Traffic light phase mining method and device
By mining traffic light phase and historical trajectory data, accurate prediction of traffic light countdown is achieved, users' anxiety about waiting for cars before traffic lights is solved, and urban road traffic efficiency is improved.
Patent Information
- Application Number
- CN202411203550.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-29
- Publication Date
- 2024-11-26
AI Technical Summary
During navigation and driving, users feel anxious before the traffic light because they cannot obtain accurate countdown information, and the traffic light countdown countdown function is difficult to implement, which affects the efficiency of urban road traffic.
By mining traffic light phases based on historical trajectory data, extracting target trajectory features, determining traffic light candidate phase segments, aggregating and verifying phase information, predicting traffic light countdown, and providing accurate traffic light countdown information.
It improves the accuracy and efficiency of users waiting for cars before traffic lights, reduces user anxiety, improves urban road traffic efficiency, and enhances the accuracy and coverage of traffic light countdown.
Smart Images

Figure CN119028135A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of big data technology, and in particular to the field of map navigation technology. Background Art
[0002] When users use navigation to drive, they will pass by traffic lights. When they encounter a red light, they need to stop and wait. In many cases, users do not know how long they need to wait at the traffic light because the car in front blocks the view or the traffic light in the real world does not display the traffic light countdown information. This requires that the traffic light countdown information be accurately displayed on the navigation page to alleviate the anxiety of users waiting for cars at the traffic lights. At the same time, when the red light is about to turn green, remind the user to get ready to start. This not only saves users' time, but also improves the efficiency of urban road traffic.
[0003] To realize the countdown function of traffic lights, it is necessary to mine the traffic light timing scheme based on historical trajectory data, including but not limited to the total traffic light cycle, red light cycle, green light cycle and phase, etc. At present, the phase of traffic lights can be mined based on the total traffic light cycle, using the phase mining method of a single traffic light trajectory. This scheme assumes that when the total traffic light cycle remains unchanged, the phase does not change. After the total traffic light cycle mining is completed, the time period with stable phase can be obtained. Then, the traffic light phase is mined based on the historical trajectory data in each phase stable time period. Summary of the invention
[0004] The embodiments of the present disclosure provide a traffic light phase mining method, apparatus, device, storage medium, and program product.
[0005] In a first aspect, an embodiment of the present disclosure proposes a traffic light phase mining method, including: extracting a target trajectory feature set based on a historical trajectory data set of vehicles passing through an intersection; determining a candidate traffic light phase segment based on the target trajectory features of the traffic light within a constant time period of a total cycle; aggregating the traffic light candidate phase segments to obtain intersection candidate phase segments; determining an intersection phase segment based on the target trajectory features within the intersection candidate phase segments; determining the traffic light phase based on the target trajectory features of the traffic light within the intersection phase segment.
[0006] In the second aspect, an embodiment of the present disclosure proposes a vehicle navigation method, including: obtaining the current position and current time of a vehicle that is about to pass a traffic light; based on the current position, current time, the total cycle of the traffic light and the phase of the traffic light, predicting the countdown of the traffic light, wherein the phase of the traffic light is mined using the method described in the first aspect.
[0007] In a third aspect, an embodiment of the present disclosure proposes a traffic light phase mining device, comprising: an extraction module, configured to extract a target trajectory feature set based on a historical trajectory data set of vehicles passing through an intersection; a first determination module, configured to determine a candidate traffic light phase segment based on the target trajectory features of the traffic light within a total cycle unchanged time period; an aggregation module, configured to aggregate the traffic light candidate phase segments to obtain intersection candidate phase segments; a second determination module, configured to determine an intersection phase segment based on the target trajectory features within the intersection candidate phase segments; and a third determination module, configured to determine the traffic light phase based on the target trajectory features of the traffic light within the intersection phase segment.
[0008] In a fourth aspect, an embodiment of the present disclosure proposes a vehicle navigation device, comprising: an acquisition module, configured to acquire the current position and current time of a vehicle that is about to pass a traffic light; a prediction module, configured to predict the countdown of the traffic light based on the current position, current time, the total cycle of the traffic light and the phase of the traffic light, wherein the phase of the traffic light is mined using the device described in the third aspect.
[0009] In a fifth aspect, an embodiment of the present disclosure proposes an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in the first aspect or the second aspect.
[0010] In a sixth aspect, an embodiment of the present disclosure proposes a non-transitory computer-readable storage medium storing computer instructions, where the computer instructions are used to cause a computer to execute the method described in the first aspect or the second aspect.
[0011] In a seventh aspect, an embodiment of the present disclosure proposes a computer program product, including a computer program, which implements the method described in the first aspect or the second aspect when executed by a processor.
[0012] The key or important features of the embodiments of the present disclosure are not intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0013] Other features, purposes and advantages of the present disclosure will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings. The drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure. Among them:
[0014] Figure 1 is a flow chart of an embodiment of a traffic light phase mining method according to the present disclosure;
[0015] Figure 2is a flow chart of another embodiment of a traffic light phase mining method according to the present disclosure;
[0016] Figure 3 is a flow chart of an embodiment of a vehicle navigation method according to the present disclosure;
[0017] Figure 4 is a structural schematic diagram of an embodiment of a traffic light phase mining device according to the present disclosure;
[0018] Figure 5 is a structural schematic diagram of an embodiment of a vehicle navigation device according to the present disclosure;
[0019] Figure 6 It is a block diagram of an electronic device used to implement the traffic light phase mining method of the embodiment of the present disclosure. DETAILED DESCRIPTION
[0020] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.
[0021] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.
[0022] Figure 1 A flow chart 100 of an embodiment of a traffic light phase mining method according to the present disclosure is shown. The traffic light phase mining method comprises the following steps:
[0023] Step 101 : extracting a target trajectory feature set based on a historical trajectory dataset of vehicles passing through an intersection.
[0024] In this embodiment, the execution subject of the traffic light total cycle mining method can obtain a historical trajectory data set of vehicles passing through the intersection, and extract a target trajectory feature set based on the historical trajectory data set.
[0025] The execution subject of the traffic light phase mining method is usually a server. The server can be hardware or software. When the server is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or it can be implemented as a single server. When the server is software, it can be implemented as multiple software or software modules (for example, used to provide distributed services), or it can be implemented as a single software or software module. No specific limitation is made here.
[0026] An intersection may be an intersection of at least two roads, such as a crossroads, a T-shaped intersection, etc. An intersection may be provided with at least one traffic light. Vehicles passing through the intersection may travel according to the instructions of the corresponding traffic light. For example, at a crossroads, traffic lights may be provided on all four sides. A left-turn traffic light and a straight-ahead traffic light may be provided on each side. In some cases, a right-turn traffic light may also be provided at the same time.
[0027] The historical trajectory data set can contain a large amount of historical trajectory data of vehicles passing through the intersection. Usually, the traffic light timing scheme on the same day in different weeks is basically unchanged. Therefore, the historical trajectory data of the same day for multiple consecutive weeks can be obtained to generate a historical trajectory data set. Of course, if the traffic light configuration scheme is the same every day, the historical trajectory data of multiple consecutive days can also be obtained to generate a historical trajectory data set.
[0028] Based on the historical trajectory data set, the target trajectory feature set can be extracted. The target trajectory features may include but are not limited to: parking information, start information, and traffic light information. This can refine the description of the vehicle's parking, start, and traffic light status at the traffic light, and more finely realize the description of the traffic light status change.
[0029] Step 102, determining candidate phase segments of the traffic light based on the target trajectory characteristics of the traffic light within the constant time period of the total cycle.
[0030] In this embodiment, the execution entity may determine the candidate phase segment of each traffic light based on the target trajectory characteristics of each traffic light within the constant time period of the total cycle.
[0031] Based on the target trajectory feature set, the total cycle of the traffic light and the total cycle unchanged time period can be determined. The total cycle of the traffic light can be the time interval between the last time the red light switched to green and the current time the red light switched to green. The total cycle unchanged time period can be the time period when the total cycle of the traffic light remains unchanged.
[0032] The total cycle of traffic lights at different traffic lights at the same intersection is the same. The total cycle of traffic lights at different time periods on the same day may be different. For example, the total cycle of traffic lights during the morning peak (such as 7:00 to 9:00) and evening peak (such as 17:00 to 20:00) is usually different from the total cycle of traffic lights during the off-peak period (such as the time period other than the morning peak and evening peak). The total cycle of traffic lights during the morning peak and evening peak is usually longer than the total cycle of traffic lights during the off-peak period. Therefore, it is necessary to first determine the time period when the total cycle remains unchanged, and then mine the total cycle of traffic lights within this time period when the total cycle remains unchanged, so as to ensure the accuracy of the total cycle of traffic lights.
[0033] In some embodiments, the total cycle of the traffic light and the total cycle unchanged time period can be determined by the following steps:
[0034] In the first step, the target trajectory feature set is sorted in chronological order, and the target trajectory features of each traffic light within a preset time period (such as within 10 minutes) are selected.
[0035] The second step is to traverse the natural numbers in a preset interval to obtain a reference cycle, wherein the preset interval may be a range of the total cycle of the traffic light determined based on experience.
[0036] The third step is to take the modulus of the starting point moment of the target trajectory feature of each traffic light in the preset time period for each reference cycle to obtain the starting point phase of each traffic light in each reference cycle.
[0037] The fourth step is to select a candidate cycle of each traffic light from the reference cycle based on the distribution of the start point phase of each traffic light in each reference cycle. The denser the distribution of the start point phase, the greater the possibility that the corresponding reference cycle is a candidate cycle.
[0038] The fifth step is to obtain the intersection of candidate cycles of different traffic lights to obtain candidate cycles of intersections.
[0039] The sixth step is to gradually expand the preset time period and recalculate the candidate cycle of the intersection until the candidate cycle of the intersection disappears, and determine the extended preset time period as the time period with unchanged total cycle. For example, the preset time period is extended by 10 minutes each time so that each traffic light in the intersection adds the target trajectory characteristics for a period of time, and recalculates the candidate cycle of the intersection. When the candidate cycle of the intersection changes from existing to non-existent, it means that the total cycle of the traffic lights at the intersection has changed. At this time, the extended preset time period is the time period with unchanged total cycle. The moment when the candidate cycle of the intersection disappears is the time when the total cycle of the traffic lights changes.
[0040] Step 7: Based on the red-green conflict of each candidate cycle at each intersection, determine the total cycle of the traffic light. The red-green conflict can be used to characterize the degree of conflict between the parking interval and the passing interval. The lower the conflict degree, the higher the possibility that the corresponding candidate cycle of the intersection is the total cycle of the traffic light.
[0041] For the time period with a constant total cycle, the candidate phase segments of each traffic light in the intersection can be mined. For example, each starting point moment in the target trajectory feature of the traffic light within the time period with a constant total cycle is traversed. Taking the starting point moment modulo the total cycle of the traffic light, the starting point phase of the traffic light within the time period with a constant total cycle can be obtained. When the phase deviation between the two starting points is greater than the first preset deviation threshold, it can be considered that the phase has changed. Then restart the mining of the next candidate phase segment of the traffic light. After the traversal of the time period with a constant total cycle is completed, the possible candidate phase segments of the traffic light within the time period with a constant total cycle can be obtained.
[0042] It should be noted that in order to avoid the influence of abnormal starting point trajectories on the phase mining results, it can be assumed that a stable phase segment cannot be less than a preset duration (such as 20 minutes).
[0043] Step 103, aggregating the candidate phase segments of traffic lights to obtain candidate phase segments of intersections.
[0044] In this embodiment, the above-mentioned execution subject can aggregate the candidate phase segments of different traffic lights to obtain the candidate phase segments of the intersection.
[0045] Traverse each traffic light candidate phase segment from small to large, and calculate the score of each traffic light in the intersection according to the target trajectory characteristics constructed offline. Then calculate the average of the scores of all traffic lights to get the intersection score. As time goes by, when the intersection score begins to decrease, it can be considered that the phase has changed. Among them, the traffic light score mainly includes two parts, namely, the aggregation degree of the starting point trajectory in the candidate phase segment of the traffic light and the red-green conflict score. The aggregation degree of the starting point trajectory can be the density of the starting point phase distribution. The red-green conflict score can be used to characterize the degree of conflict between the parking interval and the passing interval.
[0046] Step 104 , determining the intersection phase segment based on the target trajectory characteristics within the candidate intersection phase segment.
[0047] In this embodiment, the execution subject may determine the intersection phase segment based on the target trajectory characteristics within the candidate phase segment of the intersection.
[0048] For each possible candidate intersection phase segment, the target trajectory features of all traffic lights within the candidate intersection phase segment are aggregated to calculate the final moment when the phase changes, and obtain a stable phase segment, i.e., the intersection phase segment. Traverse the starting point moments in the target trajectory features within the candidate intersection phase segments. Take the starting point moment modulo the total traffic light cycle to obtain the intersection starting point phase. When the phase deviation between the two previous and next intersection starting points is greater than the third preset deviation threshold, it can be considered that the intersection phase has changed. Then restart the next intersection phase segment mining. After the intersection candidate phase segments are traversed, the intersection phase segment can be obtained.
[0049] Step 105, determining the traffic light phase based on the target trajectory characteristics of the traffic light in the phase segment of the intersection.
[0050] In this embodiment, the execution entity may determine the phase of each traffic light based on the target trajectory characteristics of each traffic light within the phase segment of the intersection.
[0051] After obtaining a stable intersection phase segment, the phase of each traffic light can be mined. The starting point moment of the traffic light in the intersection phase segment is taken as the modulus of the total traffic light cycle, and the starting point phase of the traffic light in the intersection phase segment is obtained. The average value of the starting point phase of the traffic light in the intersection phase segment is calculated to obtain the traffic light phase.
[0052] At this time, the total cycle of the traffic light remains unchanged. Even if the phase changes due to the release order or the red-green cycle, stable and correct phase information can be mined to improve the accuracy of the algorithm. At the same time, the influence of abnormal trajectories on the final result is avoided, improving the robustness of the algorithm.
[0053] In some embodiments, based on the lane-level trajectory data, the lane-level traffic light phase can be determined; based on the lane-level traffic light phase, the mined traffic light phase can be verified to obtain the confidence of the mined traffic light phase. Among them, the lane-level trajectory data can be the trajectory data of the left-turn lane or the straight lane. Based on the lane-level trajectory data, other methods different from the traffic light phase mining method provided in the embodiment of the present disclosure can be used to determine the lane-level traffic light phase. Among them, other traffic light phase mining methods can be based on the total traffic light cycle, using a phase mining method of the trajectory data of a single lane. This method assumes that when the total traffic light cycle remains unchanged, the phase does not change. After the total traffic light cycle mining is completed, the time period with stable phase can be obtained. Then, based on the historical trajectory data in each phase stable time period, the traffic light phase is mined.
[0054] The disclosed embodiment provides a traffic light phase mining method, which aggregates the candidate phase mining results of different traffic lights in the intersection, uses the intersection trajectory to comprehensively judge the moment when the phase changes, and realizes the mining of the phase relationship of different traffic lights in the intersection in a precise and complete manner. It focuses on solving the scenario where the total cycle of the traffic light remains unchanged but the phase relationship changes, and enriches the description of the traffic light timing scheme.
[0055] Figure 2 A process 200 of another embodiment of a traffic light phase mining method according to the present disclosure is shown. The traffic light phase mining method comprises the following steps:
[0056] Step 201 : extracting a target trajectory feature set based on a historical trajectory dataset of vehicles passing through an intersection.
[0057] In this embodiment, the execution subject of the traffic light total cycle mining method can obtain a historical trajectory data set of vehicles passing through the intersection, and extract a target trajectory feature set based on the historical trajectory data set.
[0058] The execution subject of the traffic light phase mining method is usually a server. The server can be hardware or software. When the server is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or it can be implemented as a single server. When the server is software, it can be implemented as multiple software or software modules (for example, used to provide distributed services), or it can be implemented as a single software or software module. No specific limitation is made here.
[0059] An intersection may be an intersection of at least two roads, such as a crossroads, a T-shaped intersection, etc. An intersection may be provided with at least one traffic light. Vehicles passing through the intersection may travel according to the instructions of the corresponding traffic light. For example, at a crossroads, traffic lights may be provided on all four sides. A left-turn traffic light and a straight-ahead traffic light may be provided on each side. In some cases, a right-turn traffic light may also be provided at the same time.
[0060] The historical trajectory data set can contain a large amount of historical trajectory data of vehicles passing through the intersection. Usually, the traffic light timing scheme on the same day in different weeks is basically unchanged. Therefore, the historical trajectory data of the same day for multiple consecutive weeks can be obtained to generate a historical trajectory data set. Of course, if the traffic light configuration scheme is the same every day, the historical trajectory data of multiple consecutive days can also be obtained to generate a historical trajectory data set.
[0061] Based on the historical trajectory data set, the target trajectory feature set can be extracted. The target trajectory features may include but are not limited to: parking information, start information, and traffic light information. This can refine the description of the vehicle's parking, start, and traffic light status at the traffic light, and more finely realize the description of the traffic light status change.
[0062] In some embodiments, feature extraction is performed on each piece of historical trajectory data in the historical trajectory data set to obtain corresponding features of each historical trajectory. The historical trajectory features can be used as target trajectory features to generate a target trajectory feature set.
[0063] In some embodiments, in order to avoid the influence of abnormal trajectories on the results, feature extraction is first performed on the historical trajectory data set to obtain a historical trajectory feature set, and then the abnormal features in the historical trajectory feature set are filtered to obtain a target trajectory feature set. The abnormal features may include but are not limited to: parking information of multiple stops at traffic lights, parking information of a stop time less than a preset time threshold at a traffic light, parking information of a stop at a location where the distance from the traffic light is greater than a preset distance threshold, etc.
[0064] Step 202, the start point moment in the target trajectory feature of the traffic light within the time period of the total cycle unchanged is taken as the modulus of the total cycle of the traffic light to obtain the start point phase of the traffic light within the time period of the total cycle unchanged.
[0065] In this embodiment, the above-mentioned execution entity can take the start point moment of each traffic light in the target trajectory feature within the time period of the total cycle unchanged as the modulus of the total traffic light cycle to obtain the start point phase of each traffic light within the time period of the total cycle unchanged.
[0066] Based on the target trajectory feature set, the total cycle of the traffic light and the total cycle unchanged time period can be determined. The total cycle of the traffic light can be the time interval between the last time the red light switched to green and the current time the red light switched to green. The total cycle unchanged time period can be the time period when the total cycle of the traffic light remains unchanged.
[0067] The total cycle of traffic lights at different traffic lights at the same intersection is the same. The total cycle of traffic lights at different time periods on the same day may be different. For example, the total cycle of traffic lights during the morning peak (such as 7:00 to 9:00) and evening peak (such as 17:00 to 20:00) is usually different from the total cycle of traffic lights during the off-peak period (such as the time period other than the morning peak and evening peak). The total cycle of traffic lights during the morning peak and evening peak is usually longer than the total cycle of traffic lights during the off-peak period. Therefore, it is necessary to first determine the time period when the total cycle remains unchanged, and then mine the total cycle of traffic lights within this time period when the total cycle remains unchanged, so as to ensure the accuracy of the total cycle of traffic lights.
[0068] Traverse each starting point moment in the target trajectory feature of the traffic light within the time period when the total cycle remains unchanged. Take the starting point moment modulo the total cycle of the traffic light to obtain the starting point phase of the traffic light within the time period when the total cycle remains unchanged.
[0069] Step 203, calculating the phase difference between the two starting points before and after the traffic light in the total cycle unchanged time period.
[0070] In this embodiment, the execution entity may calculate the phase difference between the two starting points before and after each traffic light within the constant time period of the total cycle.
[0071] Step 204 , determining the moment when the difference is greater than the first preset deviation threshold as the traffic light phase change moment, and obtaining the traffic light candidate phase segment.
[0072] In this embodiment, the execution entity may determine the moment when the difference is greater than the first preset deviation threshold as the traffic light phase change moment, and obtain the candidate traffic light phase segment.
[0073] For example, when the phase deviation between the two starting points is greater than the first preset deviation threshold, it can be considered that the phase has changed. Then the next traffic light candidate phase segment mining is restarted. After the total cycle unchanged time period traversal is completed, the possible traffic light candidate phase segments within the total cycle unchanged time period can be obtained.
[0074] It should be noted that in order to avoid the influence of abnormal starting point trajectories on the phase mining results, it can be assumed that a stable phase segment cannot be less than a preset duration (such as 20 minutes).
[0075] Step 205, calculating the average value of the phase of the starting point of the traffic light in the candidate phase segment of the traffic light, and obtaining the phase of the traffic light in the candidate phase segment of the traffic light.
[0076] In this embodiment, the execution entity may calculate the average value of the starting point phase of each traffic light in the candidate traffic light phase segment to obtain the phase of each traffic light in the candidate traffic light phase segment.
[0077] Step 206, calculating the phase difference of the traffic light in the two preceding and succeeding traffic light candidate phase segments.
[0078] In this embodiment, the execution entity may calculate the phase difference of each traffic light in two preceding and succeeding traffic light candidate phase segments.
[0079] Step 207: merge the two preceding and succeeding traffic light candidate phase segments whose difference is less than a second preset deviation threshold into one traffic light candidate phase segment.
[0080] In this embodiment, the execution entity may merge two preceding and following traffic light candidate phase segments whose difference is less than a second preset deviation threshold into one traffic light candidate phase segment.
[0081] After mining a single traffic light candidate phase segment, the phase value of this phase segment can be obtained by averaging the phase of the starting point. For phase segments with small phase deviations before and after, they can be smoothed into a stable phase segment.
[0082] Step 208, traverse the candidate phase segments of the traffic light, and calculate the traffic light score based on the target trajectory characteristics of the traffic light in the candidate phase segments of the traffic light.
[0083] In this embodiment, the execution entity may traverse each traffic light candidate phase segment, and calculate the score of each traffic light based on the target trajectory feature of each traffic light in the traffic light candidate phase segment.
[0084] Traverse each traffic light candidate phase segment from small to large, and calculate the score of each traffic light in the intersection according to the target trajectory characteristics constructed offline. The traffic light score mainly includes two parts, namely, the aggregation degree of the starting point trajectory in the traffic light candidate phase segment and the red-green conflict score. The aggregation degree of the starting point trajectory can be the density of the starting point phase distribution. The red-green conflict score can be used to characterize the conflict degree between the parking interval and the passing interval.
[0085] In some embodiments, the traffic light score may be calculated by the following steps:
[0086] First, the start point moment of each traffic light in the target trajectory feature within the candidate phase segment of the traffic light is divided by the total period of the traffic light to obtain the aggregation degree of the start point trajectory. Specifically, the start point moment of the traffic light is divided by the total period of the traffic light to obtain the start point phase of the traffic light. The denser the start point phase distribution, the higher the aggregation degree of the start point trajectory.
[0087] Afterwards, the stopping interval and passing interval of each traffic light are calculated based on the target trajectory characteristics of each traffic light within the candidate phase segment of the traffic light.
[0088] The stopping time of the traffic light in the target trajectory feature within the candidate phase segment of the traffic light is taken as the modulus of the total cycle unchanged time period to obtain the stopping interval of the traffic light; the starting time of the traffic light in the candidate phase segment of the traffic light is taken as the modulus of the total cycle unchanged time period to obtain the passing interval of the traffic light. For example, if the vehicle stops in front of the traffic light, the light state of the traffic light is red at this time. From the target trajectory feature of the traffic light in the candidate phase segment of the traffic light, all the moments when the light state is red are obtained, and the modulus of the total cycle unchanged time period is obtained to obtain the phase segment of the red light interval. The phase segment of the red light interval is combined with the starting time information to obtain the stopping interval. If the vehicle passes the traffic light, the light state of the traffic light is green at this time. From the target trajectory feature of the traffic light in the candidate phase segment of the traffic light, all the moments when the light state is green are obtained, and the modulus of the total cycle unchanged time period is obtained to obtain the phase segment of the green light interval. The phase segment of the green light interval can be approximated as the passing interval.
[0089] Then, based on the parking interval and the passing interval of each traffic light, each red-green conflict score is calculated. The red-green conflict score can be used to characterize the degree of conflict between the parking interval and the passing interval. The lower the red-green conflict score, the less conflict there is between the parking interval and the passing interval.
[0090] Finally, the start-point trajectory aggregation degree and the red-green conflict score are weighted and summed to obtain the traffic light score.
[0091] Step 209, calculating the average of the traffic light scores to obtain the intersection score.
[0092] In this embodiment, the execution entity may calculate the average of different traffic light scores to obtain the intersection score.
[0093] Step 210: Determine the moment when the intersection score decreases with time as the intersection phase change moment, and obtain the candidate intersection phase segment.
[0094] In this embodiment, the execution subject may determine the moment when the intersection score decreases with time as the intersection phase change moment, and obtain the candidate phase segment of the intersection. When the intersection score starts to decrease with time, it can be considered that the phase has changed.
[0095] Step 211, the start point time in the target trajectory feature within the candidate phase segment of the intersection is modulo the total traffic light cycle to obtain the intersection start point phase.
[0096] In this embodiment, the execution subject may obtain the intersection starting point phase by taking the start point time in the target trajectory feature within the candidate phase segment of the intersection as a modulus of the total traffic light cycle.
[0097] Traverse the starting point time in the target trajectory feature within the candidate phase segment of the intersection. Take the starting point time modulo the total traffic light cycle to get the starting point phase of the intersection.
[0098] Step 212, calculating the phase difference between the two front and rear intersection starting points.
[0099] In this embodiment, the execution entity may calculate the phase difference between the start points of the two intersections.
[0100] Step 213: determine the moment when the phase difference between the two intersection start points is greater than a third preset deviation threshold as the intersection phase change moment, and obtain the intersection phase segment.
[0101] In this embodiment, the execution entity may determine the moment when the phase difference between the two preceding and following intersection starting points is greater than a third preset deviation threshold as the intersection phase change moment, and obtain the intersection phase segment.
[0102] When the phase deviation between the two intersection start points is greater than the third preset deviation threshold, it can be considered that the intersection phase has changed. Then the next intersection phase segment mining is restarted. After the intersection candidate phase segment traversal is completed, the intersection phase segment can be obtained.
[0103] Step 214, taking the start point moment in the target trajectory feature of the traffic light in the phase segment of the intersection as a modulus of the total period of the traffic light, to obtain the start point phase of the traffic light in the phase segment of the intersection.
[0104] In this embodiment, the execution entity may obtain the starting point phase of each traffic light in the intersection phase segment by taking the starting point moment of the target trajectory feature of each traffic light in the intersection phase segment modulo the total traffic light cycle.
[0105] Step 215, calculating the average value of the phase of the starting point of the traffic light in the phase segment of the intersection to obtain the phase of the traffic light.
[0106] In this embodiment, the execution entity may calculate the average value of the phases of the starting points of different traffic lights within the phase segment of the intersection to obtain the traffic light phase.
[0107] At this time, the total cycle of the traffic light remains unchanged. Even if the phase changes due to the release order or the red-green cycle, stable and correct phase information can be mined to improve the accuracy of the algorithm. At the same time, the influence of abnormal trajectories on the final result is avoided, improving the robustness of the algorithm.
[0108] To realize the countdown function of traffic lights, it is necessary to mine the traffic light timing scheme based on historical trajectory data, including but not limited to the total cycle of traffic lights, red light cycle, green light cycle and phase, etc. The mining of different information usually has a certain order. For example, after the total cycle of traffic lights is mined, the red and green cycles and phases of traffic lights in different directions can be mined based on the total cycle of traffic lights. After the phase mining is completed, the phase difference between the two traffic lights in the intersection can be applied to the traffic light countdown task to improve the accuracy and coverage of the traffic light countdown.
[0109] In some embodiments, the traffic light phase difference between the current traffic light and other traffic lights in the intersection is first calculated; then based on the traffic light phase difference, the trajectory data of the current traffic light and the trajectory data of other traffic lights are aggregated to obtain aggregated trajectory data; finally, based on the aggregated trajectory data, the first predicted countdown of the current traffic light is obtained. During the use of the traffic light countdown, for traffic lights with sparse trajectories in the intersection, the trajectories of other traffic lights in the intersection can be aggregated through phase difference information to enrich the trajectory of the current traffic light and assist in the calculation of countdown information.
[0110] In some embodiments, first, based on the trajectory data of the current traffic light, the second predicted countdown of the traffic light is obtained; then, the first predicted countdown of the traffic light is verified with the second predicted countdown. For traffic lights with rich trajectories, countdown information can be obtained using their own trajectories. Similarly, countdown information can also be obtained by aggregating the trajectories of other traffic lights in the intersection through phase difference information. Mutual verification of the countdown calculation results of the two can improve the accuracy of countdown and phase mining.
[0111] The disclosed embodiment provides a traffic light phase mining method, which aggregates the candidate phase mining results of different traffic lights in an intersection, uses the intersection trajectory to comprehensively judge the moment when the phase changes, and realizes the mining of the phase relationship of different traffic lights in the intersection in a precise and complete manner. It focuses on solving the scenario where the total cycle of the traffic lights remains unchanged but the phase relationship changes, and enriches the characterization of the traffic light timing scheme. The phase difference between each pair of traffic lights in the intersection is applied to the traffic light countdown task, which improves the accuracy and coverage of the traffic light countdown. For traffic lights with sparse trajectories, the number of traffic lights calculated for countdown increases significantly. For scenarios where the total cycle of traffic lights remains unchanged but the phase changes, the accuracy is significantly improved. The situation where users see incorrect light states or large deviations in countdown results is greatly reduced, which improves the user experience and alleviates the anxiety of users when waiting for the bus.
[0112] Figure 3 A process 300 of an embodiment of a vehicle navigation method according to the present disclosure is shown. The vehicle navigation method comprises the following steps:
[0113] Step 301, obtaining the current position and current time of a vehicle that is about to pass the traffic light.
[0114] In this embodiment, the execution subject of the vehicle navigation method can obtain the current position and current time of the vehicle that is about to pass the traffic light.
[0115] The execution subject of the vehicle navigation method is usually a server. The server can be hardware or software. When the server is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or it can be implemented as a single server. When the server is software, it can be implemented as multiple software or software modules (for example, used to provide distributed services), or it can be implemented as a single software or software module. No specific limitation is made here.
[0116] Usually, the vehicle can travel along the route planned by the navigation. The route usually includes traffic lights corresponding to lanes (such as left-turn lanes and straight lanes). The current position of the vehicle is collected in real time, and the distance between the vehicle and the traffic light is calculated. When the distance between the vehicle and the traffic light is less than the preset distance threshold, it can be determined that the vehicle is about to pass the traffic light. At this time, the current time can be further obtained to assist in predicting the countdown of the traffic light.
[0117] Step 302, predicting the countdown of the traffic light based on the current position, the current time, the total cycle of the traffic light and the phase of the traffic light.
[0118] In this embodiment, the execution subject can predict the countdown of the traffic light based on the current position, the current time, the total cycle of the traffic light and the phase of the traffic light.
[0119] Usually, the traffic light timing scheme on the same day of different weeks remains basically unchanged. Therefore, the traffic light countdown information on the same day of this week can be predicted by the total traffic light cycle and traffic light phase of a certain day last week. The traffic light countdown information can be calculated by combining the total traffic light cycle and traffic light phase, as well as the current position and current time of the vehicle.
[0120] It should be noted that the traffic light phase is based on Figure 1 or Figure 2 The described embodiments are obtained by mining and will not be repeated here.
[0121] Further references Figure 4 As an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a traffic light phase mining device. Figure 1Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.
[0122] like Figure 4 As shown, the traffic light phase mining device 400 of this embodiment may include: an extraction module 401, a first determination module 402, an aggregation module 403, a second determination module 404 and a third determination module 405. The extraction module 401 is configured to extract a target trajectory feature set based on a historical trajectory data set of vehicles passing through an intersection; the first determination module 402 is configured to determine a candidate phase segment of a traffic light based on the target trajectory feature of a traffic light within a constant period of a total cycle; the aggregation module 403 is configured to aggregate the candidate phase segments of a traffic light to obtain a candidate phase segment of an intersection; the second determination module 404 is configured to determine an intersection phase segment based on the target trajectory feature within the candidate phase segment of the intersection; and the third determination module 405 is configured to determine the traffic light phase based on the target trajectory feature of the traffic light within the phase segment of the intersection.
[0123] In this embodiment, in the traffic light phase mining device 400, the specific processing of the extraction module 401, the first determination module 402, the aggregation module 403, the second determination module 404 and the third determination module 405 and the technical effects thereof can be referred to respectively. Figure 1 The relevant descriptions of steps 101-105 in the corresponding embodiment are not repeated here.
[0124] In some optional implementations of this embodiment, the extraction module 401 is further configured to: perform feature extraction on the historical trajectory data set to obtain a historical trajectory feature set; filter abnormal features in the historical trajectory feature set to obtain a target trajectory feature set, wherein the abnormal features include at least one of the following: parking information of multiple stops at traffic lights, parking information of a stop time at a traffic light that is less than a preset time threshold, and parking information of a stop at a position where the distance from the traffic light is greater than a preset distance threshold.
[0125] In some optional implementations of the present embodiment, the first determination module 402 is further configured to: take the starting point moment in the target trajectory feature of the traffic light within the total cycle unchanged time period modulo the total traffic light cycle, and obtain the starting point phase of the traffic light within the total cycle unchanged time period; calculate the difference between the two starting point phases before and after the traffic light within the total cycle unchanged time period; determine the moment when the difference is greater than the first preset deviation threshold as the traffic light phase change moment, and obtain the candidate phase segment of the traffic light.
[0126] In some optional implementations of the present embodiment, the traffic light phase mining device 400 also includes a merging module, which is configured to: calculate the average value of the starting point phase of the traffic light in the traffic light candidate phase segment to obtain the phase of the traffic light in the traffic light candidate phase segment; calculate the difference in the phase of the traffic light in the two front and rear traffic light candidate phase segments; merge the two front and rear traffic light candidate phase segments whose difference is less than a second preset deviation threshold into one traffic light candidate phase segment.
[0127] In some optional implementations of the present embodiment, the aggregation module 403 includes: a first calculation submodule, configured to traverse the candidate phase segments of the traffic light, and calculate the traffic light score based on the target trajectory characteristics of the traffic light within the candidate phase segments of the traffic light; a second calculation submodule, configured to calculate the average of the traffic light scores to obtain the intersection score; a determination submodule, configured to determine the moment when the intersection score decreases with time as the intersection phase change moment, and obtain the candidate phase segment of the intersection.
[0128] In some optional implementations of the present embodiment, the first calculation submodule is further configured to: take the starting point moment in the target trajectory feature of the traffic light within the candidate phase segment of the traffic light modulus by the total period of the traffic light to obtain the degree of aggregation of the starting point trajectory; calculate the parking interval and the passing interval of the traffic light based on the target trajectory feature of the traffic light within the candidate phase segment of the traffic light; calculate the red-green conflict score based on the parking interval and the passing interval; and take a weighted sum of the starting point trajectory aggregation degree and the red-green conflict score to obtain the traffic light score.
[0129] In some optional implementations of the present embodiment, the second determination module 404 is further configured to: take the starting point moment in the target trajectory feature within the candidate phase segment of the intersection modulo the total traffic light cycle to obtain the intersection starting point phase; calculate the difference in phase between the two front and rear intersection starting points; determine the moment when the difference in phase between the two front and rear intersection starting points is greater than a third preset deviation threshold as the intersection phase change moment to obtain the intersection phase segment.
[0130] In some optional implementations of the present embodiment, the third determination module 405 is further configured to: take the starting point moment in the target trajectory feature of the traffic light within the intersection phase segment modulo the total traffic light cycle to obtain the starting point phase of the traffic light within the intersection phase segment; calculate the average value of the starting point phase of the traffic light within the intersection phase segment to obtain the traffic light phase.
[0131] In some optional implementations of the present embodiment, the traffic light phase mining device 400 also includes a prediction module, which is configured to: calculate the traffic light phase difference between the current traffic light and other traffic lights in the intersection; based on the traffic light phase difference, aggregate the trajectory data of the current traffic light and the trajectory data of other traffic lights to obtain aggregated trajectory data; based on the aggregated trajectory data, obtain the first predicted countdown of the traffic light.
[0132] In some optional implementations of this embodiment, the traffic light phase mining device 400 also includes a verification module, which is configured to: obtain a second predicted countdown of the current traffic light based on the trajectory data of the current traffic light; and verify the first predicted countdown and the second predicted countdown of the current traffic light.
[0133] In some optional implementations of this embodiment, the traffic light phase mining device 400 also includes: a fourth determination module, configured to determine the lane-level traffic light phase based on the lane-level trajectory data; a verification module, configured to verify the mined traffic light phase based on the lane-level traffic light phase to obtain the confidence of the mined traffic light phase.
[0134] Further references Figure 5 As an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a vehicle navigation device, and the device embodiment is Figure 3 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.
[0135] like Figure 5 As shown, the vehicle navigation device 500 of this embodiment may include: an acquisition module 501 and a prediction module 502. The acquisition module 501 is configured to acquire the current position and current time of the vehicle that is about to pass the traffic light; the prediction module 502 is configured to predict the countdown of the traffic light based on the current position, current time, the total cycle of the traffic light and the phase of the traffic light, wherein the phase of the traffic light is calculated using Figure 4 The device described was excavated.
[0136] In the present embodiment, in the vehicle navigation device 500, the specific processing of the acquisition module 501 and the prediction module 502 and the technical effects thereof can be referred to in Figure 3 The relevant descriptions of steps 301-302 in the corresponding embodiment are not repeated here. In the technical solution of the present disclosure, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good customs.
[0137] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.
[0138] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.
[0139] like Figure 6 As shown, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.
[0140] A number of components in the device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0141] The computing unit 601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 601 performs the various methods and processes described above, such as the traffic light phase mining method. For example, in some embodiments, the traffic light phase mining method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the traffic light phase mining method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the traffic light phase mining method in any other appropriate manner (e.g., by means of firmware).
[0142] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0143] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.
[0144] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0145] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).
[0146] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.
[0147] A computer system may include a client and a server. The client and the server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises through computer programs running on respective computers and having a client-server relationship to each other. The server may be a cloud server, a server in a distributed system, or a server combined with a blockchain.
[0148] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions provided by this disclosure can be achieved, and this document does not limit this.
[0149] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.
Claims
1. A traffic light phase mining method, comprising: Based on the historical trajectory dataset of vehicles passing through the intersection, a target trajectory feature set is extracted; Determining candidate phase segments of the traffic light based on target trajectory characteristics of the traffic light within a constant total cycle time period; Aggregating the traffic light candidate phase segments to obtain intersection candidate phase segments; Determining an intersection phase segment based on target trajectory characteristics within the candidate intersection phase segment; The traffic light phase is determined based on the target trajectory characteristics of the traffic light in the phase segment of the intersection.
2. The method according to claim 1, wherein: The target trajectory feature set is extracted based on the historical trajectory data set of vehicles passing through the intersection, including: Performing feature extraction on the historical trajectory data set to obtain a historical trajectory feature set; The abnormal features in the historical trajectory feature set are filtered to obtain the target trajectory feature set, wherein the abnormal features include at least one of the following: parking information of multiple stops at traffic lights, parking information of a parking time at a traffic light that is less than a preset time threshold, and parking information of a parking position at a distance from the traffic light that is greater than a preset distance threshold.
3. The method according to claim 1, wherein: The step of determining the candidate phase segments of the traffic light based on the target trajectory characteristics of the traffic light within the constant total cycle time period includes: Taking the start point moment of the target trajectory feature of the traffic light within the time period of the total cycle unchanged as the modulus of the total cycle of the traffic light, the start point phase of the traffic light within the time period of the total cycle unchanged is obtained; Calculating the phase difference between the two starting points before and after the traffic light within the total cycle unchanged time period; The moment when the difference is greater than the first preset deviation threshold is determined as the traffic light phase change moment, and the traffic light candidate phase segment is obtained.
4. The method according to claim 3, wherein: The method further comprises: Calculating an average value of the start-up point phases of the traffic light within the candidate traffic light phase segment to obtain the phase of the traffic light within the candidate traffic light phase segment; Calculating the phase difference of the traffic light in two candidate phase segments of the preceding and following traffic lights; The two preceding and following traffic light candidate phase segments whose difference is less than a second preset deviation threshold are merged into one traffic light candidate phase segment.
5. The method according to claim 1, wherein: The aggregating the traffic light candidate phase segments to obtain the intersection candidate phase segments includes: Traversing the candidate traffic light phase segments, and calculating a traffic light score based on target trajectory features of the traffic light within the candidate traffic light phase segments; Calculate the average of the traffic light scores to obtain an intersection score; The moment when the intersection score decreases with time is determined as the intersection phase change moment, and the candidate phase segment of the intersection is obtained.
6. The method according to claim 5, wherein: The calculating the traffic light score based on the target trajectory feature of the traffic light in the candidate traffic light phase segment includes: The start point moment in the target trajectory feature of the traffic light in the candidate phase segment of the traffic light is modulo the total period of the traffic light to obtain the start point trajectory aggregation degree; Calculating a stop interval and a pass interval of the traffic light based on a target trajectory feature of the traffic light within the candidate phase segment of the traffic light; Calculating a red-green conflict score based on the parking interval and the passing interval; The traffic light score is obtained by weighted summing the start point trajectory aggregation degree and the red-green conflict score.
7. The method according to claim 1, wherein: The determining of the intersection phase segment based on the target trajectory feature in the candidate intersection phase segment includes: The starting point time in the target trajectory feature within the candidate phase segment of the intersection is modulo the total traffic light cycle to obtain the starting point phase of the intersection; Calculate the phase difference between the starting points of the two intersections; The moment when the phase difference between the two front and rear intersection starting points is greater than a third preset deviation threshold is determined as the intersection phase change moment to obtain the intersection phase segment.
8. The method according to claim 1, wherein: The determining the traffic light phase based on the target trajectory feature of the traffic light in the phase segment of the intersection includes: The starting point moment of the target trajectory feature of the traffic light in the phase segment of the intersection is modulo the total period of the traffic light to obtain the starting point phase of the traffic light in the phase segment of the intersection; The average value of the starting point phase of the traffic light in the phase segment of the intersection is calculated to obtain the traffic light phase.
9. The method according to claim 1, wherein: The method further comprises: Calculating the traffic light phase difference between the current traffic light and other traffic lights in the intersection; Based on the traffic light phase difference, aggregating the trajectory data of the current traffic light and the trajectory data of the other traffic lights to obtain aggregated trajectory data; Based on the aggregated trajectory data, a first predicted countdown of the current traffic light is obtained.
10. The method according to claim 9, wherein: The method further comprises: Based on the trajectory data of the current traffic light, obtaining a second predicted countdown of the current traffic light; A verification is performed based on the first predicted countdown and the second predicted countdown of the current traffic light.
11. The method according to any one of claims 1 to 10, wherein: The method further comprises: Determining a lane-level traffic light phase based on the lane-level trajectory data; Based on the lane-level traffic light phase, the mined traffic light phase is verified to obtain the confidence of the mined traffic light phase.
12. A vehicle navigation method, comprising: Get the current position and time of the vehicle that is about to pass the traffic light; Based on the current position, the current time, the total cycle of the traffic light and the phase of the traffic light, the countdown of the traffic light is predicted, wherein the phase of the traffic light is mined using the method described in any one of claims 1-11.
13. A traffic light phase mining device, comprising: an extraction module configured to extract a target trajectory feature set based on a historical trajectory dataset of vehicles passing through the intersection; A first determination module is configured to determine a candidate phase segment of the traffic light based on the target trajectory characteristics of the traffic light within a constant total cycle time period; an aggregation module, configured to aggregate the traffic light candidate phase segments to obtain intersection candidate phase segments; A second determination module is configured to determine the intersection phase segment based on the target trajectory characteristics within the candidate phase segment of the intersection; The third determination module is configured to determine the traffic light phase based on the target trajectory characteristics of the traffic light in the phase segment of the intersection.
14. The device according to claim 13, wherein: The extraction module is further configured to: Performing feature extraction on the historical trajectory data set to obtain a historical trajectory feature set; The abnormal features in the historical trajectory feature set are filtered to obtain the target trajectory feature set, wherein the abnormal features include at least one of the following: parking information of multiple stops at traffic lights, parking information of a parking time at a traffic light that is less than a preset time threshold, and parking information of a parking position at a distance from the traffic light that is greater than a preset distance threshold.
15. The device according to claim 13, wherein: The first determining module is further configured to: Taking the start point moment of the target trajectory feature of the traffic light within the time period of the total cycle unchanged as the modulus of the total cycle of the traffic light, the start point phase of the traffic light within the time period of the total cycle unchanged is obtained; Calculating the phase difference between the two starting points before and after the traffic light within the total cycle unchanged time period; The moment when the difference is greater than the first preset deviation threshold is determined as the traffic light phase change moment, and the traffic light candidate phase segment is obtained.
16. The device according to claim 15, wherein: The apparatus further comprises a merging module configured to: Calculating an average value of the start-up point phases of the traffic light within the candidate traffic light phase segment to obtain the phase of the traffic light within the candidate traffic light phase segment; Calculating the phase difference of the traffic light in two candidate phase segments of the preceding and following traffic lights; The two preceding and following traffic light candidate phase segments whose difference is less than a second preset deviation threshold are merged into one traffic light candidate phase segment.
17. The device according to claim 13, wherein: The aggregation module includes: A first calculation submodule is configured to traverse the traffic light candidate phase segment and calculate a traffic light score based on a target trajectory feature of the traffic light in the traffic light candidate phase segment; A second calculation submodule is configured to calculate an average value of the traffic light scores to obtain an intersection score; The determination submodule is configured to determine the moment when the intersection score decreases with time as the intersection phase change moment, and obtain the candidate phase segment of the intersection.
18. The device according to claim 17, wherein: The first calculation submodule is further configured to: The start point moment in the target trajectory feature of the traffic light in the candidate phase segment of the traffic light is modulo the total period of the traffic light to obtain the start point trajectory aggregation degree; Calculating a stop interval and a pass interval of the traffic light based on a target trajectory feature of the traffic light within the candidate phase segment of the traffic light; Calculating a red-green conflict score based on the parking interval and the passing interval; The traffic light score is obtained by weighted summing the start point trajectory aggregation degree and the red-green conflict score.
19. The device according to claim 13, wherein: The second determining module is further configured to: The starting point time in the target trajectory feature within the candidate phase segment of the intersection is modulo the total traffic light cycle to obtain the starting point phase of the intersection; Calculate the phase difference between the starting points of the two intersections; The moment when the phase difference between the two front and rear intersection starting points is greater than a third preset deviation threshold is determined as the intersection phase change moment to obtain the intersection phase segment.
20. The device according to claim 13, wherein: The third determination module is further configured to: The starting point moment of the target trajectory feature of the traffic light in the phase segment of the intersection is modulo the total period of the traffic light to obtain the starting point phase of the traffic light in the phase segment of the intersection; The average value of the starting point phase of the traffic light in the phase segment of the intersection is calculated to obtain the traffic light phase.
21. The device according to claim 13, wherein: The apparatus further comprises a prediction module configured to: Calculating the traffic light phase difference between the current traffic light and other traffic lights in the intersection; Based on the traffic light phase difference, aggregating the trajectory data of the current traffic light and the trajectory data of the other traffic lights to obtain aggregated trajectory data; Based on the aggregated trajectory data, a first predicted countdown of the current traffic light is obtained.
22. The method according to claim 21, wherein: The device also includes a verification module configured to: Based on the trajectory data of the current traffic light, obtaining a second predicted countdown of the current traffic light; A verification is performed based on the first predicted countdown and the second predicted countdown of the current traffic light.
23. The device according to any one of claims 13 to 22, wherein: The device also includes: a fourth determination module, configured to determine a lane-level traffic light phase based on the lane-level trajectory data; The verification module is configured to verify the mined traffic light phase based on the lane-level traffic light phase to obtain the confidence of the mined traffic light phase.
24. A vehicle navigation device, comprising: An acquisition module is configured to acquire a current position and a current time of a vehicle that is about to pass a traffic light; A prediction module is configured to predict the countdown of the traffic light based on the current position, the current time, the total traffic light cycle and the traffic light phase, wherein the traffic light phase is mined using the device described in any one of claims 13-23.
25. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 12.
26. A non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the method of any one of claims 1-12.
27. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 12.
Citation Information
Cited By
Traffic data processing method and device, electronic equipment and medium
CN122067419A
