Traffic light cycle evaluation method, device, equipment and storage medium
By constructing the frequency distribution and KS test score within the traffic light cycle, the traffic light cycle is automatically evaluated, solving the problems of small coverage and long update cycle of manual intervention in the existing technology, and realizing the accuracy and dynamic adjustment support of the traffic light cycle.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- BEIJING SIWEI TUXIN TECHNOLOGY CO LTD
- Filing Date
- 2025-12-01
- Publication Date
- 2026-04-24
AI Technical Summary
Existing methods for evaluating traffic light cycles rely on manual intervention, have limited coverage, cannot adapt to the dynamic adjustment needs of urban traffic, and have long update cycles, failing to meet the real-time and accuracy requirements of intelligent transportation.
By acquiring the timestamps of stops at traffic lights and crossing road stop lines within a traffic light cycle, a frequency distribution is constructed. Using the KS test, the operational effectiveness of the traffic light cycle is automatically evaluated, and a target score is provided.
It improves the accuracy of traffic light cycle evaluation, objectively reflects the coordination efficiency of vehicle waiting and passage, provides scoring support for subsequent adjustments, and supports dynamic traffic optimization.
Smart Images
Figure CN121921988A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of electronic map technology, and in particular to a method, apparatus, device, and storage medium for evaluating traffic light cycles. Background Technology
[0002] In modern urban transportation systems, the rationality and accuracy of traffic light cycles directly affect traffic efficiency, traffic safety, and travel experience. With the rapid development of intelligent transportation technologies, applications such as in-vehicle navigation and dynamic traffic services (such as traffic light countdowns) are placing higher demands on the real-time performance and accuracy of traffic light cycles.
[0003] Currently, the main methods for monitoring and evaluating traffic light cycles are verification through manual annotation or by using the true values of traffic lights provided by local traffic management bureaus.
[0004] However, the above methods rely on manual intervention, can only cover a limited area, and have a long update cycle, making them unable to adapt to the needs of dynamic adjustments in urban traffic. Summary of the Invention
[0005] This application provides a method, apparatus, device, and storage medium for evaluating traffic light cycles, in order to improve the efficiency of dynamic adjustment of urban traffic needs.
[0006] In a first aspect, embodiments of this application provide a method for evaluating traffic light cycles, including:
[0007] Obtain the data collection windows corresponding to different traffic light cycles at the intersection to be evaluated;
[0008] For each collection window, obtain the set of timestamps for the time spent waiting at traffic lights and the set of timestamps for the time spent crossing the road stop line within the collection window during the period to be evaluated;
[0009] Based on the set of timestamps for stopping at traffic lights and the set of timestamps for crossing road stop lines, determine the first frequency distribution of timestamps for stopping at traffic lights and the second frequency distribution of timestamps for crossing road stop lines;
[0010] Based on the first frequency distribution and the second frequency distribution, the target score for the traffic light cycle corresponding to the acquisition window is determined.
[0011] In one or more embodiments, determining a first frequency distribution of waiting times at traffic lights and a second frequency distribution of crossing stop lines based on the set of timestamps for waiting times at traffic lights and the set of timestamps for crossing stop lines includes:
[0012] The multiple stop-at-the-light timestamps in the set of stop-at-the-light timestamps are normalized within the traffic light cycle to generate the first frequency distribution;
[0013] The timestamps of multiple road stop line timestamps in the set of road stop line timestamps are normalized within the traffic light cycle to generate the second frequency distribution.
[0014] In one or more embodiments, determining the target score for the traffic light cycle corresponding to the acquisition window based on the first frequency distribution and the second frequency distribution includes:
[0015] Determine the first score of the first frequency distribution under the KS test;
[0016] Determine the second score of the second frequency distribution under the KS test;
[0017] Based on the first score and the second score, the target score for the traffic light cycle corresponding to the acquisition window is determined.
[0018] In one or more embodiments, the method further includes:
[0019] If the target score is greater than the first preset score, then the evaluation corresponding to the traffic light cycle of the collection window is determined to be positive.
[0020] If the target score is less than or equal to the first preset score, then the evaluation corresponding to the traffic light cycle of the collection window is determined to be negative.
[0021] In one or more embodiments, obtaining the set of timestamps for stopping at traffic lights and the set of timestamps for crossing road stop lines within the collection window during the evaluation period includes:
[0022] Obtain the floating car trajectory data in the collection window during the time period to be evaluated;
[0023] Based on the floating car trajectory data, determine the set of timestamps for the time when the car stops at the traffic light and the set of timestamps for the time when the car crosses the road stop line.
[0024] In one or more embodiments, determining the set of timestamps for the time spent waiting at traffic lights and the set of timestamps for the time spent crossing road stop lines based on the floating car trajectory data includes:
[0025] Multiple timestamps for stopping at traffic lights and multiple timestamps for crossing road stop lines were extracted from the floating car trajectory data.
[0026] Based on the first-time compensation data, the timestamps of the multiple stops waiting at the lights are compensated to obtain the set of timestamps of the stops waiting at the lights;
[0027] Based on the second time compensation data, the timestamps of the multiple timestamps for crossing the road stop line are compensated to obtain the set of timestamps for crossing the road stop line.
[0028] In one or more embodiments, the method further includes:
[0029] Determine the target score corresponding to each collection window, and determine the overall score for all traffic light cycles in the intersection to be evaluated;
[0030] The identifier of the intersection to be evaluated and the overall score are stored in the database.
[0031] Secondly, embodiments of this application provide a traffic light cycle evaluation device, comprising:
[0032] The first acquisition module is used to acquire the collection windows corresponding to different traffic light cycles at the intersection to be evaluated.
[0033] The second acquisition module is used to acquire, for each acquisition window, the set of timestamps of the time spent waiting at traffic lights and the set of timestamps of the time spent crossing the road stop line in the acquisition window within the time period to be evaluated;
[0034] The first determining module is used to determine a first frequency distribution of the time spent waiting at the traffic lights and a second frequency distribution of the time spent crossing the road stop line based on the set of timestamps of the ...
[0035] The second determining module is used to determine the target score of the traffic light cycle corresponding to the acquisition window based on the first frequency distribution and the second frequency distribution.
[0036] In one or more embodiments, the first determining module is specifically used for:
[0037] The multiple stop-at-the-light timestamps in the set of stop-at-the-light timestamps are normalized within the traffic light cycle to generate the first frequency distribution;
[0038] The timestamps of multiple road stop line timestamps in the set of road stop line timestamps are normalized within the traffic light cycle to generate the second frequency distribution.
[0039] In one or more embodiments, the second determining module is specifically used for:
[0040] Determine the first score of the first frequency distribution under the KS test;
[0041] Determine the second score of the second frequency distribution under the KS test;
[0042] Based on the first score and the second score, the target score for the traffic light cycle corresponding to the acquisition window is determined.
[0043] In one or more embodiments, the first determining module is further configured to:
[0044] If the target score is greater than the first preset score, then the evaluation corresponding to the traffic light cycle of the collection window is determined to be positive.
[0045] If the target score is less than or equal to the first preset score, then the evaluation corresponding to the traffic light cycle of the collection window is determined to be negative.
[0046] In one or more embodiments, the second acquisition module acquires a set of timestamps for stopping at traffic lights and a set of timestamps for crossing road stop lines within the acquisition window during the evaluation period, specifically for:
[0047] Obtain the floating car trajectory data in the collection window during the time period to be evaluated;
[0048] Based on the floating car trajectory data, determine the set of timestamps for the time when the car stops at the traffic light and the set of timestamps for the time when the car crosses the road stop line.
[0049] In one or more embodiments, the second acquisition module, based on the floating car trajectory data, determines the set of timestamps for stopping at traffic lights and the set of timestamps for crossing road stop lines, specifically for:
[0050] Multiple timestamps for stopping at traffic lights and multiple timestamps for crossing road stop lines were extracted from the floating car trajectory data.
[0051] Based on the first-time compensation data, the timestamps of the multiple stops waiting at the lights are compensated to obtain the set of timestamps of the stops waiting at the lights;
[0052] Based on the second time compensation data, the timestamps of the multiple timestamps for crossing the road stop line are compensated to obtain the set of timestamps for crossing the road stop line.
[0053] In one or more embodiments, the second determining module is further configured to:
[0054] Determine the target score corresponding to each collection window, and determine the overall score for all traffic light cycles in the intersection to be evaluated;
[0055] The identifier of the intersection to be evaluated and the overall score are stored in the database.
[0056] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;
[0057] The memory stores computer-executed instructions;
[0058] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.
[0059] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.
[0060] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.
[0061] The traffic light cycle evaluation method, apparatus, device, and storage medium provided in this application obtain collection windows corresponding to different traffic light cycles at the intersection to be evaluated. For each collection window, the set of timestamps for waiting at the light and crossing the stop line are obtained within the collection window during the evaluation period. Based on the sets of timestamps for waiting at the light and crossing the stop line, a first frequency distribution of waiting at the light and a second frequency distribution of crossing the stop line are determined. Based on the first and second frequency distributions, the target score for the traffic light cycle corresponding to the collection window is determined. This scheme first uses collection windows to accurately divide the traffic light cycle and extracts the timestamp sets for waiting at the light and crossing the stop line, respectively, and then constructs the first and second frequency distributions, thereby transforming complex traffic behavior data into a quantifiable distribution model. Based on this, by comparing and analyzing the matching degree of the two distributions (such as overlap area or difference measure), the coordination efficiency of vehicle waiting and passage within the traffic light cycle can be objectively reflected, ultimately achieving the target score for the operational effect of each cycle, effectively improving the accuracy of traffic light cycle evaluation and providing a scoring support basis for subsequent traffic light cycle adjustments. Attached Figure Description
[0062] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.
[0063] Figure 1 A flowchart illustrating the traffic light cycle evaluation method provided in this application embodiment. Figure 1 ;
[0064] Figure 2 This is an illustration of traffic light cycle data provided in the embodiments of this application.
[0065] Figure 3 A flowchart illustrating the traffic light cycle evaluation method provided in this application embodiment. Figure 2 ;
[0066] Figure 4 This is a first example of a first frequency distribution map and a second frequency distribution map provided in the embodiments of this application;
[0067] Figure 5 This is a second example of the first frequency distribution map and the second frequency distribution map provided in the embodiments of this application;
[0068] Figure 6 A flowchart illustrating the traffic light cycle evaluation method provided in this application embodiment. Figure 3 ;
[0069] Figure 7 This is a schematic diagram of the traffic light cycle evaluation device provided in the embodiments of this application;
[0070] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.
[0071] The accompanying drawings have illustrated specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to specific embodiments. Detailed Implementation
[0072] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.
[0073] In modern urban transportation systems, the rationality and accuracy of traffic light cycles directly affect traffic efficiency, traffic safety, and travel experience. With the rapid development of intelligent transportation technologies, applications such as in-vehicle navigation and dynamic traffic services (such as traffic light countdowns) are placing higher demands on the real-time performance and accuracy of traffic light cycles.
[0074] In existing technologies, methods for evaluating traffic light cycles are mainly divided into two categories:
[0075] The first category is based on traditional monitoring and evaluation methods, which involves obtaining the true values of traffic lights from local traffic management bureaus and conducting evaluations.
[0076] The second category is perception-based evaluation methods, which obtain the true value of traffic lights through visual means and then conduct evaluations.
[0077] However, the existing technologies described above have the following technical problems:
[0078] 1) The supervision and evaluation method requires obtaining the true values of traffic lights from local traffic management bureaus, which can only cover local areas in the real world, resulting in a small evaluation scope.
[0079] 2) Perception-based evaluation methods are limited by the accuracy and positioning accuracy of visual traffic light perception methods, as well as by the coverage limitations of perception collection vehicles.
[0080] To address the technical problems existing in the prior art, the inventors of this application propose the following concept: Within a single traffic light cycle, there is a specific correspondence between the time distribution of a vehicle's stopping at the light and its crossing of the stop line. A well-designed cycle should exhibit the characteristic of vehicles quickly and centrally crossing the stop line after the green light turns on. Therefore, by defining a data collection window for each cycle and separately statistically analyzing the frequency distribution of stopping time (reflecting queue formation) and crossing time (reflecting traffic release), the abstract problem of signal timing efficiency can be transformed into a matching degree analysis problem of two specific distributions. Based on these two frequency distributions, the traffic light score for that cycle, i.e., the quality of its operation, can be determined.
[0081] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.
[0082] Figure 1 A flowchart illustrating the traffic light cycle evaluation method provided in this application embodiment. Figure 1 ,like Figure 1 As shown, the method includes:
[0083] Step 11: Obtain the collection windows corresponding to different traffic light cycles at the intersection to be evaluated;
[0084] In this step, at a traffic light intersection, there are generally multiple different traffic light cycles throughout the day, and each traffic light cycle is used as the corresponding data collection window.
[0085] Optional, Figure 2 The traffic light cycle data provided in the embodiments of this application is intended to illustrate the following: Figure 2 As shown in the diagram, the traffic light cycles include: 91s cycle duration, 76s cycle duration, and 86s cycle duration.
[0086] The acquisition window corresponding to the 91s cycle duration is 06.00-10.00; the acquisition window corresponding to the 86s cycle duration is 16.00-20.00; the acquisition window corresponding to the 76s cycle duration is 00.00-06.00; 10.00-16.00; and 20.00-00.00.
[0087] In this example, the period to be evaluated is a duration, which can be 30 days, 1 day, etc.
[0088] Throughout the day, from 00:00 to 24:00, each time slice (i.e. Figure 2 If the sampling point is 15 minutes, then it includes 96 time slices.
[0089] Furthermore, the first The data from the first traffic light cycle can indicate the... One collection window .
[0090] in, Representing the The start time of each acquisition window Representing the The end time of each data collection window. Representing the One acquisition window cycle.
[0091] Step 12: For each collection window, obtain the set of timestamps for the time spent waiting at traffic lights and the set of timestamps for the time spent crossing the road stop line within the collection window during the period to be evaluated;
[0092] In this step, within each independent traffic light cycle (i.e., the acquisition window) defined in the previous step, the original trajectory data within the acquisition window, i.e. the floating car trajectory data, is processed. By identifying the behavior of vehicles suddenly slowing down and stopping in front of the stop line for a long time, the stopping time of all vehicles is extracted to form a timestamp set, which is recorded as the stopping time timestamp set.
[0093] Meanwhile, by identifying the behavior of vehicles starting from a stationary state and crossing the stop line, the times when all vehicles cross the road stop line are extracted to form another set of timestamps, which is recorded as the set of timestamps for crossing the road stop line.
[0094] Step 13: Based on the set of timestamps for stopping at traffic lights and the set of timestamps for crossing road stop lines, determine the first frequency distribution of timestamps for stopping at traffic lights and the second frequency distribution of timestamps for crossing road stop lines;
[0095] In this step, the timestamp sets of timestamps for waiting at traffic lights and timestamps for crossing road stop lines are mapped to the corresponding traffic light cycles. Through normalization, the frequency distributions of timestamps for waiting at traffic lights and timestamps for crossing road stop lines in the traffic light cycle are obtained, and are denoted as the first frequency distribution of timestamps for waiting at traffic lights and the second frequency distribution of timestamps for crossing road stop lines, respectively.
[0096] Step 14: Determine the target score for the traffic light cycle corresponding to the acquisition window based on the first frequency distribution and the second frequency distribution.
[0097] In this step, the first and second frequency distributions of traffic light cycles with higher scores will be dispersed with little overlap; the first and second frequency distributions of traffic light cycles with lower scores will have greater overlap and tend to be randomly distributed.
[0098] For example, the following Figure 4 The target score of the corresponding frequency distribution map is better than Figure 5 The target score of the corresponding frequency distribution map.
[0099] Optionally, the Kolmogorov-Smirnov (KS) check can be used to detect whether the distribution of traffic lights follows a random distribution. The higher the degree of random distribution, the lower the score. KS scores are given to the two frequency distributions respectively (the score is negatively correlated with following a random distribution).
[0100] For example, one possible implementation of step 14 is:
[0101] Step 1: Determine the first score of the first frequency distribution under the KS test;
[0102] In this implementation, the first frequency distribution is compared with a preset ideal reference distribution (e.g., a uniform distribution representing uniform vehicle arrival, or a theoretical distribution representing the optimal queuing situation) using the KS test.
[0103] That is, by calculating the maximum vertical distance between two cumulative distribution functions, an objective statistic is obtained. This statistic is defined as the first score.
[0104] Step 2: Determine the second score of the second frequency distribution under the KS test;
[0105] In this implementation, the second frequency distribution is compared with another preset ideal reference distribution (e.g., a distribution that represents vehicles that can pass quickly and in a concentrated manner after the green light turns on) using the KS test.
[0106] That is, by calculating the maximum vertical distance between two cumulative distribution functions, an objective statistic is obtained. This statistic is defined as the second score.
[0107] Step 3: Based on the first score and the second score, determine the target score for the traffic light cycle corresponding to the collection window.
[0108] In this implementation, the average of the first score and the second score is used as the target score for the traffic light cycle corresponding to the collection window.
[0109] Furthermore, the method also includes the following implementation:
[0110] Implementation 1: If the target score is greater than the first preset score, then the evaluation corresponding to the traffic light cycle of the collection window is determined to be positive;
[0111] In this implementation, when the target score determined above is higher than the score line corresponding to the first preset score, the operation effect of the traffic light cycle can be determined to be positive.
[0112] This means that the overall performance of the signal timing within this traffic light cycle, taking into account both the rationality of vehicle waiting time distribution (first score) and the efficiency of traffic release (second score), has reached the preset excellent standard. In other words, the traffic flow during this cycle is relatively smooth, the green light time is effectively utilized, and the overall coordination is good.
[0113] Implementation 2: If the target score is less than or equal to the first preset score, then the evaluation corresponding to the traffic light cycle of the collection window is determined to be negative.
[0114] In this implementation, when the target score is lower than or equal to the first preset score, the cycle can be determined to be negative.
[0115] This means that the overall operational efficiency of this traffic light cycle has not met expectations, and there may be problems such as low utilization of green light time, slow dissipation of vehicle queues, or poor coordination between waiting and passage. This indicates that traffic management personnel need to pay close attention to the signal timing scheme for this specific cycle and may need to make optimizations to improve intersection efficiency.
[0116] Furthermore, the method also includes the following implementation:
[0117] Step 1: Determine the target score corresponding to each collection window, and determine the overall score for all traffic light cycles in the intersection to be evaluated;
[0118] In this implementation, the target score for each collection window (i.e., each independent traffic light cycle) in the intersection to be evaluated has been calculated using the aforementioned method.
[0119] Then, these target scores are aggregated using aggregation rules (e.g., calculating the arithmetic mean, median, or weighted average by period duration) to generate an overall score that represents the overall operational level of the intersection during the evaluation period.
[0120] This overall score transcends the performance of a single cycle, providing a comprehensive quantitative assessment of the intersection's overall traffic efficiency and signal timing effectiveness from a more macroscopic perspective.
[0121] Step 2: Store the signage and overall score of the intersection to be evaluated in the database.
[0122] In this implementation, the overall score calculated in the previous step is associated with an identifier that can uniquely identify the intersection to be evaluated (such as intersection ID, name, or geolocation code), and stored in the database as a complete record entry.
[0123] Furthermore, by repeating the above method, the cycle score for each acquisition window can be obtained. Through mapping, cycle scores for 96 time slices (15-minute intervals) can be obtained, and the average of these time slice scores is the current traffic light cycle score. The traffic light cycle scores are then stored in a database and updated periodically.
[0124] The traffic light cycle evaluation method provided in this application obtains collection windows corresponding to different traffic light cycles at the intersection to be evaluated. For each collection window, it obtains the set of timestamps for waiting at the light and crossing the stop line within the collection window during the evaluation period. Based on the timestamps for waiting at the light and crossing the stop line, it determines the first frequency distribution of waiting at the light and the second frequency distribution of crossing the stop line. Based on the first and second frequency distributions, it determines the target score for the traffic light cycle corresponding to the collection window. This scheme first uses collection windows to accurately divide the traffic light cycle and extracts the timestamp sets for waiting at the light and crossing the stop line, thereby constructing the first and second frequency distributions, thus transforming complex traffic behavior data into a quantifiable distribution model. Based on this, by comparing and analyzing the matching degree of the two distributions (such as overlap area or difference measure), it can objectively reflect the coordination efficiency of vehicle waiting and passage within the traffic light cycle, and finally achieve the target score for the operation effect of each cycle, effectively improving the accuracy of traffic light cycle evaluation and providing a scoring support basis for subsequent traffic light cycle adjustments.
[0125] Based on the above embodiments, Figure 3 A flowchart illustrating the traffic light cycle evaluation method provided in this application embodiment. Figure 2 ,like Figure 3 As shown, step 13 may include:
[0126] Step 31: Normalize multiple stop-at-the-light timestamps in the stop-at-the-light timestamp set within the traffic light cycle to generate the first frequency distribution;
[0127] In this step, all the timestamps of the actual stop times of all vehicles in the collection window, which are in absolute time coordinates, are mapped and aligned to a standardized traffic light cycle in relative time coordinates.
[0128] By statistically analyzing all such normalized times, a first frequency distribution is generated. This first frequency distribution visually represents the clustering of vehicle queuing requests along the time axis within a traffic light cycle, reflecting the traffic demand pressure during the red light period.
[0129] Example 1, Figure 4 A first example of the first frequency distribution map and the second frequency distribution map provided in the embodiments of this application, such as... Figure 4 As shown, taking a period of 91 seconds as an example:
[0130] Normalizing the timestamps of each stop at the light within a 91-second period yields the first frequency distribution map, as shown in red.
[0131] Example 2, Figure 5 A second example of the first frequency distribution map and the second frequency distribution map provided in the embodiments of this application, such as... Figure 5 As shown, taking a period of 55 seconds as an example:
[0132] Normalizing the timestamps of each stop at the light within a 55-second period yields the first frequency distribution map, as shown in red.
[0133] It should be understood that dark green still indicates the first frequency distribution, which overlaps with the second frequency distribution.
[0134] Step 32: Normalize the multiple timestamps of the ...
[0135] In this step, the timestamps of all vehicles actually crossing the road stop line in absolute time coordinates within the acquisition window are mapped onto the standardized traffic light cycle time axis mentioned above at the same ratio.
[0136] After normalizing and statistically analyzing all timestamps of the timestamps at the stop lines, a second frequency distribution is generated. This second frequency distribution clearly shows the time distribution pattern of the traffic capacity provided by the traffic lights (i.e., green light passage) actually consumed by vehicles within a traffic light cycle, reflecting the efficiency and pattern of traffic flow release.
[0137] Example 1, following the above Figure 4 As shown, taking a period of 91 seconds as an example:
[0138] Normalizing the timestamps of each road stop line within a 91-second period yields the second frequency distribution map, as shown in light green.
[0139] Example 2, continuing from the above, taking a period of 55 seconds as an example:
[0140] Normalizing the timestamps of each road stop line within a 55-second period yields the second frequency distribution map, as shown in light green.
[0141] It should be understood that dark green still indicates the second frequency distribution, which overlaps with the first frequency distribution.
[0142] The traffic light cycle evaluation method provided in this application normalizes multiple stop-at-the-light timestamps from the set of stop-at-the-light timestamps within the traffic light cycle to generate a first frequency distribution; and normalizes multiple stop-at-the-road timestamps from the set of stop-at-the-road timestamps within the traffic light cycle to generate a second frequency distribution. This scheme transforms discrete, absolute timeline vehicle behavior data into superimposed and comparable relative time distributions, thereby eliminating interference caused by differences in absolute duration and start time across different cycles. The first and second frequency distributions generated on this basis clearly and systematically reveal the coordinated patterns of vehicle aggregation and dissipation within the cycle, making it possible to quantitatively evaluate signal timing efficiency by directly comparing the morphology of the two distributions (such as peak offset and overlap area), ultimately achieving a stable and objective measurement of the traffic light cycle's operational efficiency.
[0143] Based on the above embodiments, Figure 6 A flowchart illustrating the traffic light cycle evaluation method provided in this application embodiment. Figure 3 ,like Figure 6 As shown, step 12, which involves obtaining the set of timestamps for stopping at traffic lights and crossing road stop lines within the data collection window during the evaluation period, may include:
[0144] Step 61: Obtain floating car trajectory data in the collection window during the evaluation period;
[0145] In this step, taking any collection window as an example, we can filter and extract all vehicle trajectory data that pass through or exist at the intersection to be evaluated from a massive amount of floating car data sources (such as GPS positioning data of taxis, buses, and ride-hailing vehicles) or electronic monitoring of traffic management departments, according to the pre-defined collection window.
[0146] Step 62: Based on the floating car trajectory data, determine the set of timestamps for stopping at traffic lights and the set of timestamps for crossing road stop lines.
[0147] In this step, by identifying patterns such as vehicle speed changes and position dwell times in the floating car trajectory data, the precise moment when each floating car stops and waits at the stop line at the intersection due to a red light is determined, thus forming a set of timestamps of the stopping and waiting time.
[0148] And the precise moment when a vehicle accelerates through the road stop line after the green light is turned on, thus forming a set of timestamps for the moment of crossing the road stop line.
[0149] Optionally, one possible implementation of step 62 is:
[0150] Step 1: Extract multiple timestamps of stopping at traffic lights and multiple timestamps of crossing road stop lines from the floating car trajectory data;
[0151] In this implementation, the trajectory containing the waiting-at-the-light behavior is extracted from the floating car trajectory data, and the waiting-at-the-light behavior is split into multiple waiting-at-the-light timestamps in 1-second increments.
[0152] Among them, the timestamp for the moment of waiting for the light is defined as follows: ,in, Represents the set of timestamps for the time when waiting for the light. This represents the number of timestamps indicating the time of the traffic light arrival. Representing the Each light is a time stamp.
[0153] Furthermore, the timestamp of the moment when the floating car crossed the road stop line is extracted from the floating car trajectory data using the same method described above.
[0154] The timestamp for crossing the road stop line is defined as follows: ,in, A set of timestamps representing the moments when a road stop line was crossed. The number of timestamps representing the moments when the road stopped at the stop line. Representing the A timestamp of the moment when the road stop line is crossed.
[0155] Step 2: Based on the first-time compensation data, compensate for multiple stop-and-wait-at-the-light timestamps to obtain a set of stop-and-wait-at-the-light timestamps;
[0156] In this implementation, the set of timestamps for the traffic light change times (red light to green light) is obtained based on the following formula. :
[0157]
[0158] in, This represents the time compensation for the set of timestamps indicating when the light turns green (or red to green) and the waiting time at the light, i.e., the first-time compensation data. By aggregating the data for the period to be evaluated (e.g., 30 days), the set of timestamps indicating the time spent waiting at the light can be obtained. .
[0159] Step 3: Based on the second time compensation data, compensate for the timestamps of multiple timestamps when crossing the road stop line to obtain a set of timestamps when crossing the road stop line.
[0160] In this implementation, the set of timestamps for the road stop line timestamps that align with the traffic light change time (red light to green light) is obtained based on the following formula. :
[0161]
[0162] in, This represents the time compensation of the set of timestamps indicating when the light changes from green (red to green) and when the road stop line is crossed; it is the second time compensation data. By aggregating 30 days of data, the set of timestamps indicating when the road stop line is crossed can be obtained. .
[0163] It should be understood that both the second and first time compensation data mentioned above can be set based on experiments or the experience of technical personnel.
[0164] The traffic light cycle evaluation method provided in this application acquires floating car trajectory data within the collection window during the evaluation period. Based on the floating car trajectory data, it determines the set of timestamps for stopping at the light and the set of timestamps for crossing the road stop line. This scheme bypasses the dependence on current fixed detectors, greatly expanding the data collection range and significantly reducing hardware costs. Based on the continuous information such as vehicle speed and position contained in the trajectory data, it can accurately identify two key behavioral nodes: the vehicle decelerates to a stop (corresponding to the stopping at the light) and accelerates from a standstill to cross the stop line (corresponding to the time of crossing the line). This automatically constructs two high-precision timestamp sets, providing a core data foundation that is difficult to obtain using traditional methods and truly reflects the dynamic behavior of vehicles for subsequent fine-grained traffic light cycle evaluation.
[0165] Figure 7 This is a schematic diagram of the traffic light cycle evaluation device provided in the embodiments of this application, as shown below. Figure 7 As shown, the traffic light cycle evaluation device includes:
[0166] The first acquisition module 71 is used to acquire the acquisition windows corresponding to different traffic light cycles in the intersection to be evaluated.
[0167] The second acquisition module 72 is used to acquire, for each acquisition window, the set of timestamps of the time of stopping at the traffic lights and the set of timestamps of the time of crossing the road stop line in the acquisition window during the period to be evaluated;
[0168] The first determining module 73 is used to determine the first frequency distribution of the time of stopping at the traffic light and the second frequency distribution of the time of crossing the road stop line based on the set of timestamps of the time of stopping at the traffic light and the set of timestamps of the time of crossing the road stop line.
[0169] The second determining module 74 is used to determine the target score of the traffic light cycle corresponding to the acquisition window based on the first frequency distribution and the second frequency distribution.
[0170] In one or more embodiments, the first determining module 73 is specifically used for:
[0171] The multiple stop-at-the-light timestamps in the set of stop-at-the-light timestamps are normalized within the traffic light cycle to generate the first frequency distribution;
[0172] Multiple timestamps of ...
[0173] In one or more embodiments, the second determining module 74 is specifically used for:
[0174] Determine the first score of the first frequency distribution under the KS test;
[0175] Determine the second score of the second frequency distribution under the KS test;
[0176] Based on the first score and the second score, determine the target score for the traffic light cycle corresponding to the collection window.
[0177] In one or more embodiments, the first determining module 73 is further configured to:
[0178] If the target score is greater than the first preset score, then the evaluation corresponding to the traffic light cycle of the collection window is determined to be positive.
[0179] If the target score is less than or equal to the first preset score, then the evaluation corresponding to the traffic light cycle of the collection window is determined to be negative.
[0180] In one or more embodiments, the second acquisition module 72 acquires the set of timestamps for stopping at traffic lights and the set of timestamps for crossing road stop lines within the acquisition window during the evaluation period, specifically for:
[0181] Acquire floating car trajectory data within the collection window during the evaluation period;
[0182] Based on the floating car trajectory data, determine the set of timestamps for the time when stopping at traffic lights and the set of timestamps for the time when crossing the road stop line.
[0183] In one or more embodiments, the second acquisition module 72 determines, based on the floating car trajectory data, a set of timestamps for stopping at traffic lights and a set of timestamps for crossing road stop lines, specifically for:
[0184] Multiple timestamps for stopping at traffic lights and multiple timestamps for crossing road stop lines were extracted from the floating car trajectory data.
[0185] Based on the first-time compensation data, the timestamps of multiple stops waiting at the traffic lights are compensated to obtain a set of timestamps of stops waiting at the traffic lights;
[0186] Based on the second time compensation data, the timestamps of multiple timestamps when crossing the road stop line are compensated to obtain a set of timestamps when crossing the road stop line.
[0187] In one or more embodiments, the second determining module 74 is further configured to:
[0188] Determine the target score for each data collection window and the overall score for all traffic light cycles at the intersection to be evaluated.
[0189] The signage and overall score of the intersection to be evaluated are stored in the database.
[0190] It should be noted that the division of the various modules in the above device is merely a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical element, or they can be physically separated. Furthermore, these modules can be implemented entirely in software through processing element calls, or entirely in hardware. Alternatively, some modules can be implemented through processing element calls in software, while others can be implemented in hardware. Moreover, these modules can be integrated together or implemented independently. The processing element here can be an integrated circuit with signal processing capabilities. During implementation, each step of the above method or each of the above modules can be completed through the integrated logic circuits in the hardware of the processor element or through software instructions.
[0191] As can be seen from the above, the traffic light cycle evaluation device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.
[0192] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 8 As shown, the electronic device provided in this embodiment includes at least one processor 81 and a memory 82.
[0193] Optionally, the electronic device also includes a communication component 83.
[0194] The processor 81, memory 82, and communication component 83 are connected via bus 84.
[0195] In a specific implementation, at least one processor 81 executes computer execution instructions stored in memory 82, causing at least one processor 81 to perform the above-described method.
[0196] The specific implementation process of processor 81 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.
[0197] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.
[0198] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.
[0199] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.
[0200] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.
[0201] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.
[0202] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.
[0203] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.
[0204] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.
[0205] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.
[0206] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.
[0207] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0208] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.
[0209] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.
Claims
1. A method for evaluating the cycle of traffic lights, characterized in that, include: Obtain the data collection windows corresponding to different traffic light cycles at the intersection to be evaluated; For each collection window, obtain the set of timestamps for the time spent waiting at traffic lights and the set of timestamps for the time spent crossing the road stop line within the collection window during the period to be evaluated; Based on the set of timestamps for stopping at traffic lights and the set of timestamps for crossing road stop lines, determine the first frequency distribution of timestamps for stopping at traffic lights and the second frequency distribution of timestamps for crossing road stop lines; Based on the first frequency distribution and the second frequency distribution, the target score for the traffic light cycle corresponding to the acquisition window is determined.
2. The method according to claim 1, characterized in that, The step of determining the first frequency distribution of waiting times at traffic lights and the second frequency distribution of crossing stop lines based on the set of timestamps for waiting times at traffic lights and the set of timestamps for crossing stop lines includes: The multiple stop-at-the-light timestamps in the set of stop-at-the-light timestamps are normalized within the traffic light cycle to generate the first frequency distribution; The timestamps of multiple road stop line timestamps in the set of road stop line timestamps are normalized within the traffic light cycle to generate the second frequency distribution.
3. The method according to claim 1 or 2, characterized in that, The step of determining the target score for the traffic light cycle corresponding to the acquisition window based on the first frequency distribution and the second frequency distribution includes: Determine the first score of the first frequency distribution under the KS test; Determine the second score of the second frequency distribution under the KS test; Based on the first score and the second score, the target score for the traffic light cycle corresponding to the acquisition window is determined.
4. The method according to claim 3, characterized in that, The method further includes: If the target score is greater than the first preset score, then the evaluation corresponding to the traffic light cycle of the collection window is determined to be positive. If the target score is less than or equal to the first preset score, then the evaluation corresponding to the traffic light cycle of the collection window is determined to be negative.
5. The method according to claim 1 or 2, characterized in that, The process of obtaining the set of timestamps for stopping at traffic lights and the set of timestamps for crossing road stop lines within the collection window during the evaluation period includes: Obtain the floating car trajectory data in the collection window during the time period to be evaluated; Based on the floating car trajectory data, determine the set of timestamps for the time when the car stops at the traffic light and the set of timestamps for the time when the car crosses the road stop line.
6. The method according to claim 5, characterized in that, The step of determining the set of timestamps for the time spent waiting at traffic lights and the set of timestamps for the time spent crossing road stop lines based on the floating car trajectory data includes: Multiple timestamps for stopping at traffic lights and multiple timestamps for crossing road stop lines were extracted from the floating car trajectory data. Based on the first-time compensation data, the timestamps of the multiple stops waiting at the lights are compensated to obtain the set of timestamps of the stops waiting at the lights; Based on the second time compensation data, the timestamps of the multiple timestamps for crossing the road stop line are compensated to obtain the set of timestamps for crossing the road stop line.
7. The method according to claim 1 or 2, characterized in that, The method further includes: Determine the target score corresponding to each collection window, and determine the overall score for all traffic light cycles in the intersection to be evaluated; The identifiers of the intersections to be evaluated and the overall score are stored in the database.
8. A traffic light cycle evaluation device, characterized in that, include: The first acquisition module is used to acquire the collection windows corresponding to different traffic light cycles at the intersection to be evaluated. The second acquisition module is used to acquire, for each acquisition window, the set of timestamps of the time spent waiting at traffic lights and the set of timestamps of the time spent crossing the road stop line in the acquisition window within the time period to be evaluated; The first determining module is used to determine a first frequency distribution of the time spent waiting at the traffic lights and a second frequency distribution of the time spent crossing the road stop line based on the set of timestamps of the ... The second determining module is used to determine the target score of the traffic light cycle corresponding to the acquisition window based on the first frequency distribution and the second frequency distribution.
9. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-7.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-7.