Signal lamp visualization method and device based on digital twinning, equipment and medium

Abstract

The invention provides a signal lamp visualization method and device based on digital twinning, equipment and a medium, and belongs to the technical field of intelligent traffic. The method comprises the following steps: acquiring lane center line data of a target intersection; wherein the lane center line data comprises a plurality of data points arranged according to a position sequence, and each data point comprises corresponding position information; determining model position information of a digital twin model corresponding to a signal lamp of the target intersection according to position information of data points in the lane center line data; and according to the model position information, generating a model instance of a digital twinborn model in a digital twinborn environment corresponding to the target intersection, and according to the real-time data corresponding to the signal lamp, updating display parameters of the model instance so as to realize visual display of the signal lamp of the target intersection. According to the embodiment of the invention, rapid and accurate signal lamp adaptive visual display can be realized in a digital twin environment.

Description

Technical Field

[0001] This disclosure relates to the field of intelligent transportation technology, and in particular to a signal light visualization method and device, electronic device, and computer-readable storage medium based on digital twins. Background Technology

[0002] Visualization of traffic lights at intersections typically employs simplified geometry to replace actual traffic light equipment, often under vehicle-to-infrastructure (V2I) technology. However, this visualization method struggles to support precise visualization analysis and location optimization.

[0003] Specifically, in the above scheme, the position of the traffic light model still requires manual configuration, making it impossible to achieve automated parameter calibration of the traffic light model's position. Furthermore, the constructed traffic light model cannot quickly display the current traffic light status in real time. Therefore, the above scheme struggles to achieve accurate and efficient adaptive visualization of traffic lights across the entire intersection. Summary of the Invention

[0004] Therefore, this disclosure provides a traffic light visualization method, device, equipment, and medium based on digital twins, so as to achieve fast and accurate adaptive visualization of traffic lights in a digital twin environment.

[0005] To achieve the above objectives, the first aspect of this disclosure provides a traffic light visualization method based on digital twins. The method includes: acquiring lane centerline data of a target intersection; wherein the lane centerline data includes multiple data points arranged in positional order, each data point including corresponding positional information; determining the model position information of a digital twin model corresponding to the traffic lights at the target intersection based on the positional information of the data points in the lane centerline data; generating a model instance of the digital twin model in a digital twin environment corresponding to the target intersection based on the model position information; and updating the display parameters of the model instance based on real-time data corresponding to the traffic lights, thereby achieving a visualized display of the traffic lights at the target intersection.

[0006] In one optional implementation, before determining the model position information of the digital twin model corresponding to the traffic lights at the target intersection based on the position information of the target data points in the lane centerline data, the method further includes: performing scale distortion anomaly detection on the last data point of the lane centerline based on the position information of the last two data points in the lane centerline data; performing curvature abrupt change anomaly detection on the last data point of the lane centerline based on the position information of the last three data points in the lane centerline data; and calibrating the last data point if there is a scale distortion anomaly or a curvature abrupt change anomaly, and updating the lane centerline data based on the calibration result.

[0007] In one optional implementation, the planar coordinates of any data point are determined based on the position information of the data point. The step of detecting a curvature abrupt change anomaly at the last data point of the lane centerline based on the position information of the last three data points in the lane centerline data includes: determining a first azimuth angle corresponding to a first vector from the last third data point to the last second data point based on the planar coordinates of the last third and last second data points; determining a second azimuth angle corresponding to a second vector from the last second data point to the last first data point based on the planar coordinates of the last second and last first data points; determining the steering angle corresponding to the last first data point based on the angle difference between the second azimuth angle and the first azimuth angle; and determining that the last first data point has a curvature abrupt change anomaly if the steering angle is within a preset angle range.

[0008] In one optional implementation, the planar coordinates of any data point are determined based on the location information of the data point. The step of performing scale distortion anomaly detection on the last data point of the lane centerline based on the location information of the last two data points in the lane centerline data includes: determining the data point distance between the last first data point and the last second data point based on the planar coordinates of the last first data point and the last second data point; and determining that the last first data point has scale distortion anomaly if the data point distance is less than a preset distance threshold.

[0009] In one optional implementation, the step of calibrating the last first data point when it exhibits scale distortion or curvature abrupt change, and updating the lane centerline data based on the calibration result, includes: deleting the last first data point from the lane centerline data when the steering angle corresponding to the last first data point is within a first preset angle range; and calibrating the last first data point based on the position information of the last third and last second data points when it exhibits scale distortion or the steering angle corresponding to the last first data point is within a second preset angle range, and updating the lane centerline data based on the calibration result.

[0010] In one optional implementation, calibrating the last first data point based on the position information of the last third data point and the last second data point, and updating the lane centerline data based on the calibration result, includes: constructing a connecting line between the last third data point and the last second data point; extending the connecting line to obtain a target extension line; generating a target perpendicular line to the target extension line starting from the last first data point; and updating the position information of the last first data point in the lane centerline data based on the position information of the intersection of the target perpendicular line and the target extension line.

[0011] In one optional implementation, the model position information includes the target position information and target azimuth of the digital twin model; determining the model position information of the digital twin model corresponding to the traffic lights at the target intersection based on the position information of the data points in the lane centerline data includes: determining a third azimuth corresponding to the target direction, starting from the second-to-last data point and ending at the first-to-last data point, based on the position information of the last first and second-to-last data points in the lane centerline data; determining the endpoint position information obtained by moving a preset distance along the third azimuth based on the third azimuth, the model length of the digital twin model, and the position information of the last first data point; wherein the preset distance is determined based on the model length; determining the target azimuth in the model position information based on the third azimuth; and determining the target position information in the model position information based on the endpoint position information.

[0012] Secondly, this disclosure provides a traffic light visualization device based on digital twins. The device includes: an acquisition module for acquiring lane centerline data of a target intersection; wherein the lane centerline data includes multiple data points arranged in positional order, and each data point includes corresponding position information; a determination module for determining the model position information of the digital twin model corresponding to the traffic light at the target intersection based on the position information of the data points in the lane centerline data; and a display module for generating a model instance of the digital twin model in a digital twin environment corresponding to the target intersection based on the model position information, and updating the display parameters of the model instance based on the real-time data corresponding to the traffic light, so as to realize the visualization display of the traffic light at the target intersection.

[0013] Thirdly, this disclosure provides an electronic device comprising: one or more processors; a memory storing one or more programs that, when executed by the one or more processors, enable the one or more processors to implement the aforementioned signal light visualization method based on digital twins; and one or more I / O interfaces connected between the processors and the memory, configured to enable information interaction between the processors and the memory.

[0014] Fourthly, this disclosure provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the above-described signal light visualization method based on digital twins.

[0015] This disclosure has the following advantages:

[0016] This disclosure provides a traffic light visualization method based on digital twins. First, lane centerline data of the target intersection is acquired. This lane centerline data includes multiple data points arranged in positional order, each data point containing corresponding positional information. Then, based on the positional information of the data points in the lane centerline data, the model position information of the digital twin model corresponding to the traffic lights at the target intersection is determined. Finally, based on the model position information, a model instance of the digital twin model is generated in the digital twin environment corresponding to the target intersection. The display parameters of the model instance are updated based on the real-time data corresponding to the traffic lights to achieve the visualization of the traffic lights at the target intersection.

[0017] Therefore, this embodiment of the present disclosure can acquire high-precision position information of the lane centerline of the target intersection, and then adaptively determine the model position information of the digital twin model corresponding to the traffic lights at the target intersection based on this position information, thus achieving adaptive position calibration of the traffic light model. Furthermore, this embodiment of the present disclosure generates a corresponding model instance in the digital twin environment corresponding to the target intersection based on the model position information, and updates the display parameters of the model instance in a timely manner based on real-time traffic light data, thereby achieving accurate and rapid adaptive visualization of the traffic lights in the digital twin environment.

[0018] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0019] The accompanying drawings are provided to further illustrate the present disclosure and form part of the specification. They are used together with the embodiments of the present disclosure to explain the disclosure and do not constitute a limitation thereof. The above and other features and advantages will become more apparent to those skilled in the art from the detailed description of exemplary embodiments with reference to the accompanying drawings, in which:

[0020] Figure 1 A flowchart illustrating a traffic light visualization method based on digital twins, provided as an embodiment of this disclosure;

[0021] Figure 2 This is a schematic diagram illustrating the presence of scale distortion anomalies in data points.

[0022] Figure 3 This is a schematic diagram illustrating when data points exhibit abrupt curvature changes.

[0023] Figure 4 This is a schematic diagram illustrating anomaly detection for the first data point at the end of the dataset.

[0024] Figure 5 This is a schematic diagram illustrating the calibration of the first data point at the end.

[0025] Figure 6 A flowchart illustrating a traffic light visualization method based on digital twins provided in this disclosure embodiment;

[0026] Figure 7 This is a schematic diagram for visualizing the traffic lights at a target intersection.

[0027] Figure 8 A block diagram of a traffic light visualization device based on digital twin provided in this disclosure embodiment;

[0028] Figure 9 This is a block diagram of an electronic device provided in an embodiment of the present disclosure. Detailed Implementation

[0029] The specific embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit this disclosure.

[0030] As used in this disclosure, the term "and / or" includes any and all combinations of one or more of the related enumerated entries.

[0031] The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the disclosure. As used in this disclosure, the singular forms “a” and “the” are also intended to include the plural forms, unless the context clearly indicates otherwise.

[0032] When the terms “comprising” and / or “made of” are used in this disclosure, they specify the presence of the said feature, integral, step, operation, element and / or component, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or groups thereof.

[0033] Unless otherwise specified, all terms used in this disclosure (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and this disclosure, and will not be interpreted as having an idealized or overly formal meaning, unless expressly so specified in this disclosure.

[0034] In vehicle-road cooperative technology, the visualization of traffic lights at intersections typically employs BIM and GIS technologies to construct a basic 3D scene, achieving digital modeling of the road network environment. However, these methods generally use simplified geometry to replace actual traffic light equipment, making it difficult to support accurate visibility analysis and model position optimization. The position of the traffic light model still requires manual configuration, and automated parameter calibration of the traffic light model's position is not possible. Furthermore, existing systems lack an effective virtual-real interaction mechanism, making it difficult for relevant personnel to intuitively adjust the traffic light position and instantly evaluate the effect through a digital twin interface. Therefore, it is evident that these technologies cannot achieve adaptive and accurate configuration of the traffic light model's position.

[0035] Furthermore, the traffic light models constructed in related technologies cannot quickly display the current status of traffic lights in real time. For example, traffic light models often use offline simulation, making them unable to reflect real-time physical changes such as intersection modifications. Another example is in digital twin scenarios, where some solutions visualize traffic lights based on real-world scenes. This approach reduces the visualization weight of traffic lights, thus failing to quickly display their current status. Moreover, this approach typically relies on manual configuration of the traffic light models, resulting in lengthy processing times and unreliable configuration quality.

[0036] It is evident that accurate and efficient adaptive visual display of traffic lights at all intersections is difficult to achieve using relevant technologies.

[0037] In view of this, this disclosure provides a traffic light visualization method based on digital twins. First, lane centerline data of the target intersection is acquired; wherein, the lane centerline data includes multiple data points arranged in positional order, and each data point includes corresponding position information; then, based on the position information of the data points in the lane centerline data, the model position information of the digital twin model corresponding to the traffic light of the target intersection is determined; finally, based on the model position information, a model instance of the digital twin model is generated in the digital twin environment corresponding to the target intersection, and the display parameters of the model instance are updated according to the real-time data corresponding to the traffic light, so as to realize the visualization display of the traffic light of the target intersection.

[0038] Therefore, this embodiment of the present disclosure can acquire high-precision position information of the lane centerline of the target intersection, and then adaptively determine the model position information of the digital twin model corresponding to the traffic lights at the target intersection based on this position information, thus achieving adaptive position calibration of the traffic light model. Furthermore, this embodiment of the present disclosure generates a corresponding model instance in the digital twin environment corresponding to the target intersection based on the model position information, and updates the display parameters of the model instance in a timely manner based on real-time traffic light data, thereby achieving accurate and rapid adaptive visualization of the traffic lights in the digital twin environment.

[0039] In a first aspect, embodiments of this disclosure provide a traffic light visualization method based on digital twins. Figure 1 A flowchart of a traffic light visualization method based on digital twins provided in this disclosure is shown below. Figure 1 The method includes:

[0040] Step S110: Obtain the lane centerline data of the target intersection; wherein, the lane centerline data includes multiple data points arranged in positional order, and each data point includes corresponding position information.

[0041] The target intersection refers to the intersection where traffic light visualization will be implemented. Each target intersection includes at least one lane. For each lane at the target intersection, the lane centerline data can be obtained.

[0042] The lane centerline data includes multiple data points arranged in positional order, with each data point containing corresponding location information. The positional order corresponds to the spatial orientation of the lane centerline in the physical world. For example, for any lane, its lane centerline data includes multiple data points arranged from the starting point to the ending point of the lane centerline according to the corresponding driving direction.

[0043] The location information of each data point is used to characterize the geographical location of the data point. For example, the location information of a data point includes its latitude and longitude.

[0044] Step S120: Based on the location information of the data points in the lane centerline data, determine the model location information of the digital twin model corresponding to the traffic lights at the target intersection.

[0045] The number of digital twin models corresponding to the traffic lights at the target intersection can be multiple. For example, for each lane of the target intersection, a corresponding digital twin model can be constructed based on the traffic lights corresponding to that lane.

[0046] Among them, the model position information of the digital twin model corresponding to the traffic lights at the target intersection is used to characterize the model position and orientation of the digital twin model.

[0047] Specifically, the model location information can include the target location information and target azimuth of the digital twin model. The target location information can be represented by latitude and longitude, which describes the placement position of the model, while the target azimuth can be represented by an angle value, which describes the orientation of the model.

[0048] For any lane at a target intersection, the location information of the digital twin model corresponding to the traffic light of that lane can be adaptively determined by using the location information of the data points in the lane centerline data.

[0049] Step S130: Based on the model location information, generate a model instance of the digital twin model in the digital twin environment corresponding to the target intersection, and update the display parameters of the model instance according to the real-time data corresponding to the traffic lights to realize the visual display of the traffic lights at the target intersection.

[0050] The digital twin environment corresponding to the target intersection is a digital mirror environment constructed based on the physical entities of the target intersection, such as roads, lanes, and surrounding buildings.

[0051] Once the location information of the digital twin model is determined, it can be placed within the digital twin environment based on this information, i.e., a model instance of the digital twin model can be generated within the digital twin environment. For example, configuration information such as model position and model orientation can be added to the digital twin model through the digital twin engine.

[0052] The model instance includes built-in traffic light animations for displaying traffic lights. For example, by default, the traffic light starts at red, turns green after a countdown to 0, turns yellow after another countdown to 0, and then turns red again after another countdown to 0, thus achieving a cyclical display of the traffic lights. By configuring the cyclical animations of each traffic light color in the model instance, the performance overhead of performing countdown calibrations on a large number of traffic lights can be saved, thereby reducing the load on the graphics card.

[0053] Accordingly, the display parameters of a model instance can include light color parameters, countdown parameters, duration parameters, traffic light direction parameters, and light status parameters. The light color parameter allows configuration of the light color displayed by the model instance, such as red or green. The countdown parameter allows configuration of the countdown value displayed by the model instance, for example, updating from 5 to 3. The duration parameter allows configuration of the total duration of the traffic lights for the model instance, for example, adjusting the total duration of the red, green, and yellow lights. The traffic light direction parameter allows configuration of the direction of the traffic lights displayed by the model instance, such as updating from left turn to straight ahead. The light status parameter allows configuration of the status of the traffic lights displayed by the model instance, such as flashing or on / off.

[0054] In situations with significant network fluctuations or time loss or deviations in model animation, the model instance may not perfectly match the actual traffic light status. Furthermore, in real-world scenarios, some roads may dynamically adjust traffic light directions based on traffic flow. Therefore, to match the actual traffic light status in real time, this embodiment of the disclosure requires updating the aforementioned display parameters of the model instance based on the real-time data corresponding to the traffic lights.

[0055] Accordingly, the real-time data for the traffic lights may include the color, status, total duration, and direction of the traffic lights, etc., and this embodiment does not limit this.

[0056] For example, after a preset time interval, the display parameters of the model instance are updated based on the real-time data corresponding to the traffic light. For instance, after every 5 to 10 seconds, the display parameters of the model instance are calibrated based on the real-time data corresponding to the traffic light. This embodiment of the present disclosure does not limit this.

[0057] This disclosure provides a traffic light visualization method based on digital twins. First, lane centerline data of the target intersection is acquired. This lane centerline data includes multiple data points arranged in positional order, each data point containing corresponding positional information. Then, based on the positional information of the data points in the lane centerline data, the model position information of the digital twin model corresponding to the traffic lights at the target intersection is determined. Finally, based on the model position information, a model instance of the digital twin model is generated in the digital twin environment corresponding to the target intersection. The display parameters of the model instance are updated based on the real-time data corresponding to the traffic lights to achieve the visualization of the traffic lights at the target intersection.

[0058] Therefore, this embodiment of the present disclosure can acquire high-precision position information of the lane centerline of the target intersection, and then adaptively determine the model position information of the digital twin model corresponding to the traffic lights at the target intersection based on this position information, thus achieving adaptive position calibration of the traffic light model. Furthermore, this embodiment of the present disclosure generates a corresponding model instance in the digital twin environment corresponding to the target intersection based on the model position information, and updates the display parameters of the model instance in a timely manner based on real-time traffic light data, thereby achieving accurate and rapid adaptive visualization of the traffic lights in the digital twin environment.

[0059] In one alternative implementation, the acquired lane centerline data may contain anomalies, leading to data deviations in the model position information of the digital twin determined based on this lane centerline data, thus affecting the visualization of the traffic lights. Therefore, anomaly detection can be performed on the polarity of data points in the lane centerline data. After detecting the anomalies, the data can be calibrated to improve the visualization of the traffic lights.

[0060] Accordingly, before determining the model position information of the digital twin model corresponding to the traffic lights at the target intersection based on the position information of the data points in the lane centerline data, the method further includes: performing scale distortion anomaly detection on the last data point of the lane centerline based on the position information of the last two data points in the lane centerline data; performing curvature abrupt change anomaly detection on the last data point of the lane centerline based on the position information of the last three data points in the lane centerline data; and calibrating the last data point if there is scale distortion anomaly or curvature abrupt change anomaly, and updating the lane centerline data based on the calibration result.

[0061] Scale distortion anomaly refers to a situation where a data point is too close to its nearest neighbor, causing significant angular distortion at that data point. For example, Figure 2 This diagram illustrates a situation where scale distortion anomalies exist in the data points. (Refer to...) Figure 2 At a scale of 20:1, the distance between a data point P and its nearest data point is about 0.1m, which shows obvious angular distortion. However, in the actual scenario, the road segment is a straight segment without any turning points. Therefore, the data point has scale distortion anomalies.

[0062] Among them, curvature abrupt change anomaly refers to a large angular deformation at a certain data point, resulting in a large inflection point in the lane centerline. For example, Figure 3 This diagram illustrates a situation where data points exhibit abrupt curvature aberrations. (Refer to...) Figure 3At a scale of 1:20, the distance between the data point circled in the box and its nearest other data point is approximately 1.16 meters, indicating significant angular distortion at this data point. In the actual scenario, this road segment is a straight-turn section, but its road width varies, resulting in significant inflection points in the collected lane centerline data. This affects the accuracy of the model position information in the digital twin model corresponding to the traffic light, thereby impacting the visualization effect of the traffic light.

[0063] In particular, the lane centerline data may have data anomalies at its last data point, and the data anomalies at the last data point will affect the accuracy of the model position information of the digital twin model corresponding to the traffic light. Therefore, in this embodiment of the disclosure, it is necessary to perform anomaly detection on the last data point in the lane centerline data.

[0064] Specifically, the distance between the last two data points in the lane centerline data can be determined based on their position information, and then the scale distortion anomaly detection can be performed on the last data point of the lane centerline based on this distance.

[0065] Furthermore, based on the position information of the last three data points in the lane centerline data, the steering angle corresponding to the last data point can be determined, and then the curvature abrupt change anomaly detection can be performed on the last data point based on the steering angle.

[0066] In one optional implementation, the planar coordinates of any data point are determined based on the position information of that data point. Based on the position information of the last three data points in the lane centerline data, curvature abrupt change anomaly detection is performed on the last data point of the lane centerline, including: determining the first azimuth angle corresponding to the first vector from the last third data point to the last second data point based on the planar coordinates of the last third data point and the last second data point; determining the second azimuth angle corresponding to the second vector from the last second data point to the last first data point based on the planar coordinates of the last second data point and the last first data point; determining the steering angle corresponding to the last first data point based on the angle difference between the second azimuth angle and the first azimuth angle; and determining that the curvature abrupt change anomaly exists at the last first data point if the steering angle is within a preset angle range.

[0067] In the lane centerline data, the third-to-last data point is P1, the second-to-last data point is P2, and the first-to-last data point is P3. The plane coordinates of these data points can be determined based on their position information.

[0068] For example, the location information of the data points includes longitude information λ and latitude information. In this case, the planar coordinates of the data point, such as the Cartesian plane coordinates (x, y), can be determined by the following formula:

[0069] Formula (1)

[0070] Formula (2)

[0071] Where R is the Earth's radius, for example, 6371 km. Accordingly, according to the above formula, the plane coordinates of the last third data point P1 are (x1, y1), the plane coordinates of the last second data point P2 are (x2, y2), and the plane coordinates of the last first data point P3 are (x3, y3).

[0072] Correspondingly, the first azimuth angle is the direction angle between the first vector and the positive X-axis. The first vector from the third data point to the second data point is the vector... =P2-P1 corresponding to the first azimuth angle for:

[0073] Formula (3)

[0074] Where atan2 is a two-parameter arctangent function. Further, the second azimuth angle is the direction angle between the second vector and the positive X-axis. The second vector from the second-to-last data point to the first-to-last data point is the vector... =P3-P2 corresponding to the second azimuth angle for:

[0075] Formula (4)

[0076] Here, atan2 is a two-parameter arctangent function. Therefore, based on the angle difference between the first and second azimuth angles, the steering angle corresponding to the first data point P1 can be obtained. for:

[0077] Formula (5)

[0078] Furthermore, the steering angle corresponding to the last data point can be normalized by converting it to degrees and setting its value to within the range of 0 to 180°, thus obtaining the processed steering angle corresponding to the last data point. The specific processing procedure is described in formulas (6) to (7) below.

[0079] Formula (6)

[0080] Formula (7)

[0081] After determining the steering angle corresponding to the last data point, it can be compared with a preset angle range. If the steering angle is within the preset angle range, it is determined that the last data point has a curvature abrupt change anomaly.

[0082] For example, for the steering angle corresponding to the last data point obtained after normalization, a preset angle range of less than or equal to 160° is set. Thus, if the steering angle is within this preset angle range, the last data point is determined to have a curvature abrupt change anomaly. However, if the steering angle is not within the preset angle range, for example, if the steering angle is greater than 160° and less than or equal to 180°, it is determined that there is no curvature abrupt change anomaly, and in this case, data calibration processing for the last data point is not required.

[0083] In this embodiment of the disclosure, the direction angles corresponding to the first vector and the second vector are determined by the planar coordinates of the last three data points, and the turning angle corresponding to the last first data point is determined based on the difference between the two direction angles. Based on the comparison result of the turning angle with the preset angle range, the accurate curvature change anomaly detection of the last first data point is realized.

[0084] In one optional implementation, the spatial coordinates of any data point are determined based on the location information of that data point. Based on the location information of the last two data points in the lane centerline data, scale distortion anomaly detection is performed on the last data point of the lane centerline, including: determining the data point distance between the last data point and the last data point based on the spatial coordinates of the last first data point and the last second data point; if the data point distance is less than a preset distance threshold, it is determined that the last first data point has scale distortion anomaly.

[0085] The location information of the data points includes longitude (λ) and latitude. In this case, the spatial coordinates of the data point, i.e., the three-dimensional Cartesian coordinates (x, y, z), can be determined by the following formula:

[0086] Formula (8)

[0087] Formula (9)

[0088] Formula (10)

[0089] Where R is the Earth's radius, for example, 6371 km. Accordingly, according to the above formula, the spatial coordinates of the last data point P3 are (x3, y3, z3), and the spatial coordinates of the last data point P2 are (x2, y2, z2).

[0090] Furthermore, the distance between the data points can be calculated based on their spatial coordinates. For example, the Eulerian distance *dis* between the last first data point and the last second data point can be calculated using the aforementioned spatial coordinates:

[0091] Formula (11)

[0092] Correspondingly, the calculated distance between data points can be compared with a preset distance threshold. If the distance between the data points is less than the preset distance threshold, it is determined that the last data point has a scale distortion anomaly.

[0093] It should be noted that the preset distance threshold can be adaptively set according to actual application needs, and this embodiment does not limit it. For example, the preset distance threshold can be set to 0.5m.

[0094] In this embodiment of the disclosure, the distance between the last two data points is calculated using their spatial coordinates. Based on the comparison between this distance and a preset distance threshold, accurate scale anomaly detection of the last data point is achieved.

[0095] In one optional implementation, if the last data point has scale distortion anomalies or curvature abrupt changes, the last data point is calibrated, and the lane centerline data is updated based on the calibration result. This includes: if the steering angle corresponding to the last data point is within a first preset angle range, deleting the last data point from the lane centerline data; if the last data point has scale distortion anomalies or the steering angle corresponding to the last data point is within a second preset angle range, calibrating the last data point based on the position information of the last third data point and the last second data point, and updating the lane centerline data based on the calibration result.

[0096] The preset angle range may include a first preset angle range and a second preset angle range. The size of the first preset angle range and the second preset angle range can be adaptively set according to actual application needs, and this embodiment does not limit this. For example, the first preset angle range can be set to less than or equal to 90°, and the second preset angle range can be set to greater than 90° and less than or equal to 160°.

[0097] Correspondingly, if the turning angle corresponding to the last data point is within the first preset angle range (e.g., less than or equal to 90°), the point can be identified as a singularity and thus directly deleted. However, if the last data point exhibits scale distortion anomalies, or if its turning angle is within the second preset angle range (e.g., greater than 90° and less than or equal to 160°), the position information of the last data point needs to be further adjusted based on the position information of the last third and last second data points to ensure that the adjusted last first data point does not exhibit significant angular distortion.

[0098] Figure 4 This diagram illustrates anomaly detection for the first data point at the end of the dataset. (Refer to...) Figure 4 ,in, Figure 4 In the example, 'a' corresponds to the straight-line scenario, and the first data point P at the end of the example does not have any data anomalies. Figure 4 In the diagram, b and d correspond to left and right turning scenarios. If the turning angle corresponding to the last data point P changes too much, it will cause the digital twin model of the traffic light in the visualization scenario to produce a rather abrupt turning effect. Therefore, the position information of the last data point P needs to be adjusted. Figure 4 In scenarios c and e, the first data point P at the end of the data points has a data anomaly. Based on its turning angle, the first data point P at the end of the data points can be determined to be a singular point. In this case, the singular point can be directly deleted.

[0099] In this embodiment of the disclosure, by setting a first preset angle range and a second preset angle range, singular points whose steering angle is within the first preset angle range are directly deleted. For the last data point whose steering angle is within the second preset angle range or has scale distortion anomalies, data calibration is directly performed based on the position information of the last third data point and the last second data point, thereby improving the accuracy of anomaly processing of lane centerline data.

[0100] In one optional implementation, the last data point is calibrated based on the position information of the last third data point and the last second data point, and the lane centerline data is updated based on the calibration result. This includes: constructing a connecting line between the last third data point and the last second data point, extending the connecting line to obtain a target extension line; generating a target perpendicular line to the target extension line starting from the last first data point, and updating the position information of the last first data point in the lane centerline data based on the position information of the intersection of the target perpendicular line and the target extension line.

[0101] Specifically, the first data point at the end of the line, which exhibits scale distortion or a turning angle within the second preset angle range, will show significant angular deformation. This affects the accuracy of the model position information in the corresponding data twin model of the traffic light, thus impacting the visualization effect of the traffic light. Therefore, it is necessary to calibrate the position information of the first data point at the end based on the position information of the third and second data points at the end.

[0102] Specifically, a connecting line can be constructed between the last third data point and the last second data point, and this connecting line can be extended to obtain the target extension line.

[0103] For ease of understanding, Figure 5 A schematic diagram illustrating the calibration of the first data point at the end is shown. (Refer to...) Figure 5 ,in, Figure 5 The target extension line is L1, P1 is the third data point at the end, P2 is the second data point at the end, and P is the first data point at the end.

[0104] Furthermore, starting from the first data point P at the end, a target perpendicular line L2 can be generated towards the target extension line L1. The intersection of the target perpendicular line L2 and the target extension line L1 is P'. Based on the position information of this intersection point P', the position information of the first data point at the end of the lane centerline data can be updated.

[0105] In this embodiment of the disclosure, by constructing a target extension line corresponding to the third data point and the second data point, and generating a perpendicular line from the first data point to the target extension line, the position information of the first data point is updated according to the position information of the intersection of the target extension line and the perpendicular line, so that the updated first data point will not have obvious angular deformation, thus achieving effective calibration of the position information of the first data point.

[0106] In one optional implementation, the model position information includes the target position information and target azimuth of the digital twin model; based on the position information of data points in the lane centerline data, the model position information of the digital twin model corresponding to the traffic lights at the target intersection is determined, including: based on the position information of the last first and last second data points in the lane centerline data, determining the third azimuth corresponding to the target direction with the last second data point as the starting point and the last first data point as the ending point; based on the third azimuth, the model length of the digital twin model, and the position information of the last first data point, determining the endpoint position information obtained by moving a preset distance along the third azimuth from the last first data point as the starting point; wherein, the preset distance is determined based on the model length; based on the third azimuth, the target azimuth in the model position information is determined, and based on the endpoint position information, the target position information in the model position information is determined.

[0107] Among them, the target location information of the digital twin model determines the placement position and orientation of the digital twin model in the digital twin environment corresponding to the target intersection.

[0108] Considering that the lanes at the target intersection may be straight lanes or turning lanes, visualizing traffic lights using the overall orientation of the lanes might lead to errors in the placement of the digital twin models corresponding to the traffic lights, thus affecting the visualization effect. Therefore, in this embodiment, the rotation angle of the model, i.e., the target azimuth angle, is determined based on the angle between the line connecting the last two data points in the lane centerline data and a reference direction, such as with true north as the 0° axis. Then, based on this determined rotation angle, an extension line is drawn outwards to determine the placement position of the model, i.e., the target placement information.

[0109] Specifically, based on the position information of the last two data points in the lane centerline data, it is necessary to determine the third azimuth angle corresponding to the target direction, with the second data point as the starting point and the first data point as the ending point. The position information of the first and second data points can include longitude and latitude information in radians. Third azimuth angle The following formula can be used to calculate it:

[0110] Formula (12)

[0111] in, , The second-to-last data point represents the latitude and longitude in radians. , The latitude and longitude in radians are for the last data point. , which is the difference in longitude between the last first data point and the last second data point. atan2 is the two-parameter arctangent function.

[0112] Based on this third azimuth angle, the target azimuth angle of the model's position information can be determined. For example, the target azimuth angle rotation of the model can be set to the third azimuth angle. Therefore, based on the digital twin engine, the model is rotated clockwise by a third azimuth angle along the reference direction to obtain the final orientation of the model.

[0113] It should be noted that the digital twin engine can be configured to rotate the azimuth angle clockwise or counterclockwise according to application needs. The above example is a calculation example of the third azimuth angle when the azimuth angle is clockwise. When the azimuth angle is counterclockwise, the corresponding third azimuth angle can still be adaptively calculated based on the position information of the last first and second data points. For example, the supplementary angle of the third azimuth angle in the clockwise direction can be taken as the third azimuth angle in the counterclockwise direction. This disclosure does not limit this.

[0114] After determining the third azimuth angle, the target position information of the model can be further determined based on the third azimuth angle, the model length of the digital twin model, and the position information of the last data point. The model length of the digital twin model is used to determine the preset distance to move the last data point along the third azimuth angle. For example, the preset distance can be set to half the model length; however, this embodiment does not impose any limitations on this.

[0115] Furthermore, starting from the first data point at the end, the endpoint position information is obtained by moving a preset distance along a third azimuth angle. , The result can be calculated using the following formula:

[0116] Formula (13)

[0117] Formula (14)

[0118] Formula (15)

[0119] in, The latitude of the endpoint location information. The longitude is the location information of the endpoint. , This represents the latitude and longitude of the last data point. For the preset distance, R is the model length of the digital twin model, and R is the Earth's radius. This is a third-party azimuth angle.

[0120] Accordingly, based on this endpoint location information, the target location information of the digital twin model can be determined. For example, the target location information (position) of the digital twin model can be set as the endpoint location information (…). , ).

[0121] In this embodiment of the disclosure, the target azimuth angle of the digital twin model is determined by the position information of the two data points at the end of the lane center line. The position information after moving a preset distance along the target azimuth angle from the first data point at the end is used as the target position information of the digital twin model. This allows for accurate determination of the placement position and orientation of the digital twin model, improving the visualization effect of the traffic lights.

[0122] To facilitate understanding, the following specific example illustrates the detailed implementation of the above method:

[0123] Figure 6 A flowchart illustrating a traffic light visualization method based on digital twins provided in this disclosure is shown below. Figure 6 The method includes:

[0124] Step S601: Obtain the lane centerline data of the target intersection.

[0125] Step S602: Determine whether the last data point of the lane centerline data has scale distortion anomalies or curvature abrupt change anomalies. If the last data point has scale distortion anomalies or curvature abrupt change anomalies, proceed to step S603. If the last data point does not have scale distortion anomalies or curvature abrupt change anomalies, proceed to step S604.

[0126] Step S603: Calibrate the last data point, update the lane centerline data based on the calibration result, and continue to step S604.

[0127] Step S604: Based on the location information of the data points in the lane centerline data, determine the model location information of the digital twin model corresponding to the traffic lights at the target intersection.

[0128] Step S605: Based on the model location information, generate a model instance of the digital twin model in the digital twin environment corresponding to the target intersection, and update the display parameters of the model instance according to the real-time data of the traffic lights to realize the visual display of the traffic lights at the target intersection.

[0129] The real-time data corresponding to the traffic lights may include light color, light status, total duration of red light, total duration of yellow light, total duration of green light, traffic light direction, and other related content. This embodiment does not limit these aspects.

[0130] Furthermore, for ease of understanding, Figure 7 This diagram illustrates the visualization of traffic lights at a target intersection. See also... Figure 7The black box area contains digital twin models of four traffic lights. This means that a digital twin model of a corresponding traffic light is set up for each lane at the target intersection. Furthermore, the digital twin model of each traffic light can display information such as countdown timer, direction, color, and status.

[0131] The orientation and placement of the digital twin model of the traffic light can be determined based on the location information of data points in the lane centerline data. Furthermore, the display parameters corresponding to the digital twin model of the traffic light, such as light status parameters, light color parameters, and countdown parameters, can all be updated based on real-time data of the traffic light pushed from the cloud.

[0132] This example provides a traffic light visualization method based on digital twins. It can detect anomalies in acquired high-precision lane centerline data and calibrate the data upon detection. Based on the calibrated lane centerline data, it determines the model position information corresponding to the digital twin model of the traffic light. Furthermore, it calibrates the display parameters of the digital twin model of the traffic light based on received real-time traffic light data, achieving fast and accurate adaptive visualization of traffic lights within a digital twin environment. Without interfering with the user's vision and judgment, it ensures the matching and alignment of traffic lights with different road types, facilitating the user's quick identification of road driving direction and traffic light status.

[0133] The steps of the various methods described above are only for clarity. In practice, they can be combined into one step or some steps can be split into multiple steps. As long as they include the same logical relationship, they are all within the scope of protection of this patent. Adding insignificant modifications or introducing insignificant designs to the algorithm or process, but without changing the core design of the algorithm and process, are also within the scope of protection of this patent.

[0134] Secondly, embodiments of this disclosure provide a traffic light visualization device based on digital twins.

[0135] Figure 8 A block diagram of a traffic light visualization device based on digital twins provided in this disclosure embodiment, referring to... Figure 8 The traffic light visualization device includes:

[0136] The acquisition module 81 is used to acquire lane centerline data of the target intersection; wherein, the lane centerline data includes multiple data points arranged in positional order, and each data point includes corresponding position information;

[0137] The determination module 82 is used to determine the model position information of the digital twin model corresponding to the traffic lights at the target intersection based on the position information of the data points in the lane centerline data.

[0138] Display module 83 is used to generate a model instance of the digital twin model in the digital twin environment corresponding to the target intersection based on the model location information, and update the display parameters of the model instance based on the real-time data corresponding to the traffic lights, so as to realize the visual display of the traffic lights at the target intersection.

[0139] In one optional implementation, before determining the model position information of the digital twin model corresponding to the traffic lights at the target intersection based on the position information of the data points in the lane centerline data, the device is further configured to: perform scale distortion anomaly detection on the last data point of the lane centerline based on the position information of the last two data points in the lane centerline data; perform curvature abrupt change anomaly detection on the last data point of the lane centerline based on the position information of the last three data points in the lane centerline data; and, if the last data point has scale distortion anomaly or curvature abrupt change anomaly, calibrate the last data point and update the lane centerline data based on the calibration result.

[0140] In one optional implementation, the planar coordinates of any data point are determined based on the position information of the data point. The step of detecting a curvature abrupt change anomaly at the last data point of the lane centerline based on the position information of the last three data points in the lane centerline data includes: determining a first azimuth angle corresponding to a first vector from the last third data point to the last second data point based on the planar coordinates of the last third and last second data points; determining a second azimuth angle corresponding to a second vector from the last second data point to the last first data point based on the planar coordinates of the last second and last first data points; determining the steering angle corresponding to the last first data point based on the angle difference between the second azimuth angle and the first azimuth angle; and determining that the last first data point has a curvature abrupt change anomaly if the steering angle is within a preset angle range.

[0141] In one optional implementation, the spatial coordinates of any data point are determined based on the location information of the data point. The step of performing scale distortion anomaly detection on the last data point of the lane centerline based on the location information of the last two data points in the lane centerline data includes: determining the data point distance between the last first data point and the last second data point based on the spatial coordinates of the last first data point and the last second data point; and determining that the last first data point has scale distortion anomaly if the data point distance is less than a preset distance threshold.

[0142] In one optional implementation, the step of calibrating the last first data point when it exhibits scale distortion or curvature abrupt change, and updating the lane centerline data based on the calibration result, includes: deleting the last first data point from the lane centerline data when the steering angle corresponding to the last first data point is within a first preset angle range; and calibrating the last first data point based on the position information of the last third and last second data points when it exhibits scale distortion or the steering angle corresponding to the last first data point is within a second preset angle range, and updating the lane centerline data based on the calibration result.

[0143] In one optional implementation, calibrating the last first data point based on the position information of the last third data point and the last second data point, and updating the lane centerline data based on the calibration result, includes: constructing a connecting line between the last third data point and the last second data point; extending the connecting line to obtain a target extension line; generating a target perpendicular line to the target extension line starting from the last first data point; and updating the position information of the last first data point in the lane centerline data based on the position information of the intersection of the target perpendicular line and the target extension line.

[0144] In one optional implementation, the model position information includes the target position information and target azimuth of the digital twin model; determining the model position information of the digital twin model corresponding to the traffic lights at the target intersection based on the position information of the data points in the lane centerline data includes: determining a third azimuth corresponding to the target direction, starting from the second-to-last data point and ending at the first-to-last data point, based on the position information of the last first and second-to-last data points in the lane centerline data; determining the endpoint position information obtained by moving a preset distance along the third azimuth based on the third azimuth, the model length of the digital twin model, and the position information of the last first data point; wherein the preset distance is determined based on the model length; determining the target azimuth in the model position information based on the third azimuth; and determining the target position information in the model position information based on the endpoint position information.

[0145] The apparatus provided in this disclosure can have functions or include modules that can be used to perform the methods described in the first aspect of the method embodiments above. The specific implementation and technical effects can be referred to the description of the method embodiments above. For the sake of brevity, they will not be repeated here.

[0146] It should be noted that all modules involved in this embodiment are logical modules. In practical applications, a logical unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. Furthermore, to highlight the innovative aspects of this disclosure, this embodiment does not introduce units that are not closely related to solving the technical problems proposed in this disclosure; however, this does not mean that other units are absent from this embodiment.

[0147] Reference Figure 9 This disclosure provides an electronic device, which includes:

[0148] One or more processors 901;

[0149] The memory 902 stores one or more programs that, when executed by one or more processors, enable the one or more processors to implement any of the above-mentioned signal light visualization methods based on digital twins.

[0150] One or more I / O interfaces 903 are connected between the processor and the memory and configured to enable information exchange between the processor and the memory.

[0151] Among them, processor 901 is a device with data processing capabilities, including but not limited to central processing unit (CPU); memory 902 is a device with data storage capabilities, including but not limited to random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory (FLASH); I / O interface (read-write interface) 903 is connected between processor 901 and memory 902, and can realize information interaction between processor 901 and memory 902, including but not limited to data bus (Bus).

[0152] In some embodiments, the processor 901, memory 902, and I / O interface 903 are interconnected via a bus, and thus connected to other components of the computing device.

[0153] This embodiment also provides a computer-readable medium storing a computer program. When the program is executed by a processor, it implements the traffic light visualization method based on digital twins provided in this embodiment. To avoid repetition, the specific steps of the traffic light visualization method based on digital twins will not be repeated here.

[0154] This disclosure also provides a computer program product, including computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code, wherein when the computer-readable code is run in a processor of an electronic device, the processor in the electronic device executes the above-described signal light visualization method based on digital twins.

[0155] Those skilled in the art will understand that all or some of the steps, systems, or apparatuses in the methods, systems, and apparatuses described above can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software may be distributed on a computer-readable medium, which may include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0156] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0157] Those skilled in the art will understand that although some embodiments described herein include certain features that are included in other embodiments but not others, combinations of features from different embodiments are meant to be within the scope of this embodiment and form different embodiments.

[0158] It is understood that the above embodiments are merely exemplary embodiments used to illustrate the principles of this disclosure, and this disclosure is not limited thereto. For those skilled in the art, various modifications and improvements can be made without departing from the spirit and substance of this disclosure, and these modifications and improvements are also considered to be within the scope of protection of this disclosure.

Claims

1. A signal light visualization method based on digital twinning, characterized in that, The method comprises the following steps: acquiring lane center line data of a target intersection; wherein the lane center line data comprises a plurality of data points arranged in a position sequence, and each data point comprises corresponding position information; determining model position information of a digital twin model corresponding to a signal lamp of the target intersection according to the position information of the data points in the lane center line data; generating a model instance of the digital twin model in a digital twin environment corresponding to the target intersection according to the model position information, and updating display parameters of the model instance according to real-time data corresponding to the signal lamp, so as to realize visual display of the signal lamp of the target intersection.

2. The method of claim 1, wherein, Before the step of determining the model position information of the digital twin model corresponding to the signal lamp of the target intersection according to the position information of the data points in the lane center line data, the method further comprises the following steps: performing scale distortion anomaly detection on a first data point at the end of the lane center line according to the position information of the last two data points in the lane center line data; performing curvature mutation anomaly detection on the first data point at the end of the lane center line according to the position information of the last three data points in the lane center line data; in a case where the first data point at the end of the lane center line has scale distortion anomaly or curvature mutation anomaly, calibrating the first data point at the end of the lane center line, and updating the lane center line data according to a calibration result.

3. The method of claim 2, wherein, The planar coordinates of any data point are determined according to the position information of the data point, and the curvature mutation anomaly detection on the first data point at the end of the lane center line according to the position information of the last three data points in the lane center line data comprises the following steps: determining a first azimuth angle corresponding to a first vector from a third data point at the end to a second data point at the end according to the planar coordinates of the third data point at the end and the second data point at the end; determining a second azimuth angle corresponding to a second vector from the second data point at the end to the first data point at the end according to the planar coordinates of the second data point at the end and the first data point at the end; determining a turning angle corresponding to the first data point at the end according to an angle difference between the second azimuth angle and the first azimuth angle, and determining that the first data point at the end has curvature mutation anomaly in a case where the turning angle is within a preset angle range.

4. The method of claim 2, wherein, The spatial coordinates of any data point are determined according to the position information of the data point, and the scale distortion anomaly detection on the first data point at the end of the lane center line according to the position information of the last two data points in the lane center line data comprises the following steps: determining a data point distance between the first data point at the end and the second data point at the end according to the spatial coordinates of the first data point at the end and the second data point at the end; determining that the first data point at the end has scale distortion anomaly in a case where the data point distance is less than a preset distance threshold.

5. The method of claim 2, wherein, The calibration of the first data point at the end of the lane center line and the updating of the lane center line data according to the calibration result in a case where the first data point at the end of the lane center line has scale distortion anomaly or curvature mutation anomaly comprise the following steps: In a case where the steering angle corresponding to the last first data point is in a first preset angle range, the last first data point in the lane center line data is deleted; In a case where the last first data point has a scale distortion anomaly or the steering angle corresponding to the last first data point is in a second preset angle range, the last first data point is calibrated according to position information of the last third data point and the last second data point, and the lane center line data is updated according to a calibration result.

6. The method of claim 5, wherein, The calibration of the last first data point according to the position information of the last third data point and the last second data point, and the updating of the lane center line data according to a calibration result, include: A connecting line between the last third data point and the last second data point is constructed, and the connecting line is extended to obtain a target extension line; A target perpendicular line is generated from the last first data point to the target extension line, and position information of the last first data point in the lane center line data is updated according to position information of an intersection point of the target perpendicular line and the target extension line.

7. The method according to any one of claims 1 to 6, characterized in that, The model position information includes target position information and a target azimuth angle of the digital twin model; and the determination of the model position information of the digital twin model corresponding to the signal lamp of the target intersection according to the position information of the data points in the lane center line data includes: A third azimuth angle corresponding to a target direction from the last second data point to the last first data point is determined according to the position information of the last first data point and the last second data point in the lane center line data; End point position information is determined according to the third azimuth angle, a model length of the digital twin model, and the position information of the last first data point, by moving a preset distance from the last first data point along the third azimuth angle; wherein the preset distance is determined according to the model length; The target azimuth angle in the model position information is determined according to the third azimuth angle, and the target position information in the model position information is determined according to the end point position information.

8. A signal light visualization device based on digital twinning, characterized by, The method includes: An acquisition module is configured to acquire lane center line data of a target intersection; wherein the lane center line data includes a plurality of data points arranged in a position sequence, and each data point includes corresponding position information; A determination module is configured to determine model position information of a digital twin model corresponding to a signal lamp of the target intersection according to the position information of the data points in the lane center line data; A display module is configured to generate a model instance of the digital twin model in a digital twin environment corresponding to the target intersection according to the model position information, and update a display parameter of the model instance according to real-time data of the signal lamp, so as to realize visual display of the signal lamp of the target intersection.

9. An electronic device, comprising: The method includes: One or more processors; a memory having stored thereon one or more programs, which, when executed by the one or more processors, cause the one or more processors to carry out the digital-twin-based signal light visualization method according to any one of claims 1-7; one or more I / O interfaces connected between the processor and the memory and configured to enable information interaction between the processor and the memory.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program, when executed by a processor, implements the digital-twin-based signal light visualization method according to any one of claims 1-7.

Images