily, constructing a signal light timing model involves multiple fields such as data analysis, traffic theory, control theory, and optimization algorithms, and the following steps can be taken: collect traffic flow data at intersections, including vehicle counts, vehicle speeds, vehicle types, traffic peak periods, etc.; define basic parameters of the signal light timing model, such as cycle length, phase difference, green light time, red light time, and yellow light time; establish an objective function, such as minimizing vehicle waiting time, reducing the number of stops, and improving traffic capacity; set model constraints, such as: cycle length restrictions, minimum and maximum green light times for each phase, the red light time cannot exceed the cycle length minus the corresponding green light time and yellow light time, and phase difference restrictions, etc.; select a suitable optimization algorithm according to the characteristics of the model, such as linear programming, nonlinear programming, integer programming, genetic algorithm, simulated annealing algorithm, neural network, etc.; construct a signal light timing model; use an optimization algorithm to solve the signal light timing model to obtain the optimal signal light timing parameters; test the effect of the signal light timing model in an actual traffic environment, and adjust the signal light timing model parameters and optimization algorithm according to the test results.

[0082] In one embodiment, a three-dimensional simulation of intersection traffic is performed based on the geometric features and dimensional information and the trained signal light timing model, including: constructing a three-dimensional intersection model based on the geometric features and dimensional information based on simulation software; setting the traffic flow and signal light timing parameters of the three-dimensional intersection model according to the trained signal light timing model to perform a three-dimensional simulation of intersection traffic.

[0083] Specifically, the three-dimensional simulation: Figure 8 As shown, a 3D model of the intersection is constructed using simulation software, traffic flow and signal light timing parameters are set, simulation tests are performed, and the impact of different timing schemes on traffic flow, congestion, and safety is analyzed. In this embodiment, the 3D simulation can evaluate the effect of signal lights under different traffic flows and road conditions, helping traffic engineers test new technologies and provide data support for policy making.

[0084] It should be noted that the method described in this embodiment has the following beneficial effects: Improve traffic management efficiency: Through simulation, the configuration and control strategy of traffic lights can be evaluated under different traffic flow and road conditions, thereby optimizing traffic flow and reducing congestion and accidents. Safe experimental environment: Provides a safe experimental environment for traffic engineers to test new technologies and control algorithms without high-risk experiments on actual roads. Scientific decision support: Simulation results provide data support for policy makers, assist more scientific traffic management decisions, and ultimately improve the overall efficiency and safety of urban transportation systems. High-precision data processing: Through systematic data preparation and preprocessing steps, the high quality of image data, point cloud data and traffic light data is ensured, laying the foundation for subsequent feature extraction and model training. Effective signal light feature extraction: The application of 3D Gauss mask technology improves the accuracy of signal light recognition and ensures that the geometric shape and size of the signal light are consistent with the actual situation. Intelligent signal light control: Combined with AI technology, it can realize signal light entity type recognition, direction calculation and size calculation, providing technical support for the realization of intelligent transportation systems. Dynamically optimized signal light timing model: Through simulation results analysis, it provides a scientific basis for traffic management, helps optimize signal light timing strategies, and improves traffic flow efficiency and safety. Promote sustainable development: It provides strong technical support for the sustainable development of urban transportation systems and promotes the comprehensive development of intelligent transportation systems.

[0085] It can be understood that in this embodiment, the application of 3D Gauss mask technology effectively extracts and enhances the features of traffic lights, improves the accuracy of traffic light recognition, and can reduce unnecessary details while retaining important structural information. AI-based model training: Designing a deep learning model for traffic light entity type recognition and direction calculation provides technical support for the implementation of intelligent transportation systems and enhances the intelligence level of traffic light control. Construction and optimization of traffic light timing model: Through the analysis of simulation results, the construction process and parameter optimization method of the traffic light timing model are proposed, which provides a scientific basis for traffic management and improves traffic flow efficiency and safety. Implementation of three-dimensional simulation: A three-dimensional simulation environment for intersection traffic lights is constructed, which reflects the beneficial impact of simulation results on traffic management and improves the importance of simulation technology in urban traffic management.

[0086] The present embodiment provides a traffic light control simulation method, including: obtaining oblique photography image data and road traffic data; performing data preprocessing on the oblique photography image data and road traffic data to obtain processed data; extracting and identifying features of the processed data based on 3D Gauss mask technology combined with deep learning technology to obtain geometric features and size information of the traffic light; constructing a traffic light timing model, and training the traffic light timing model through a preset optimization algorithm; performing three-dimensional simulation of intersection traffic according to the geometric features and size information and the trained traffic light timing model. In the present embodiment, the features of the traffic light are effectively extracted and enhanced through the 3D Gauss mask technology, the accuracy of traffic light recognition is improved, and unnecessary details can be reduced while retaining important structural information. Deep learning technology is used to identify the entity type of the traffic light and calculate the direction, thereby enhancing the intelligent level of traffic light control. The traffic flow efficiency and safety of traffic management are improved through the construction and optimization of the traffic light timing model. The realization of three-dimensional simulation provides a safe experimental environment. The simulation results provide data support for traffic management decisions, which is conducive to improving the overall efficiency and safety of the urban transportation system.

[0087] In addition, an embodiment of the present invention further proposes a storage medium, on which a traffic light control simulation program is stored. When the traffic light control simulation program is executed by a processor, the steps of the traffic light control simulation method described above are implemented.

[0088] Reference Fig. 9 , Fig. 9 This is a structural block diagram of an embodiment of a traffic signal light control simulation system of the present invention.

[0089] like Fig. 9 As shown, the traffic light control simulation system includes:

[0090] The data acquisition module 10 is used to obtain oblique photography image data and road traffic data;

[0091] A data preprocessing module 20, used for preprocessing the oblique photography image data and the road traffic data to obtain processed data;

[0092] A feature extraction and recognition module 30 is used to extract and recognize features of the processed data based on 3D Gauss mask technology combined with deep learning technology to obtain geometric features and size information of the signal light;

[0093] A signal light timing module 40, used to construct a signal light timing model and train the signal light timing model through a preset optimization algorithm;

[0094] The three-dimensional simulation module 50 is used to perform three-dimensional simulation of intersection traffic according to the geometric features and size information and the trained signal light timing model.

[0095] This embodiment provides a traffic light control simulation system, which effectively extracts and enhances the features of traffic lights through 3D Gauss mask technology, improves the accuracy of traffic light recognition, can reduce unnecessary details while retaining important structural information, and uses deep learning technology to identify the type of traffic light entity and calculate the direction, thereby enhancing the intelligent level of traffic light control. The traffic flow efficiency and safety of traffic management are improved through the construction and optimization of the traffic light timing model. The realization of three-dimensional simulation provides a safe experimental environment, and the simulation results provide data support for traffic management decisions, which is conducive to improving the overall efficiency and safety of the urban transportation system.

[0096] It should be noted that the technical details that are not described in detail in the traffic light control simulation system embodiment can be found in the traffic light control simulation method described above provided in any embodiment of the present invention, and will not be repeated here.

[0097] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present invention. In specific applications, technicians in this field can make settings as needed, and the present invention does not limit this.

[0098] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0099] In addition, it should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0100] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0101] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0102] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A traffic light control simulation method, characterized in that: include: Obtain oblique photography image data and road traffic data; Performing data preprocessing on the oblique photography image data and the road traffic data to obtain processed data; Based on 3D Gauss mask technology combined with deep learning technology, feature extraction and recognition are performed on the processed data to obtain geometric features and size information of the traffic light; Constructing a traffic light timing model, and training the traffic light timing model through a preset optimization algorithm; A three-dimensional simulation of intersection traffic is performed based on the geometric features and size information and the trained signal light timing model.

2. The method according to claim 1, characterized in that The obtaining of oblique photography image data and road traffic data includes: Obtain oblique photography image data based on oblique photogrammetry technology; Obtaining three-dimensional point cloud data according to the oblique photography image data; Collecting traffic light location information, traffic light status data, and road and traffic flow data; The location information of the traffic light, the state data of the traffic light, and the road and traffic flow data are used as road traffic data.

3. The method according to claim 1, characterized in that The data preprocessing of the oblique photography image data and the road traffic data includes: Performing denoising, correction and enhancement processing on the oblique photography image data; Cleaning, correcting and formatting the road traffic data; Perform denoising, filtering, coordinate transformation and region segmentation on 3D point cloud data.

4. The method according to claim 1, characterized in that The 3D Gauss mask technology combined with the deep learning technology is used to extract and identify features of the processed data to obtain geometric features and size information of the traffic light, including: Based on the 3D Gauss mask technology, the traffic light is subjected to individual processing according to the processed data to obtain a traffic light model; Deep learning technology is used to identify the type and direction of the traffic light model to obtain the geometric characteristics and size information of the traffic light.

5. The method according to claim 1, characterized in that The step of constructing a signal light timing model and training the signal light timing model by using a preset optimization algorithm includes: Construct a signal light timing model based on the preset timing strategy; A preset optimization algorithm is used to adjust the parameters of the traffic light timing model to train the traffic light timing model.

6. The method according to claim 5, characterized in that The signal light timing model includes: a fixed signal light timing model, a dynamic signal light timing model and an adaptive signal light timing model.

7. The method according to any one of claims 1 to 6, characterized in that The three-dimensional simulation of intersection traffic based on the geometric features and size information and the trained signal light timing model includes: Constructing a three-dimensional model of the intersection based on the geometric features and dimensional information based on simulation software; The traffic flow and signal light timing parameters of the three-dimensional model of the intersection are set according to the trained signal light timing model to perform three-dimensional simulation of intersection traffic.

8. A traffic light control simulation system, characterized in that: include: Data acquisition module, used to obtain oblique photography image data and road traffic data; A data preprocessing module, used to perform data preprocessing on the oblique photography image data and the road traffic data to obtain processed data; A feature extraction and recognition module, used to extract and recognize features of the processed data based on 3D Gauss mask technology combined with deep learning technology to obtain geometric features and size information of the signal light; A signal light timing module, used to construct a signal light timing model and train the signal light timing model through a preset optimization algorithm; The three-dimensional simulation module is used to perform three-dimensional simulation of intersection traffic based on the geometric features and size information and the trained signal light timing model.

9. An electronic device, characterized in that: The electronic device includes: a memory, a processor, and a traffic light control simulation program stored in the memory and executable on the processor, wherein the traffic light control simulation program is configured to implement the traffic light control simulation method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a traffic light control simulation program, and the traffic light control simulation program is used to enable the processor to implement the traffic light control simulation method as described in any one of claims 1 to 7 when executed.

Images