A signal light data abnormality processing method, system, device and medium
By receiving traffic light data and real-time traffic information to identify anomalies and correct the status of traffic light data, the problem of abnormal traffic light data has been solved, the reliability and accuracy of traffic light data have been improved, and traffic management has been optimized.
Patent Information
- Application Number
- CN202411160771.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-22
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-08-22
AI Technical Summary
Existing technologies cannot detect and correct traffic light data anomalies in a timely manner, resulting in traffic participants being unable to obtain accurate real-time information about the status of traffic lights at holographic intersections, thus reducing road traffic efficiency and safety.
By receiving traffic light data and real-time traffic information from the target intersection, the system can determine the data status, identify anomalies, and perform error correction or compensation to ensure the reliability and timeliness of the traffic light data.
This improves the reliability and accuracy of traffic light data, ensuring that autonomous vehicles can obtain traffic light information in a timely and accurate manner, optimizing traffic signal control, and reducing traffic congestion and waiting time.
Smart Images

Figure CN118675355B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of signal light data technology, and in particular to a signal light data exception processing method, system, device and medium. Background Art
[0002] With the rapid development of intelligent transportation systems, holographic intersections play a vital role in intelligent transportation systems. As one of the key functions provided by holographic intersections, traffic light data sharing not only provides timely and accurate information about the status of traffic lights at the intersection ahead to traffic participants, but also enables traffic participants to perceive traffic light data at multiple intersections ahead beyond line of sight, so as to make more intelligent and efficient travel decisions. At present, traffic light data can be obtained through roadside signal acquisition cards or in cooperation with transportation departments, and traffic light data can also be predicted through sample vehicle trajectory data prediction methods and multi-source data fusion prediction methods. However, when encountering situations such as intersection signal control cycle adjustments, the collected traffic light data may be inconsistent with the actual traffic light data, and the above-mentioned related technologies cannot detect and correct erroneous traffic light data in a timely manner, making it impossible for traffic participants to accurately know the status of holographic intersection traffic lights in real time, reducing road traffic efficiency and safety.
[0003] Therefore, the present invention proposes a signal light data exception processing method, system, device and medium to solve the above-mentioned defects. Summary of the invention
[0004] In view of this, the present invention proposes a method, system, device and medium for handling traffic light data anomalies, which solve the problems of data anomalies, low data accuracy and so on that occur during the traffic light data sharing process, timely discover and correct abnormal data, and ensure the reliability, availability and timeliness of traffic light data.
[0005] Based on the above purpose, an embodiment of the present invention provides a method for processing abnormal signal light data, which specifically includes the following steps:
[0006] Receiving first traffic light data of a target intersection, and acquiring real-time traffic information corresponding to the target intersection;
[0007] In response to receiving the first signal light data, determining a state of the first signal light data based on the real-time traffic information;
[0008] In response to the state of the first signal light data being abnormal, determining second signal light data based on the real-time traffic information;
[0009] The first signal light data in an abnormal state is updated based on the second signal light data.
[0010] In some implementations, the signal light data exception processing method further includes:
[0011] In response to not receiving the first signal light data, determining second signal light data based on the real-time traffic information;
[0012] The first signal light data that is not received is compensated based on the second signal light data.
[0013] In some implementations, the step of determining the state of the first signal light data based on the real-time traffic information includes:
[0014] Determine, according to the first signal light data, the first signal light colors corresponding to the preset phases in the target intersection;
[0015] Based on the real-time traffic information, determining first characteristic values corresponding to the preset phases respectively;
[0016] Based on each of the first characteristic values, determining the second signal light color corresponding to each of the preset phases;
[0017] Determining whether the first signal light color and the second signal light color corresponding to each of the preset phases are the same;
[0018] If there is at least one of the preset phases corresponding to the first signal light color and the second signal light color are different, determining that the state of the first signal light data is abnormal;
[0019] The preset phases include north-south straight going, north-south left turn, north-south right turn, east-west straight going, east-west left turn and / or east-west right turn.
[0020] In some implementations, the step of determining the second signal light data based on the real-time traffic information includes:
[0021] Based on the real-time traffic information, determining a target sequence corresponding to each preset phase in the target intersection from all preset sequences;
[0022] Based on each of the target sequences, determining the target signal light colors and target countdown data corresponding to each of the preset phases;
[0023] All the target signal light colors and all the target countdown data are used as the second signal light data.
[0024] In some implementations, the signal light data exception processing method further includes:
[0025] Acquire historical traffic information of the target intersection, and analyze the types, movement directions and positions of all historical traffic participants according to the historical traffic information;
[0026] Based on a preset period, the types, movement directions and positions of all the historical traffic participants, constructing a plurality of first sequences corresponding to each of the preset phases;
[0027] All of the first sequences are taken as all of the preset sequences.
[0028] In some implementations, the step of determining, from among all preset sequences, a target sequence corresponding to each preset phase in the target intersection based on the target intersection traffic information, comprises:
[0029] Determining a target time based on the real-time traffic information;
[0030] Based on the target time, a target sequence corresponding to each preset phase is determined in all the preset sequences.
[0031] In some implementations, the step of receiving the first signal light data of the target intersection includes:
[0032] Monitor traffic information at all holographic intersections;
[0033] Based on all the intersection traffic information, determining whether there is a target intersection where the number of traffic participants meets a preset number threshold;
[0034] In response to the existence of a target intersection where the number of traffic participants meets a preset number threshold, traffic light data of the target intersection is received and the traffic light data is used as the first traffic light data.
[0035] Another aspect of the embodiment of the present invention further provides a signal light data exception processing system, including:
[0036] A receiving unit configured to receive first signal light data of a target intersection and obtain real-time traffic information corresponding to the target intersection;
[0037] a determination unit configured to determine a state of the first signal light data based on the real-time traffic information in response to receiving the first signal light data;
[0038] a processing unit configured to determine second signal light data based on the real-time traffic information in response to the state of the first signal light data being abnormal;
[0039] An updating unit is configured to update the first signal light data in an abnormal state based on the second signal light data.
[0040] According to another aspect of an embodiment of the present invention, a computer device is provided, comprising: at least one processor; and a memory, wherein the memory stores a computer program executable on the processor, and the computer program implements the steps of the above method when executed by the processor.
[0041] According to another aspect of the embodiments of the present invention, a computer-readable storage medium is provided, which stores a computer program that implements the above method steps when executed by a processor.
[0042] The present invention has at least the following beneficial technical effects:
[0043] The method for handling abnormal signal light data of the present invention promptly confirms whether a link for collecting the first signal light data fails according to the reception status of the first signal light data, and verifies the collected first signal light data in combination with real-time traffic information after receiving the data, so as to promptly discover whether the status of the first signal light data is abnormal, and adopt an error correction mechanism to correct the first signal light data when the status is abnormal, thereby ensuring that the signal light data received by the networked vehicle is more accurate, so as to better serve the decision-making of the autonomous driving vehicle, and improve the reliability, accuracy and timeliness of the signal light data in the holographic intersection. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other embodiments can be obtained based on these drawings without paying creative work.
[0045] Figure 1 A schematic diagram of an embodiment of a process for collecting and sending traffic light data;
[0046] Figure 2 A block diagram of an embodiment of a method for processing abnormal signal light data provided by the present invention;
[0047] Figure 3 A schematic diagram of an embodiment of a target intersection provided by the present invention;
[0048] Figure 4 A schematic diagram of an embodiment of a signal light data abnormality processing flow provided by the present invention;
[0049] Figure 5 A schematic diagram of an embodiment of a signal light data abnormality processing system provided by the present invention;
[0050] Figure 6 A schematic diagram of the structure of an embodiment of a computer device provided by the present invention;
[0051] Figure 7 A schematic diagram of the structure of an embodiment of a computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION
[0052] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the embodiments of the present invention are further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.
[0053] It should be noted that all expressions using "first" and "second" in the embodiments of the present invention are for distinguishing two non-identical entities with the same name or non-identical parameters. It can be seen that "first" and "second" are only for the convenience of expression and should not be understood as limitations on the embodiments of the present invention. The subsequent embodiments will not explain this one by one.
[0054] Figure 1 The figure is a schematic diagram of an embodiment of the process of collecting and sending traffic light data. The collection of traffic light data is generally carried out in real time by installing a roadside signal machine acquisition card, or by cooperating with the traffic department to collect data in real time by connecting to the traffic bureau. The collected real-time traffic light data is processed and sent to the RSU (Roadside Unit, roadside intelligent terminal) or networked vehicle deployed on the roadside. By acquiring traffic light data in real time, networked vehicles can help vehicles make more intelligent and safe driving decisions, plan driving routes and speeds more accurately, and reduce waiting time at intersections, thereby improving overall traffic efficiency and safety. However, when encountering situations such as intersection signal control cycle adjustment, the collected real-time traffic light data may be inconsistent with the actual traffic light data. The relevant technology does not involve a solution for abnormal monitoring and error correction of the collected traffic light data, resulting in the inability to timely correct the abnormal collected traffic light data, making it impossible for networked vehicles to accurately know the status of holographic intersection traffic lights in real time, reducing the reliability of traffic light data. Moreover, when the signal light collection equipment fails or the signal light data network connected to the traffic department fails, that is, when the holographic intersection signal light data cannot be collected in real time, the related technology does not provide a compensation mechanism to provide the function of sending signal light data during the collection failure, which reduces the availability of signal light data. In response to the above-mentioned defects in signal light data collection, the related technology provides a method for predicting sample vehicle trajectory data and a method for fusion prediction of multi-source data to provide real-time signal light data to networked vehicles. However, due to the factors of vehicle positioning accuracy, driver reaction time or driver driving habits, the accuracy of the signal light data provided by the above-mentioned prediction method is relatively lower than the accuracy of the signal light data collected in real time. Figure 1MQTT (Message Queuing Telemetry Transport, a lightweight messaging protocol) is used to share data between vehicles and remote servers in the Internet of Vehicles, and SDK (Software Development Kit) is used to ensure that data can be transmitted to on-board devices securely and reliably.
[0055] In order to solve the above defects and provide holographic intersection signal light data in a timely and accurate manner, a method for handling signal light data anomalies is provided in the first aspect of the embodiment of the present invention. Figure 2 As shown, it includes the following steps:
[0056] Step S100, receiving first traffic light data of a target intersection, and acquiring real-time traffic information corresponding to the target intersection.
[0057] In some embodiments, the first signal light data refers to the signal light data collected in real time through a signal light acquisition card or by connecting to the traffic bureau data. The first signal light data includes the light color and countdown information of the traffic lights in each phase. The target intersection is a holographic intersection where the number of traffic participants meets the preset number threshold. The first signal light data is received in real time at a frequency of 10Hz (i.e., every 0.1 seconds), and it is possible to determine whether the signal light data collection link fails by monitoring whether the first signal light data is received within this frequency, that is, to determine whether the signal light collection equipment fails or whether the signal light data network connected to the traffic department is abnormal. If the first signal light data is received in real time at a frequency of 10Hz, the status of the signal light data collection link is normal, and then the status of the first signal light data received at this time is determined.
[0058] In some embodiments, traffic information at the intersection is collected in real time by infrastructure installed at the holographic intersection, such as cameras, radars, or LiDAR (laser radar). The real-time traffic information corresponding to the target intersection includes data such as the type, number, location, speed, heading angle, and collection time of traffic participants at the target intersection. The types of traffic participants include pedestrians, motor vehicles, and non-motor vehicles. The locations of traffic participants include before the stop line and inside the intersection.
[0059] Step S200 , in response to receiving the first signal light data, determining the state of the first signal light data based on the real-time traffic information.
[0060] In some embodiments, after receiving the first signal light data, the real-time traffic information corresponding to the target intersection is combined with a high-precision map to analyze the movement status of all traffic participants in each phase of the target intersection at the current moment, so as to identify whether the first signal light data is consistent with the actual signal light data in the target intersection, thereby determining whether the status of the first signal light data is abnormal.
[0061] Step S300: in response to the state of the first signal light data being abnormal, determining second signal light data based on real-time traffic information.
[0062] In some embodiments, when it is identified that the first signal light data is inconsistent with the actual signal light data at the target intersection, the state of the first signal light data is determined to be abnormal, and signal light data that conforms to the actual signal light state is predicted using real-time traffic information as the second signal light data.
[0063] Step S400: updating the first signal light data in an abnormal state based on the second signal light data.
[0064] In some implementations, the first signal light data in an abnormal state is updated to the second signal light data to achieve an effect of correcting the first signal light data in an abnormal state. Figure 4 As shown, the corrected signal light data is sent to the vehicle-side device to ensure that the vehicle-side device can obtain the signal light data in a timely and accurate manner, providing more intelligent driving assistance for networked vehicles and helping networked vehicles to understand the status of the signal lights at the intersection ahead in advance, so as to make safer driving decisions. Sending the corrected signal light data to the roadside device ensures that the roadside device can obtain the signal light data in a timely and accurate manner, which helps to optimize traffic signal control and reduce traffic congestion and waiting time.
[0065] The method for handling abnormal signal light data of the present invention timely discovers whether a link for collecting the first signal light data fails according to the reception status of the first signal light data, and verifies the collected first signal light data in combination with real-time traffic information after receiving it, so as to timely discover whether the status of the first signal light data is abnormal, and adopts an error correction mechanism to correct the first signal light data when the status is abnormal, thereby ensuring that the signal light data received by the networked vehicle is more accurate, so as to better serve the decision-making of the autonomous driving vehicle, and improve the reliability, accuracy and timeliness of the signal light data in the holographic intersection.
[0066] In some embodiments, the signal light data exception processing method of the present invention further includes: in response to not receiving the first signal light data, determining the second signal light data based on the real-time traffic information; and compensating for the unreceived first signal light data based on the second signal light data.
[0067] In some embodiments, if the first signal light data is not received at a frequency of 10 Hz, it means that the time waiting to receive the first signal light data has exceeded 0.1 seconds since the last successful reception of the first signal light data. At this time, the signal light data collection link fails and the first signal light data needs to be compensated. In the event that the signal light data collection link fails, the real-time traffic information corresponding to the target intersection is collected and combined with the high-precision map to analyze the movement status of all traffic participants in each phase of the target intersection at the current moment, so as to predict the second signal light data that conforms to the actual signal light status, and use the second signal light data as compensation data for the first signal light data that has not been collected. Furthermore, if Figure 4 As shown, the compensated traffic light data is sent to the vehicle-side equipment and the roadside equipment to avoid the problem of reduced availability of traffic light data caused by failure of the traffic light data collection link, thereby ensuring road traffic efficiency and safety.
[0068] The method for handling abnormal signal light data of the present invention discovers the failure of the link for collecting the first signal light data according to the reception status of the first signal light data, and promptly adopts a compensation mechanism to avoid the situation where the signal light data cannot be normally obtained when the signal light collection equipment fails or the signal light data network connected to the traffic department is abnormal, thereby ensuring the availability and timeliness of the signal light data.
[0069] In some embodiments, the step of determining the state of the first signal light data based on real-time traffic information includes: determining the first signal light color corresponding to each preset phase in the target intersection according to the first signal light data; determining the first eigenvalue corresponding to each preset phase based on the real-time traffic information; determining the second signal light color corresponding to each preset phase based on each first eigenvalue; judging whether the first signal light color and the second signal light color corresponding to each preset phase are the same; if there is at least one preset phase corresponding to which the first signal light color and the second signal light color are different, determining that the state of the first signal light data is abnormal; wherein the preset phases include north-south straight going, north-south left turn, north-south right turn, east-west straight going, east-west left turn and / or east-west right turn.
[0070] In some embodiments, real-time traffic information is analyzed in combination with high-precision map data to determine the heading angle of each traffic participant at the target intersection, and the heading angle of each traffic participant is compared with a preset angle threshold, and the movement direction of each traffic participant is distinguished according to the comparison result, and then all traffic participants are classified into corresponding preset phases according to the movement direction of each traffic participant. For example, when the analysis shows that the heading angle of a traffic participant is 0°, it satisfies the following conditions: ~10° preset angle threshold, at this time the direction of movement of the traffic participant is toward or away from the north or south direction, and the traffic participant is classified into the preset phase of north-south straight travel. When the analysis shows that the heading angle of a traffic participant is 60°, it meets the preset angle threshold of 20°~100°. At this time, the direction of movement of the traffic participant is deviating from the north or south to the left, and the traffic participant is classified into the preset phase of north-south left turn. When the analysis shows that the heading angle of a traffic participant is , which satisfies ~ The preset angle threshold is set to , at this time, the direction of movement of the traffic participant is deviating from due north or due south to the right, and the traffic participant is classified into the preset phase of north-south right turn. The classification method for traffic participants corresponding to east-west straight, east-west left turn and east-west right turn is similar, except that the reference direction becomes due east or due west. The specific values of the above preset angle thresholds are only used as examples and are not used as limitations on the preset angle thresholds. They can be set according to actual application requirements.
[0071] In some embodiments, Figure 3 This is a schematic diagram of an embodiment of a target intersection provided by the present invention, where a road in each preset phase in the target intersection is divided into two areas: an area before a stop line and an intersection area. Figure 3 Area A in the middle is the intersection area. Figure 3The B1, B2, B3 and B4 areas are the areas before the stop line. The area before the stop line refers to the area within a preset distance threshold (such as 10 meters) from the stop line. For the area before the stop line, the number of each type of traffic participants in each preset phase is counted respectively. For example, when the traffic lights include lights for left turn, straight ahead and right turn and the target intersection is a crossroads, the preset phases include north-south straight ahead, north-south left turn, north-south right turn, east-west straight ahead, east-west left turn and east-west right turn, and the number of each type of traffic participants in each preset phase is counted respectively. When the traffic lights only include lights for left turn and straight ahead and the target intersection is only a southbound road, the preset phases include north-south straight ahead and north-south left turn, and the number of each type of traffic participants in each preset phase is counted respectively. For the intersection area, the number of each type of traffic participants in the intersection area is counted respectively. Set corresponding weight values for each type of traffic participant respectively, wherein the weight value of motor vehicles is greater than the weight value of non-motor vehicles, and the weight value of non-motor vehicles is greater than the weight value of pedestrians. For the area before the stop line at any time, the eigenvalue A corresponding to each preset phase is calculated according to the weight value and number of each type of traffic participant in each preset phase. For example, for the north-south straight phase in the area before the stop line, assuming that the number of motor vehicles, the number of non-motor vehicles, and the number of pedestrians are 10, 3, and 5 at time T0, and the weight value of motor vehicles is 5, the weight value of non-motor vehicles is 3, and the weight value of pedestrians is 1, then the eigenvalue A corresponding to the north-south straight phase at time T0 is ,Right now For the north-south left-turn phase in the area before the stop line, assuming that the number of motor vehicles, the number of non-motor vehicles, and the number of pedestrians at time T0 are 3, 1, and 0, the eigenvalue A corresponding to the north-south left-turn phase at time T0 is ,Right now For the intersection area, the eigenvalue B corresponding to the intersection area is calculated according to the weight value and number of each type of traffic participants. For example, for the intersection area, assuming that the number of motor vehicles, non-motor vehicles, and pedestrians at time T0 is 5, then the eigenvalue B corresponding to the intersection area at time T0 is 50, that is, The corresponding first eigenvalue is determined according to the sum of the eigenvalue A and the eigenvalue B corresponding to each preset phase at the same time. Continuing with the above example, the first eigenvalue corresponding to the north-south straight phase in the target intersection at time T0 can be calculated as 14 (i.e. ), the first eigenvalue corresponding to the north-south left-turn phase is 32 (i.e. ). It should be noted that the signs of the eigenvalue A calculated in the area before the stop line and the eigenvalue B calculated in the intersection area are opposite. This is because when the sports participant is in the area before the stop line, his / her motion state is usually static, and when the sports participant is in the intersection area, his / her motion state is usually moving. Therefore, different signs are used to calculate the corresponding eigenvalues.
[0072] In some embodiments, the traffic light colors include red and green. According to the positive and negative signs of the first eigenvalues corresponding to the preset phases obtained by the above calculation, the traffic light colors corresponding to the preset phases are determined and used as the second traffic light colors. For example, if the first eigenvalue corresponding to a preset phase at the current moment is a positive value, it means that the motion state of most traffic participants in the preset phase at the current moment is moving, so the traffic light color corresponding to the preset phase at the current moment is green. If the first eigenvalue corresponding to a preset phase at the current moment is a negative value, it means that the motion state of most traffic participants in the preset phase at the current moment is stationary, so the traffic light color corresponding to the preset phase at the current moment is red. Continuing with the above example, the first eigenvalue corresponding to the north-south straight phase at time T0 is calculated to be It can be determined that the second signal light color corresponding to the north-south straight phase at time T0 is red, and the first eigenvalue corresponding to the north-south left turn phase at time T0 is 32. It can be determined that the second signal light color corresponding to the north-south left turn phase at time T0 is green.
[0073] In some embodiments, the first signal light color of each preset phase is determined according to the first signal light data, that is, it is the signal light color collected in real time through a signal acquisition card or by connecting to the traffic bureau data. The first signal light color and the second signal light color of each preset phase at the same time are compared one by one. When the first signal light color and the second signal light color of any one or more preset phases are inconsistent, it can be verified that the state of the collected first signal light data is abnormal. For example, the preset phases include north-south straight driving and north-south left turning. At time T0, the first signal light color corresponding to the north-south straight driving phase is green, and the corresponding second signal light color is red, or at time T0, the first signal light color corresponding to the north-south left turning phase is red, and the corresponding second signal light color is green, then the state of the first signal light data is determined to be abnormal. Timely discover the first signal light data in abnormal state so that the first signal light data can be corrected in time later.
[0074] The signal light data anomaly processing method of the present invention combines real-time traffic information with high-precision maps to analyze the movement status of various types of traffic participants in each preset phase of the target intersection at the current moment, so as to predict the second signal light color of each preset phase of the target intersection. It can identify the status of the first signal light data according to the second signal light color, and promptly discover the anomaly of the first signal light data, so as to facilitate the rapid activation of the error correction mechanism, thereby ensuring the reliability, accuracy and timeliness of the signal light data received by the networked vehicles.
[0075] In some embodiments, the step of determining the second signal light data based on real-time traffic information includes: based on the real-time traffic information, determining a target sequence corresponding to each preset phase in the target intersection from all preset sequences; based on each target sequence, determining a target signal light color and a target countdown data corresponding to each preset phase; and using all target signal light colors and all target countdown data as the second signal light data.
[0076] In some embodiments, the signal light colors corresponding to each preset phase at each moment in a preset cycle are obtained in advance based on historical intersection traffic information analysis, and the signal light colors of the same preset phase at each moment are sorted in chronological order to form a light color time sequence, which is the preset sequence (i.e., the first preset sequence) corresponding to each preset phase in the preset cycle. The duration of each signal light color of each preset phase can be obtained according to the first preset sequence. In one example, the north-south straight phase of the target intersection is taken as an example to illustrate the process of determining the target signal light color and target countdown data corresponding to the preset phase. Assuming that the target sequence is "red light (00:00:00~00:00:20)-green light (00:00:20~00:00:50)-red light (00:00:50~00:01:10)...red light (00:29:10~00:30:00)", if the current time is "00:00:56", it can be determined that the target signal light color corresponding to the north-south straight phase is red light, and the target countdown data is 14s. Similarly, other preset phases can determine their corresponding target signal light colors and target countdown data according to the corresponding target sequence and the current time, and then all target signal light colors and all target countdown data at the current time are used as the second signal light data.
[0077] The method for handling abnormal signal light data of the present invention, when the state of the first signal light data is abnormal or the collection link fails, predicts the second signal light data consistent with the actual signal light data based on a preset sequence and real-time traffic information, corrects the abnormal first signal light data or compensates for the first signal light data that has not been received, effectively avoiding the situation where the networked vehicle cannot timely and accurately know the signal light status when the first signal light data is abnormal or missing, so that the networked vehicle can plan the driving route and speed more accurately.
[0078] In some embodiments, the traffic light data anomaly processing method of the present invention also includes: obtaining historical traffic information of the target intersection, analyzing the types, movement directions and positions of all historical traffic participants based on the historical traffic information; constructing first sequences corresponding to each preset phase based on a preset period, the types, movement directions and positions of all historical traffic participants; and taking all first sequences as all preset sequences.
[0079] In some embodiments, the preset period is set according to the length of a natural day and the length of the preset period. For example, if the length of the preset period is set to 30 minutes, then a day is divided into 30-minute periods, and there are a total of 48 time periods, each of which is considered a preset period. All preset periods can be numbered in chronological order:
[0080] The first preset cycle: 0 minutes to 30 minutes;
[0081] The second preset cycle: 30 minutes to 60 minutes;
[0082] The third preset cycle: 1 hour 0 minutes to 1 hour 30 minutes.
[0083] And so on, until the 48th preset cycle:
[0084] 48th preset cycle: 23 hours 30 minutes - 24 hours 0 minutes.
[0085] In some embodiments, each preset phase corresponds to a first sequence in different preset periods. For example, continuing with the above example, if the preset phases include north-south straight travel and north-south left turn, the north-south straight travel phase corresponds to 48 first sequences, and the north-south left turn phase corresponds to 48 first sequences. All first sequences of all preset phases are taken as all preset sequences, and there are a total of 96 preset sequences.
[0086] In some embodiments, because the traffic management department will formulate the timing plan of the traffic lights according to the traffic conditions and needs of different time periods, for example, in the period of "7 hours and 0 minutes to 9 hours and 30 minutes", due to the significant increase in traffic flow, in order to more effectively manage traffic flow, a shorter signal cycle may be used to switch phases faster, that is, the duration of each signal light color in each phase is shorter, so that vehicles and pedestrians in all directions can get more balanced passage opportunities, reducing congestion and delays. Therefore, according to the light timing of actual traffic signals in different time periods, the present invention constructs multiple first sequences corresponding to each preset phase by setting a preset cycle. The shorter the length of the preset cycle, the higher the accuracy of the constructed first sequence. When the second signal light data at a certain moment is inconsistent with the actual signal light data, the abnormal first sequence corresponding to the preset cycle to which the moment belongs can be optimized in a targeted manner. Compared with the light color time sequence corresponding to a fixed cycle (such as a fixed cycle of one day), its optimization efficiency is higher. The length of the preset cycle can be set according to actual application needs. Furthermore, since the timing of the light colors of the traffic lights in different time periods is different in actual traffic lights, the light colors and timing of the traffic lights in the first sequence in different preset cycles for the same preset phase are also different.
[0087] In some embodiments, historical traffic information is analyzed in combination with high-precision map data to obtain the type, movement direction, and position of historical traffic participants at the target intersection at each moment in each preset period, determine the area where the historical traffic participants are located (the area before the stop line or the intersection area) based on their positions, and calculate the historical characteristic values corresponding to each preset phase at each moment in each preset period according to the types of historical traffic participants and the corresponding weight values, and determine the color of the traffic light according to the positive and negative signs of each historical characteristic value. For each preset phase, the color of the traffic light at each moment is sorted according to the time sequence of the preset period, and the first sequence corresponding to each preset phase in different preset periods can be obtained. The calculation method of the historical characteristic value is consistent with the calculation method of the first characteristic value mentioned above. In one example, assuming that the preset phases of the target intersection include north-south straight driving and north-south left turning, the preset period takes the first preset period as an example, and the process of constructing the first sequence is explained below: if it is calculated according to the historical traffic information that from time T1 (00:00:00) to time T2 (00:05:30), the historical characteristic values corresponding to the north-south straight driving phases are all negative values, and the historical characteristic values corresponding to the north-south left turning phases are all positive values; from time T3 (00:05:30) to time T4 (00:15:00), the historical characteristic values corresponding to the north-south straight driving phases are all positive values, and the historical characteristic values corresponding to the north-south left turning phases are all negative values; from time T5 (00:15:00) to time T6 (00:20:30), the historical characteristic values corresponding to the north-south straight driving phases are all negative values, and the historical characteristic values corresponding to the north-south left turning phases are all positive values; at time T7 ( From time T1 (00:20:30) to time T8 (00:30:00), the historical characteristic values corresponding to the north-south straight phase are all positive, and the historical characteristic values corresponding to the north-south left turn phase are all negative; then the first sequence corresponding to the north-south straight phase in the first preset cycle is "red light (00:00:01~00:05:30)-green light (00:05:30~00:15:00)-red light (00:15:00~ The first sequence corresponding to the north-south left turn phase in the first preset cycle is “green light (00:00:01~00:05:30)-red light (00:05:30~00:15:00)-green light (00:15:00~00:20:30)-red light (00:20:30~00:30:00)”.
[0088] The signal light data exception processing method of the present invention can dynamically optimize all preset sequences by setting a preset cycle to facilitate the targeted construction or adjustment of the data in each first sequence, thereby ensuring that the second signal light data predicted at any time can be consistent with the actual signal light data, so that the signal light data received by the networked vehicle is more accurate.
[0089] In some embodiments, the step of determining, in all preset sequences, a target sequence corresponding to each preset phase in the target intersection based on real-time traffic information includes: determining a target time based on real-time traffic information; and determining, in all preset sequences, a target sequence corresponding to each preset phase based on the target time.
[0090] In some embodiments, the current time is determined according to the real-time traffic information, and then the corresponding preset period is determined according to the time period to which the current time belongs, and the preset sequence corresponding to each preset phase in the preset period is used as its corresponding target sequence. For example, when the preset phases include north-south straight driving and north-south left turning, the current time is determined to be 01:00:56 according to the implemented traffic information, and then it can be known that the current time corresponds to the third preset period (1 hour and 0 minutes to 1 hour and 30 minutes), and the target sequence of the north-south straight driving phase and the north-south left turning phase in the third preset period is determined among all preset sequences.
[0091] The traffic light data anomaly processing method of the present invention adjusts the selection of the target sequence by monitoring the real-time traffic information, ensures that the second traffic light data is consistent with the actual traffic light data, and improves the accuracy of the traffic light data sent to the terminal device.
[0092] In some embodiments, the step of receiving first signal light data of a target intersection includes: monitoring intersection traffic information of all holographic intersections; based on the traffic information of all intersections, determining whether there is a target intersection where the number of traffic participants meets a preset number threshold; in response to the existence of a target intersection where the number of traffic participants meets the preset number threshold, receiving signal light data of the target intersection, and using the signal light data as first signal light data.
[0093] In some implementations, the real-time number of traffic participants is compared with a set number threshold, and if the number of traffic participants meets (ie exceeds or reaches) the set number threshold, the holographic intersection is marked as a target intersection.
[0094] The traffic light data anomaly processing method of the present invention filters out target intersections where the number of traffic participants meets a set threshold, and monitors the traffic light data of the target intersections, which has significant advantages in improving traffic management efficiency, enhancing decision-making support capabilities, and improving public safety levels.
[0095] In some embodiments, the present invention can also establish a prediction model for intersection signal light data by learning and analyzing historical signal light data, and use it together with the signal light data anomaly processing method of the present invention to predict intersection signal light data.
[0096] Based on the same inventive concept, according to another aspect of the present invention, Figure 5As shown, an embodiment of the present invention further provides a signal light data exception processing system, comprising:
[0097] The receiving unit 110 is configured to receive first signal light data of a target intersection and obtain real-time traffic information corresponding to the target intersection;
[0098] a determination unit 120, configured to determine a state of the first signal light data based on the real-time traffic information in response to receiving the first signal light data;
[0099] The processing unit 130 is configured to determine second signal light data based on the real-time traffic information in response to the state of the first signal light data being abnormal;
[0100] The updating unit 140 is configured to update the first signal light data in an abnormal state based on the second signal light data.
[0101] The signal light data exception processing system of the present invention promptly confirms whether the link for collecting the first signal light data is faulty according to the reception status of the first signal light data, and verifies the collected first signal light data in combination with real-time traffic information after receiving it, so as to promptly discover whether the status of the first signal light data is abnormal, and adopts an error correction mechanism to correct the first signal light data when the status is abnormal, thereby ensuring that the signal light data received by the networked vehicle is more accurate, so as to better serve the decision-making of the autonomous driving vehicle, and improve the reliability, accuracy and timeliness of the signal light data in the holographic intersection.
[0102] Based on the same inventive concept, according to another aspect of the present invention, Figure 6 As shown, an embodiment of the present invention further provides a computer device 30, which includes a processor 310 and a memory 320. The memory 320 stores a computer program 321 that can be run on the processor. When the processor 310 executes the program, the steps of the above method are performed.
[0103] Based on the same inventive concept, according to another aspect of the present invention, Figure 7 As shown, an embodiment of the present invention further provides a computer-readable storage medium 40, which stores a computer program 410 for executing the above method when executed by a processor.
[0104] Finally, it should be noted that a person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium of the program can be a disk, an optical disk, a read-only storage memory (ROM) or a random access memory (RAM), etc. The above-mentioned computer program embodiments can achieve the same or similar effects as the corresponding above-mentioned any method embodiments.
[0105] It will also be appreciated by those skilled in the art that various exemplary logic blocks, modules, circuits and algorithm steps described in conjunction with the disclosure herein can be implemented as electronic hardware, computer software or a combination of the two. In order to clearly illustrate this interchangeability of hardware and software, a general description has been given to the functions of various schematic components, blocks, modules, circuits and steps. Whether this function is implemented as software or hardware depends on specific applications and the design constraints imposed on the entire system. Those skilled in the art can implement the function in various ways for each specific application, but this implementation decision should not be interpreted as causing a departure from the disclosed scope of the embodiments of the present invention.
[0106] The above are exemplary embodiments disclosed in the present invention, but it should be noted that various changes and modifications may be made without departing from the scope of the embodiments disclosed in the present invention as defined in the claims. The functions, steps and / or actions of the method claims according to the disclosed embodiments described herein do not need to be performed in any particular order. The serial numbers of the embodiments disclosed in the above embodiments of the present invention are for description only and do not represent the advantages and disadvantages of the embodiments. In addition, although the elements disclosed in the embodiments of the present invention may be described or required in individual form, they may also be understood as multiple unless explicitly limited to the singular.
[0107] It should be understood that, as used herein, the singular forms "a", "an" are intended to include the plural forms as well, unless the context clearly supports an exception. It should also be understood that, as used herein, "and / or" refers to any and all possible combinations including one or more of the associated listed items.
[0108] A person skilled in the art should understand that the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope of the disclosure of the embodiments of the present invention (including the claims) is limited to these examples; under the concept of the embodiments of the present invention, the technical features in the above embodiments or different embodiments can also be combined, and there are many other changes in different aspects of the above embodiments of the present invention, which are not provided in detail for the sake of simplicity. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present invention should be included in the protection scope of the embodiments of the present invention.
Claims
1. A method for processing abnormal signal light data, characterized in that: include: Receiving first traffic light data of a target intersection, and acquiring real-time traffic information corresponding to the target intersection; In response to receiving the first signal light data, determining a state of the first signal light data based on the real-time traffic information; In response to the state of the first signal light data being abnormal, determining second signal light data based on the real-time traffic information; updating the first signal light data in an abnormal state based on the second signal light data; The step of determining the state of the first signal light data based on the real-time traffic information comprises: Determine, according to the first signal light data, the first signal light colors corresponding to the preset phases in the target intersection; Based on the real-time traffic information, determining first characteristic values corresponding to the preset phases respectively; Based on each of the first characteristic values, determining the second signal light color corresponding to each of the preset phases; Determining whether the first signal light color and the second signal light color corresponding to each of the preset phases are the same; If there is at least one of the preset phases corresponding to the first signal light color and the second signal light color are different, determining that the state of the first signal light data is abnormal; The preset phases include north-south straight going, north-south left turn, north-south right turn, east-west straight going, east-west left turn and / or east-west right turn.
2. The signal light data abnormality processing method according to claim 1, characterized in that: Also includes: In response to not receiving the first signal light data, determining second signal light data based on the real-time traffic information; The first signal light data that is not received is compensated based on the second signal light data.
3. The method for processing abnormal signal light data according to claim 1 or 2, characterized in that: The step of determining the second signal light data based on the real-time traffic information comprises: Based on the real-time traffic information, determining a target sequence corresponding to each preset phase in the target intersection from all preset sequences; Based on each of the target sequences, determining the target signal light colors and target countdown data corresponding to each of the preset phases; All the target signal light colors and all the target countdown data are used as the second signal light data.
4. The method for processing abnormal signal light data according to claim 3, characterized in that: Also includes: Acquire historical traffic information of the target intersection, and analyze the types, movement directions and positions of all historical traffic participants according to the historical traffic information; Based on a preset period, the types, movement directions and positions of all the historical traffic participants, constructing a plurality of first sequences corresponding to each of the preset phases; All of the first sequences are taken as all of the preset sequences.
5. The method for processing abnormal signal light data according to claim 4, characterized in that: The step of determining the target sequence corresponding to each preset phase in the target intersection from all preset sequences includes: Determining a target time based on the real-time traffic information; Based on the target time, a target sequence corresponding to each preset phase is determined in all the preset sequences.
6. The method for processing abnormal signal light data according to claim 1, characterized in that: The step of receiving the first signal light data of the target intersection comprises: Monitor traffic information at all holographic intersections; Based on all the intersection traffic information, determining whether there is a target intersection where the number of traffic participants meets a preset number threshold; In response to the existence of a target intersection where the number of traffic participants meets a preset number threshold, traffic light data of the target intersection is received and the traffic light data is used as the first traffic light data.
7. A signal light data abnormality processing system, characterized in that: include: A receiving unit configured to receive first signal light data of a target intersection and obtain real-time traffic information corresponding to the target intersection; a determination unit configured to determine a state of the first signal light data based on the real-time traffic information in response to receiving the first signal light data; a processing unit configured to determine second signal light data based on the real-time traffic information in response to the state of the first signal light data being abnormal; an updating unit, configured to update the first signal light data in an abnormal state based on the second signal light data; The determination unit is further configured to: determine the first signal light colors corresponding to each preset phase in the target intersection according to the first signal light data; Based on the real-time traffic information, determine the first characteristic value corresponding to each of the preset phases; based on each of the first characteristic values, determine the second signal light color corresponding to each of the preset phases; determine whether the first signal light color and the second signal light color corresponding to each of the preset phases are the same; if there is at least one of the preset phases corresponding to the first signal light color and the second signal light color are different, determine that the state of the first signal light data is abnormal; wherein the preset phases include north-south straight going, north-south left turn, north-south right turn, east-west straight going, east-west left turn and / or east-west right turn.
8. A computer device comprising: at least one processor; as well as A memory storing a computer program executable on the processor, wherein the processor executes the steps of the method according to any one of claims 1 to 6 when executing the program.
9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are performed.
