Signal control scheme identification method, system, device and medium based on vehicle passing data

Abstract

The present invention relates to a signal control scheme identification method, system, equipment and medium based on vehicle passing data, and the method includes: obtaining vehicle passing data classified by vehicle flow direction; performing autocorrelation analysis on the vehicle passing data of each direction, and grouping the obtained signal period data to obtain a division scheme for signal control time periods; performing curve fitting on the vehicle passing data of each direction under each signal control period at each intersection, and identifying the maximum value points and corresponding time data of each fitting curve; by comparing the time data of the maximum value points of the fitting curves of each direction in the same time period, the vehicles of different directions with deviations less than a set threshold are classified as the same signal phase, and the fitting curves of different signal phases in the same signal cycle are graphically superimposed, and the phase sequence and phase duration of each signal phase are determined based on the maximum value points and intersection points of the fitting curves after superposition. The present invention solves the technical problem of poor signal control scheme identification effect in the prior art.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic signal control recognition, and in particular to a signal control scheme recognition method, system, device and medium based on vehicle passing data. Background Art

[0002] Signal control schemes are important traffic data in traffic control and evaluation. Generally speaking, except for a few intersections that use intelligent algorithms to implement signal control schemes in real time, most intersections use time-divided and timed signal control schemes. That is, when a day is divided into multiple control periods, the signal control scheme in each control period remains unchanged, showing the characteristics of cyclic control. However, since signal machine manufacturers do not open signal control scheme data communication protocols, and relevant departments do not provide data access permissions due to information security issues, the actual signal control scheme is usually difficult to obtain directly.

[0003] At present, in the prior art, the data of vehicles passing by the phase of the green light signal at the intersection is obtained by capturing the vehicle at the intersection, and then the data of vehicles passing by is analyzed to obtain the phase duration and phase sequence of the signal control at the intersection. However, the traditional signal control scheme identification method only identifies the phase duration and phase sequence of the signal control, and the range of data identified is small, which cannot fully describe the signal control scheme, and when identifying the time-divided signal control scheme, the analysis of the phase data needs to be carried out separately by time period, thereby increasing the workload and time cost. In addition, the identification of the signal control scheme is often aimed at the control scheme of each intersection of the road, and the signal control scheme of each intersection needs to be identified, which results in a lot of time required for analysis and identification in sequence, which seriously affects the speed of obtaining traffic data.

[0004] Therefore, those skilled in the art are in urgent need of developing a technical means that can quickly and comprehensively analyze and identify signal control schemes at multiple intersections on a road. Summary of the invention

[0005] 1. Technical issues to be resolved

[0006] In view of the above-mentioned shortcomings and deficiencies of the prior art, the present invention provides a method, system, device and medium for identifying a signal control scheme based on vehicle passing data, which solves the technical problem of poor signal control scheme identification effect in the prior art.

[0007] (II) Technical solution

[0008] In order to achieve the above object, the main technical solutions adopted by the present invention include:

[0009] In a first aspect, an embodiment of the present invention provides a signal control scheme identification method based on vehicle passing data, comprising:

[0010] The vehicle passing data acquired throughout the day is divided into time and flow direction aggregated to obtain vehicle passing data classified by vehicle flow direction;

[0011] The time series of the traffic data of each direction at the intersection is processed by autocorrelation analysis to identify the signal cycle data, and the obtained signal cycle data is grouped and processed in an orderly clustering manner to obtain the division scheme of the signal control period;

[0012] The vehicle passing data of each direction in each signal control period at each intersection is sorted by time to form a time series and curve fitting is performed to identify the maximum value points and corresponding time data of each fitting curve;

[0013] By comparing the time data of the maximum points of the fitting curves of each flow direction in the same time period, the traffic flows in different directions with deviations less than the set threshold are classified as the same signal phase, and the fitting curves of different signal phases in the same signal cycle are graphically superimposed. The phase sequence and phase duration of each signal phase are determined based on the maximum points and intersection points of the superimposed fitting curves.

[0014] Optionally, the acquired vehicle passing data for the whole day is divided into time and aggregated by flow direction, and the vehicle passing data classified by vehicle flow direction is obtained, including:

[0015] Obtain the vehicle passing data on the road throughout the day, which includes vehicle information, intersection information, entrance information, lane information and passing time information;

[0016] Divide the vehicle passing data into seconds to determine the vehicle passing data at the same entrance of the intersection within each second;

[0017] The vehicle passing data of the same entrance and the same flow direction in continuous time are aggregated to obtain the vehicle passing data classified by vehicle flow direction.

[0018] Optionally, the time series of the vehicle passing data in each direction of the intersection is processed by autocorrelation analysis to identify the signal cycle data, and the obtained signal cycle data is grouped and processed in an orderly clustering manner to obtain a division scheme for the signal control period, including:

[0019] The vehicle passing data classified by vehicle flow direction is divided into several time periods according to the set time intervals;

[0020] According to the preset multiple period values ​​and the autocorrelation coefficient calculation formula, the autocorrelation coefficient of the vehicle passing data in each period is obtained;

[0021] When the autocorrelation coefficient is at its maximum value, the period value corresponding to the autocorrelation coefficient is the signal period data;

[0022] According to the time series of vehicle passing data, the data of different signal cycles are grouped and processed in an orderly manner to obtain the division scheme of signal control periods;

[0023] The autocorrelation coefficient calculation formula is:

[0024] ;

[0025] In the formula, R (c) represents the autocorrelation coefficient when the period is c, T represents the time interval, c represents the period value, c =[1, T -1], Q t Representative t The total number of vehicles passing in seconds, represents the average number of vehicles passing during the entire time interval, Q t+c Representative t + c The total number of vehicles passing within a second.

[0026] Optionally, according to the time series of the vehicle passing data, the different signal cycle data are subjected to orderly clustering and grouping processing, and the division scheme of the signal control period is obtained, including:

[0027] Clean the signal cycle data in each time interval to remove abnormal data;

[0028] Conduct orderly cluster analysis on the signal cycle data after data cleaning, and group them according to the analysis results and the time series of vehicle passing data to obtain the division scheme of signal control period;

[0029] The mode of the duration of the cycle value in the signal control period is obtained, and the cycle value corresponding to the mode is used as the optimal signal cycle data of the signal control period.

[0030] Optionally, the vehicle passing data of each direction in each signal control period at each intersection is sorted in time to form a time series and curve fitting is performed, and the maximum value points and corresponding time data of each fitting curve are identified, including:

[0031] The vehicle passing data of each direction in each signal control period at each intersection is sorted by time to form a time series of the vehicle passing data;

[0032] Based on the time series, Fourier series is used to perform curve fitting on the vehicle passing data of each direction in each signal control period at each intersection;

[0033] Each fitting curve is smoothed, and the maximum points and corresponding time data in each fitting curve after processing are identified.

[0034] Optionally, by comparing the time data of the maximum points of the fitting curves of each flow direction in the same time period, the traffic flows in different directions with deviations less than a set threshold are classified as the same signal phase, and the fitting curves of different signal phases in the same signal cycle are graphically superimposed, and the phase sequence and phase duration of each signal phase are determined based on the maximum points and intersection points of the superimposed fitting curves, including:

[0035] By comparing the time data of the maximum value points of the fitting curves of different flow directions in the same period, the traffic flows of different flows with deviations less than the set threshold are classified as the same signal phase;

[0036] Extracting curve data within the same signal period from fitting curves of different signal phases, and graphically superimposing the curve data to obtain a superimposed fitting curve;

[0037] By identifying the maximum value points and corresponding time data of each curve data in the superimposed fitting curve, and according to the time sequence of the maximum value points, the phase sequence of each signal phase is determined;

[0038] The phase duration of each signal phase is determined by identifying the intersection points and corresponding time data of each curve data in the superimposed fitting curve and according to the difference between the intersection points and time.

[0039] Optionally, by comparing the time data of the maximum value points of the fitting curves of each flow direction in the same period, the traffic flows of different flows with deviations less than a set threshold are classified into the same signal phase, including:

[0040] The maximum value points of the fitting curves of each flow direction within the same signal control period are grouped in a manner of at least two maximum value points as one group;

[0041] The deviation value at the time corresponding to the maximum point in each group is compared with the set threshold, and based on the comparison result, it is determined whether the traffic corresponding to the maximum point in the group is in the same signal phase;

[0042] If the deviation value at the time corresponding to the maximum point in the group is less than the set threshold, the traffic corresponding to the maximum point in the group is in the same signal phase;

[0043] If the deviation value at the time corresponding to the maximum point in the group is greater than or equal to the set threshold, the traffic corresponding to the maximum point in the group is not in the same signal phase.

[0044] In a second aspect, an embodiment of the present invention provides a signal control scheme identification system based on vehicle passing data, comprising:

[0045] The vehicle passing data aggregation module is used to divide the acquired vehicle passing data for the whole day into time and flow direction, and obtain the vehicle passing data classified by vehicle flow direction;

[0046] The signal control period identification module is used to process the time series of the traffic data of each direction at the intersection through autocorrelation analysis to identify the signal period data, and to perform orderly clustering grouping processing on the obtained signal period data to obtain the division scheme of the signal control period;

[0047] The curve fitting and identification module is used to sort the vehicle passing data of each direction in each signal control period at each intersection into a time series and perform curve fitting, and identify the maximum value points and corresponding time data of each fitting curve;

[0048] The signal phase information identification module is used to classify the traffic flows in different directions with deviations less than a set threshold into the same signal phase by comparing the time data of the maximum points of the fitting curves of each flow direction in the same time period, and to graphically superimpose the fitting curves of different signal phases in the same signal cycle, and determine the phase sequence and phase duration of each signal phase based on the maximum points and intersection points of the superimposed fitting curves.

[0049] In a third aspect, an embodiment of the present invention provides an electronic device, including:

[0050] processor;

[0051] A memory storing steps for the processor to control the above-mentioned signal control scheme identification method based on vehicle passing data.

[0052] In a fourth aspect, an embodiment of the present invention provides a computer-readable medium having computer executable instructions stored thereon, and when the executable instructions are executed by a processor, the above-mentioned method steps for identifying a signal control scheme based on vehicle passing data are implemented.

[0053] (III) Beneficial effects

[0054] The beneficial effects of the present invention are as follows: the signal control scheme identification method based on vehicle passing data of the present invention first obtains the division scheme of the signal control period by analyzing the periodic changes of the vehicle passing data; then, a curve is fitted according to the time series for the vehicle passing data of each flow direction under the signal control period, and the maximum value points of the fitting curve and the corresponding time data are analyzed; then, based on each maximum value point and the corresponding time data, the phase sequence and phase duration of each signal phase in the corresponding signal control period are identified. Compared with the prior art, it can comprehensively identify the signal control scheme, describe the signal control scheme in a more detailed and accurate manner, and further improve the recognition speed of the phase sequence and phase duration by automatically identifying the signal control period division scheme. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 A flow chart of a method for identifying a signal control scheme based on vehicle passing data provided by one embodiment of the present invention;

[0056] Figure 2 A data effect diagram after preprocessing of vehicle passing data is provided for an embodiment of the present invention;

[0057] Figure 3 A schematic diagram of changes in the autocorrelation coefficient of vehicle passing data in a time series is provided for one embodiment of the present invention;

[0058] Figure 4 A schematic diagram of the change of the signal period throughout the day when abnormal data exists is provided for one embodiment of the present invention;

[0059] Figure 5 A Fourier series fitting effect diagram of vehicle passing data is provided for one embodiment of the present invention;

[0060] Figure 6 An effect diagram of multiple Fourier series curve fitting after image superposition is provided for one embodiment of the present invention;

[0061] Figure 7 A schematic diagram of the composition of a signal control scheme identification system based on vehicle passing data provided by one embodiment of the present invention;

[0062] Figure 8 A schematic diagram of the structure of a computer system of an electronic device provided by the present invention.

[0063] [Description of Reference Numerals]

[0064] 100: signal control scheme identification system based on vehicle passing data; 101: vehicle passing data aggregation module; 102: signal control period identification module; 103: curve fitting and identification module; 104: signal phase information identification module;

[0065] 200: computer system; 201: CPU; 202: ROM; 203: RAM; 204: bus; 205: I / O interface; 206: input part; 207: output part; 208: storage part; 209: communication part; 210: drive; 211: removable medium. DETAILED DESCRIPTION

[0066] In order to better explain the present invention and facilitate understanding, the present invention is described in detail below through specific implementation modes in conjunction with the accompanying drawings.

[0067] refer to Figure 1As shown, an embodiment of the present invention proposes a signal control scheme identification method based on vehicle passing data, a system, a device and a medium, and the method includes: performing time division and flow direction aggregation on the acquired vehicle passing data for the whole day to obtain vehicle passing data classified by vehicle flow direction; processing the time series of vehicle passing data of each flow direction at the intersection by autocorrelation analysis to identify signal period data, and performing orderly clustering grouping processing on the obtained signal period data to obtain a division scheme for the signal control period; sorting the vehicle passing data of each flow direction in each signal control period at each intersection by time to form a time series and perform curve fitting to identify the maximum point and corresponding time data of each fitting curve; by comparing the time data of the maximum point of the fitting curve of each flow direction in the same time period, the vehicle flows of different directions with deviations less than a set threshold are classified as the same signal phase, and the fitting curves of different signal phases in the same signal period are graphically superimposed, and the phase sequence and phase duration of each signal phase are determined based on the maximum point and intersection point of the superimposed fitting curve.

[0068] In this embodiment, the division scheme of the signal control period is first obtained by analyzing the periodic changes of the vehicle passing data; then, a curve is fitted according to the time series for the vehicle passing data of each flow direction under the signal control period, and the maximum value points and the corresponding time data of the fitting curve are analyzed; then, based on each maximum value point and the corresponding time data, the phase sequence and phase duration of each signal phase in the corresponding signal control period are identified. Compared with the prior art, it can comprehensively identify the signal control scheme, describe the signal control scheme in a more detailed and accurate manner, and further improve the recognition speed of the phase sequence and phase duration by automatically identifying the signal control period division scheme.

[0069] In order to better understand the above technical solution, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to enable a clearer and more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0070] Specifically, refer to Figure 1 As shown, this embodiment proposes a signal control scheme identification method based on vehicle passing data, which includes:

[0071] S100, performing time division and flow direction aggregation on the acquired vehicle passing data for the whole day to obtain vehicle passing data classified by vehicle flow direction.

[0072] In this embodiment, step S100 may include the following sub-steps S110-S130:

[0073] S110, obtaining vehicle passing data on the road throughout the day, the vehicle passing data including vehicle information, intersection information, entrance information, lane information and passing time information.

[0074] S120, dividing the vehicle passing data into seconds as a time unit, and determining the vehicle passing data passing through the same entrance of the intersection within each second.

[0075] S130, performing flow aggregation on the vehicle passing data of the same entrance and the same flow direction within a continuous time to obtain vehicle passing data classified by vehicle flow direction.

[0076] For example, the simple moving average (SMA) method is used to pre-process the vehicle passing data of the road section throughout the day, and the vehicle passing data of the original lane is aggregated according to the traffic flow direction to obtain the vehicle passing data classified by the traffic flow direction. Figure 2 The specific method is: first, divide a day into n Then, the number of vehicles passing through different lanes at the same intersection, the same entrance, and the same flow direction is added together to obtain the intersection a import i Flow direction j In the m Total number of vehicles passing in seconds Q i,j,m Finally, k The average number of vehicles passing per second is taken as the m Total number of vehicles processed in seconds Q’ i,j,m , and its mathematical expression is shown in formula (1).

[0077] (1)

[0078] S200, processing the time series of the vehicle passing data in each direction at the intersection through autocorrelation analysis to identify the signal cycle data, and performing orderly clustering grouping processing on the obtained signal cycle data to obtain a division scheme for the signal control period.

[0079] In this embodiment, step S200 may include the following sub-steps S210-S240:

[0080] S210, dividing the vehicle passing data classified by vehicle flow direction into several time periods according to set time intervals.

[0081] S220. Obtain the autocorrelation coefficient of the vehicle passing data in each time period according to the preset multiple period values ​​and in combination with the autocorrelation coefficient calculation formula.

[0082] The formula for calculating the autocorrelation coefficient is:

[0083] (2)

[0084] (2) In the formula, R (c) represents the autocorrelation coefficient when the period is c, T represents the time interval, c represents the period value, c =[1, T -1], Q t Representative t The total number of vehicles passing in seconds, represents the average number of vehicles passing during the entire time interval, Q t+c Representative t + c The total number of vehicles passing within a second.

[0085] S230. When the autocorrelation coefficient is at a maximum value, the period value corresponding to the autocorrelation coefficient is signal period data.

[0086] For example, to perform autocorrelation analysis on the vehicle passing data within a time interval of 15 minutes, first, intercept the vehicle passing data within a time interval of 15 minutes; then, divide 15 minutes into 1800 seconds, and assume that the vehicle passing data in the same flow direction has a period value of 1 second, 2 seconds, 3 seconds, and up to 1799 seconds; then, for each different period change value, calculate the autocorrelation coefficient of the vehicle passing data in the same flow direction using formula (2). The autocorrelation coefficient change data is as follows: Figure 3 Finally, when the autocorrelation coefficient is the largest, the period value corresponding to the autocorrelation coefficient is the signal period data of the flow direction, that is, the period of the real change of the vehicle passing data of the flow direction.

[0087] S240: performing orderly clustering and grouping processing on different signal cycle data according to the time series of the vehicle passing data to obtain a division scheme for the signal control period.

[0088] Further, step S240 may include the following sub-steps S241-S243:

[0089] S241, clean the signal cycle data in each time interval to remove abnormal data. The abnormal data includes abnormal changes caused by running a red light, vehicle breakdown, temporary traffic control by traffic police, etc. For example, Figure 4 The figure shows the signal period variation data for the whole day when abnormal data exists.

[0090] S243, performing ordered cluster analysis on the signal cycle data after data cleaning, and grouping them according to the analysis results and the time series of the vehicle passing data to obtain a division scheme for the signal control period.

[0091] S243, obtaining the mode of the duration of the cycle value in the signal control period, and taking the cycle value corresponding to the mode as the optimal signal cycle data of the signal control period.

[0092] For example, the division scheme of the signal control period of a certain intersection throughout the day is identified in steps S241-S243, and the division scheme of the signal control period of the intersection throughout the day is obtained as follows: Period 1: 00:00-07:00; Period 2: 07:00-09:00; Period 3: 09:00-17:00; Period 4: 17:00-19:00; Period 5: 19:00-23:59. Among them, the optimal signal cycle data of each period are: the optimal signal cycle of period 1 is 100s; the optimal signal cycle of period 2 is 140s; the optimal signal cycle of period 3 is 120s, the optimal signal cycle of period 4 is 140s; and the optimal signal cycle of period 5 is 100s.

[0093] S300, sorting the vehicle passing data of each direction in each signal control period at each intersection into a time series and performing curve fitting, identifying the maximum value point and corresponding time data of each fitting curve.

[0094] In this embodiment, step S300 may include the following sub-steps S310-S330:

[0095] S310, sorting the vehicle passing data of each direction in each signal control period at each intersection by time to form a time series of the vehicle passing data.

[0096] S320, according to the time series, using Fourier series to perform curve fitting on the vehicle passing data of each flow direction in each signal control period at each intersection.

[0097] S330, performing smoothing processing on each fitting curve, and identifying the maximum value point and the corresponding time data in each fitting curve after processing.

[0098] The vehicle data of each direction in each signal control period at each intersection are sorted by time, and Fourier series is used for curve fitting to further smooth the data and highlight the periodic change characteristics of the data. This method better avoids the problem of unstable and missing original data. The Fourier series fitting effect is shown in the figure below. Figure 5 As shown. Among them, the mathematical expression of Fourier series curve fitting is:

[0099] (3)

[0100] (3) In the formula, C is the signal period, a 0. a n, b n represents the Fourier coefficient, R is the number of Fourier terms (default is 10).

[0101] S400. By comparing the time data of the maximum points of the fitting curves of each flow direction in the same time period, the traffic flows in different directions with deviations less than a set threshold are classified as the same signal phase, and the fitting curves of different signal phases in the same signal cycle are graphically superimposed, and the phase sequence and phase duration of each signal phase are determined based on the maximum points and intersection points of the superimposed fitting curves.

[0102] In this embodiment, step S400 may include the following sub-steps S410-S440:

[0103] S410, by comparing the time data of the maximum points of the fitting curves of various flow directions in the same period, the traffic flows of different directions with deviations less than a set threshold are classified into the same signal phase.

[0104] Further, step S410 may include the following sub-steps S411-S413:

[0105] S411, grouping the maximum value points of the fitting curves of each flow direction within the same signal control period into a group of at least two maximum value points;

[0106] S412: Compare the deviation value at the time corresponding to the maximum point in each group with the set threshold, and determine whether the traffic corresponding to the maximum point in the group is in the same signal phase based on the comparison result.

[0107] S413a: If the deviation value at the time corresponding to the maximum point in the group is less than the set threshold, the traffic flows corresponding to the maximum point in the group are in the same signal phase.

[0108] S413b: If the deviation value at the time corresponding to the maximum point in the group is greater than or equal to the set threshold, the traffic flows corresponding to the maximum point in the group are not in the same signal phase.

[0109] For example, at a certain intersection, if the deviation value of the maximum point in the fitting curve of the left-turning traffic flow at the east entrance and the left-turning traffic flow at the west entrance is less than the set threshold, they are released through the intersection at the same green light signal phase.

[0110] S420, extracting curve data within the same signal period from the fitting curves of different signal phases, and graphically superimposing the curve data to obtain a superimposed fitting curve.

[0111] S430, by identifying the maximum value points and corresponding time data of each curve data in the superimposed fitting curve, and according to the time sequence of the maximum value points, determining the phase sequence of each signal phase.

[0112] S440, by identifying the intersection points and corresponding time data of each curve data in the superimposed fitting curve, and determining the phase duration of each signal phase according to the difference between the intersection points and time.

[0113] In a specific embodiment, curve data within the same signal period are intercepted from the fitting curves of different signal phases, and the curve data are graphically superimposed to obtain the following: Figure 6 The superimposed fitting curve is shown in the figure. Then, the time sequence of each maximum point in the fitting curve is identified to determine the phase sequence of each signal phase. Finally, the intersection of each fitting curve in the fitting curve is identified, which is the phase switching moment, and the difference between two adjacent phase switching moments is the phase duration.

[0114] also, Figure 7 A schematic diagram of the composition of a signal control scheme identification system based on vehicle passing data provided by the present invention is shown in FIG. Figure 7 As shown, the present invention also provides a signal control scheme identification system 100 based on vehicle passing data, which includes:

[0115] The vehicle passing data aggregation module 101 is used to divide the acquired vehicle passing data for the whole day into time and aggregate the flow direction to obtain the vehicle passing data classified by the vehicle flow direction.

[0116] The signal control period identification module 102 is used to process the time series of the vehicle passing data of each flow direction at the intersection through autocorrelation analysis to identify the signal period data, and to perform orderly clustering grouping processing on the obtained signal period data to obtain a division scheme of the signal control period.

[0117] The curve fitting and identification module 103 is used to sort the vehicle passing data of each direction in each signal control period at each intersection into a time series and perform curve fitting, and identify the maximum value point and corresponding time data of each fitting curve.

[0118] The signal phase information identification module 104 is used to classify the traffic flows in different directions with deviations less than a set threshold into the same signal phase by comparing the time data of the maximum points of the fitting curves of each flow direction in the same time period, and to graphically superimpose the fitting curves of different signal phases in the same signal cycle, and determine the phase sequence and phase duration of each signal phase based on the maximum points and intersection points of the superimposed fitting curves.

[0119] The functions of each unit in the system refer to the relevant description in the above method embodiment, which will not be repeated here.

[0120] Furthermore, the present invention provides an electronic device including a processor and a memory, wherein the memory stores steps for the processor to control a signal control scheme identification method based on vehicle passing data as described above.

[0121] Reference below Figure 8 , which shows a schematic diagram of the structure of a computer system 200 suitable for implementing the electronic device of this embodiment. Figure 8 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0122] like Figure 8 As shown, the computer system 200 includes a central processing unit (CPU) 201, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 202 or a program loaded from a storage part 208 into a random access memory (RAM) 203. In the RAM 203, various programs and data required for the operation of the system 200 are also stored. The CPU 201, the ROM 202, and the RAM 203 are connected to each other through a bus 204. An input / output (I / O) interface 205 is also connected to the bus 204.

[0123] The following components are connected to the I / O interface 205: an input section 206 including a keyboard, a mouse, etc.; an output section 207 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 208 including a hard disk, etc.; and a communication section 209 including a network interface card such as a LAN card, a modem, etc. The communication section 209 performs communication processing via a network such as the Internet. A drive 210 is also connected to the I / O interface 205 as needed. A removable medium 211, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 210 as needed, so that a computer program read therefrom is installed into the storage section 208 as needed.

[0124] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 209, and / or installed from a removable medium 211. When the computer program is executed by the central processing unit (CPU) 201, the above-mentioned functions defined in the system of the present application are executed.

[0125] It should be noted that the computer-readable medium shown in the present application may be a computer-readable signal medium or a computer-readable medium or any combination of the above two. The computer-readable medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable media may include, but are not limited to: an electrical connection with one or more wires, 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 above. In the present application, a computer-readable medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable medium other than a computer-readable medium that can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0126] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0127] The units involved in the embodiments described in this application may be implemented by software or hardware. The units described may also be arranged in a processor, wherein the names of these units do not constitute limitations on the units themselves in certain circumstances.

[0128] Finally, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device includes the following method steps:

[0129] S100, performing time division and flow direction aggregation on the acquired vehicle passing data for the whole day to obtain vehicle passing data classified by vehicle flow direction.

[0130] S200, processing the time series of the vehicle passing data in each direction at the intersection through autocorrelation analysis to identify the signal cycle data, and performing orderly clustering grouping processing on the obtained signal cycle data to obtain a division scheme for the signal control period.

[0131] S300, sorting the vehicle passing data of each direction in each signal control period at each intersection into a time series and performing curve fitting, identifying the maximum value point and corresponding time data of each fitting curve.

[0132] S400. By comparing the time data of the maximum points of the fitting curves of each flow direction in the same time period, the traffic flows in different directions with deviations less than a set threshold are classified as the same signal phase, and the fitting curves of different signal phases in the same signal cycle are graphically superimposed, and the phase sequence and phase duration of each signal phase are determined based on the maximum points and intersection points of the superimposed fitting curves.

[0133] In summary, an embodiment of the present invention proposes a signal control scheme identification method, system, device and medium based on vehicle passing data, and the method includes: first, aggregating the vehicle passing data of the whole day according to the flow direction of the vehicle flow to obtain the vehicle passing data classified by the flow direction of the vehicle flow; second, performing autocorrelation analysis on the vehicle passing data of each flow direction according to the time sequence, and performing orderly clustering grouping processing on the obtained signal control period data to obtain the division scheme of the signal control period; third, fitting the vehicle passing data of each flow direction in the signal control period into a Fourier series curve according to the time sequence, and identifying the maximum points in each Fourier series curve; then, grouping all the maximum points in a group of at least two maximum points, and determining the signal phase of each flow direction of the vehicle flow in combination with the deviation value of the time to which each group of maximum points belongs; finally, graphically superimposing the Fourier series curves of different signal phases in the same signal control period, and obtaining the phase sequence and phase duration of each signal phase based on the time information to which the phase switching points of each Fourier series curve after superposition belong. The signal control scheme identification method proposed in the embodiment can comprehensively identify the signal control scheme, describe the signal control scheme in a more detailed and accurate manner, and further improve the recognition speed of the phase sequence and phase duration by automatically identifying the signal control time period division scheme.

[0134] Since the system / device described in the above embodiments of the present invention is a system / device used to implement the method of the above embodiments of the present invention, a person skilled in the art can understand the specific structure and deformation of the system / device based on the method described in the above embodiments of the present invention, and thus will not be described in detail here. All systems / devices used in the method of the above embodiments of the present invention belong to the scope of protection of the present invention.

[0135] It should be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0136] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions.

[0137] It should be noted that in the description of the present invention, the word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The present invention can be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. The use of the words first, second, third, etc., is only for convenience of expression and does not indicate any order. These words may be understood as part of the name of the component.

[0138] In addition, it should be noted that, in the description of this specification, the description of the terms "one embodiment", "some embodiments", "embodiment", "example", "specific example" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0139] Although preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments after obtaining the basic inventive concepts.

[0140] Obviously, those skilled in the art can make various modifications and variations to the present invention without departing from the spirit and scope of the invention.

Claims

1. A signal control scheme identification method based on vehicle passing data, characterized in that: include: The vehicle passing data acquired throughout the day is divided into time and flow direction aggregated to obtain vehicle passing data classified by vehicle flow direction; The vehicle passing data classified by vehicle flow direction is divided into several time periods according to the set time intervals; According to the preset multiple period values ​​and the autocorrelation coefficient calculation formula, the autocorrelation coefficient of the vehicle passing data in each period is obtained; When the autocorrelation coefficient is at its maximum value, the period value corresponding to the autocorrelation coefficient is the signal period data; According to the time series of vehicle passing data, the data of different signal cycles are grouped and processed in an orderly manner to obtain the division scheme of signal control periods; The vehicle passing data of each direction in each signal control period at each intersection is sorted by time to form a time series and curve fitting is performed to identify the maximum value points and corresponding time data of each fitting curve; By comparing the time data of the maximum value points of the fitting curves of different flow directions in the same period, the traffic flows of different flows with deviations less than the set threshold are classified as the same signal phase; Extracting curve data within the same signal period from fitting curves of different signal phases, and graphically superimposing the curve data to obtain a superimposed fitting curve; By identifying the maximum value points and corresponding time data of each curve data in the superimposed fitting curve, and according to the time sequence of the maximum value points, the phase sequence of each signal phase is determined; By identifying the intersection points and corresponding time data of each curve data in the superimposed fitting curve, and according to the difference between the intersection points and time, the phase duration of each signal phase is determined; The autocorrelation coefficient calculation formula is: ； In the formula, R (c) represents the autocorrelation coefficient when the period is c, T represents the time interval, c represents the period value, c =[1, T -1], Q t Representative t The total number of vehicles passing in seconds, represents the average number of vehicles passing during the entire time interval, Q t+c Representative t + c The total number of vehicles passing within a second.

2. The method according to claim 1, characterized in that The vehicle passing data acquired throughout the day is divided by time and aggregated by flow direction, and the vehicle passing data classified by traffic flow direction includes: Obtain the vehicle passing data on the road throughout the day, which includes vehicle information, intersection information, entrance information, lane information and passing time information; Divide the vehicle passing data into seconds to determine the vehicle passing data at the same entrance of the intersection within each second; The vehicle passing data of the same entrance and the same flow direction in continuous time are aggregated to obtain the vehicle passing data classified by vehicle flow direction.

3. The method according to claim 1, characterized in that According to the time series of the passing vehicle data, the different signal cycle data are grouped and processed in an orderly manner, and the division scheme of the signal control period is obtained, including: Clean the signal cycle data in each time interval to remove abnormal data; Conduct orderly cluster analysis on the signal cycle data after data cleaning, and group them according to the analysis results and the time series of vehicle passing data to obtain the division scheme of signal control period; The mode of the duration of the cycle value in the signal control period is obtained, and the cycle value corresponding to the mode is used as the optimal signal cycle data of the signal control period.

4. The method according to claim 1, characterized in that The vehicle data of each direction in each signal control period at each intersection is sorted by time to form a time series and curve fitting is performed to identify the maximum points of each fitting curve and the corresponding time data including: The vehicle passing data of each direction in each signal control period at each intersection is sorted by time to form a time series of the vehicle passing data; Based on the time series, Fourier series is used to perform curve fitting on the vehicle passing data of each direction in each signal control period at each intersection; Each fitting curve is smoothed, and the maximum points and corresponding time data in each fitting curve after processing are identified.

5. The method according to claim 1, characterized in that By comparing the time data of the maximum value points of the fitting curves of each flow direction in the same period, the traffic flows of different flows with deviations less than the set threshold are classified as the same signal phase, including: The maximum value points of the fitting curves of each flow direction within the same signal control period are grouped in a manner of at least two maximum value points as one group; The deviation value at the time corresponding to the maximum point in each group is compared with the set threshold, and based on the comparison result, it is determined whether the traffic corresponding to the maximum point in the group is in the same signal phase; If the deviation value at the time corresponding to the maximum point in the group is less than the set threshold, the traffic corresponding to the maximum point in the group is in the same signal phase; If the deviation value at the time corresponding to the maximum point in the group is greater than or equal to the set threshold, the traffic corresponding to the maximum point in the group is not in the same signal phase.

6. A signal control scheme identification system based on vehicle passing data, characterized in that: include: The vehicle passing data aggregation module is used to divide the acquired vehicle passing data for the whole day into time and flow direction, and obtain the vehicle passing data classified by vehicle flow direction; The signal control period identification module is used to divide the vehicle passing data classified by vehicle flow direction into several time periods according to the set time intervals; According to the preset multiple period values ​​and the autocorrelation coefficient calculation formula, the autocorrelation coefficient of the vehicle passing data in each period is obtained; When the autocorrelation coefficient is at its maximum value, the period value corresponding to the autocorrelation coefficient is the signal period data; According to the time series of the passing vehicle data, the data of different signal cycles are grouped and processed in an orderly manner to obtain the division scheme of the signal control period; the autocorrelation coefficient calculation formula is: ； In the formula, R (c) represents the autocorrelation coefficient when the period is c, T represents the time interval, c represents the period value, c =[1, T -1], Q t Representative t The total number of vehicles passing in seconds, represents the average number of vehicles passing during the entire time interval, Q t+c Representative t + c Total number of vehicles passing within a second; The curve fitting and identification module is used to sort the vehicle passing data of each direction in each signal control period at each intersection into a time series and perform curve fitting, and identify the maximum value points and corresponding time data of each fitting curve; The signal phase information identification module is used to classify the traffic flows of different directions with deviations less than a set threshold into the same signal phase by comparing the time data of the maximum points of the fitting curves of each flow direction in the same time period; intercept the curve data within the same signal period from the fitting curves of different signal phases, and graphically superimpose the curve data to obtain the superimposed fitting curve; determine the phase sequence of each signal phase by identifying the maximum points and corresponding time data of each curve data in the superimposed fitting curve, and according to the time sequence of the maximum points; determine the phase duration of each signal phase by identifying the intersection points and corresponding time data of each curve data in the superimposed fitting curve, and according to the difference between the intersection points and time.

7. An electronic device, characterized in that: include: processor; A memory storing steps for the processor to control a signal control scheme identification method based on vehicle passing data as described in any one of claims 1-5.

8. A computer-readable medium having computer-executable instructions stored thereon, characterized in that: When the executable instructions are executed by the processor, the steps of a signal control scheme identification method based on vehicle passing data as described in any one of claims 1 to 5 are implemented.

Images