Improved traffic conflict risk evaluation method and system based on ttc index and relative speed difference, storage medium and equipment

Abstract

The improved traffic conflict risk evaluation method and system based on TTC index and relative speed difference, a storage medium and equipment belong to the technical field of safety risk prediction of mountainous highway long tunnel. In order to solve the problems that the existing traffic conflict risk evaluation index cannot better quantify the degree of traffic conflict risk when the speed of the following vehicle is less than that of the leading vehicle and cannot better distinguish traffic conflicts under different distance and speed combinations, the present application reads multiple frames of data within one second in time sequence, determines that a conflict occurs according to the number of vehicle numbers appearing in the multiple frames if the number of vehicle numbers is greater than a vehicle number threshold, calculates traffic conflict indexes for each frame in which two vehicles exist at the same time, and evaluates by using traffic conflict indexes including TTC-IM index.

Description

Technical Field

[0001] This invention belongs to the field of safety risk prediction technology for extra-long tunnels on mountainous highways, specifically involving a traffic conflict risk assessment method, system, storage medium, and equipment. Background Technology

[0002] With the acceleration of urbanization, road traffic volume is increasing daily, and the incidence of traffic accidents is also rising. Among the many traffic accidents, conflict risk caused by driver error or complex traffic environments is one of the main reasons. In order to improve traffic safety and reduce the occurrence of traffic accidents, traffic conflict risk assessment has become an important direction in traffic safety research.

[0003] Traditional traffic conflict risk assessment methods primarily rely on single indicators, such as the Time to Collision (TTC) metric. This method assesses conflict risk by calculating the time required for a vehicle to travel from its current state to a potential collision point. However, single-indicator assessment methods have the following limitations: relying solely on the TTC metric cannot fully reflect the complexities of traffic conflicts, such as the influence of factors like driver reaction time, vehicle performance, and road conditions; and the TTC metric has poor adaptability to different traffic scenarios, making it difficult to accurately assess conflict risk under various complex conditions. Therefore, combining multiple indicators for traffic conflict assessment and proposing an improved traffic conflict risk assessment method based on the TTC metric and relative speed difference is highly significant. Summary of the Invention

[0004] The purpose of this invention is to solve the problems that existing traffic conflict risk assessment indicators cannot better quantify the degree of traffic conflict risk when the speed of the following vehicle is less than that of the vehicle in front, and cannot more precisely distinguish traffic conflicts under different distance and speed combinations.

[0005] An improved traffic conflict risk assessment method based on TTC index and relative speed difference includes the following steps:

[0006] First, obtain road video surveillance data, and then obtain traffic flow data based on the road video surveillance data;

[0007] Then, read multiple frames of data within one second in chronological order and store the vehicle numbers that appear in the multiple frames within this second. If the number of vehicle numbers is greater than the vehicle number threshold, it is determined that a conflict has occurred.

[0008] Based on the number of seconds since the conflict occurred, a traffic conflict index is calculated for each frame in which two vehicles coexist. The traffic conflict index includes the TTC-IM index.

[0009] The TTC-IM metrics are as follows:

[0010]

[0011] In the formula, x i-1 (t) represents the position of the preceding vehicle i-1 at time t; x i (t) represents the position of vehicle i after the current vehicle at time t; i-1 The length of the preceding vehicle i-1; Let be the speed of car i after time t; Let λ1 be the speed of vehicle i-1 ahead at time t; λ2 be the relative speed correction coefficient; λ3 be the vehicle length-to-distance ratio correction coefficient; and λ4 be the safety distance coefficient.

[0012] Finally, the risk of traffic conflict is evaluated based on traffic conflict indicators.

[0013] Furthermore, the road video surveillance data refers to video surveillance data from highways.

[0014] Furthermore, the threshold for the number of vehicles is set to 1.

[0015] Furthermore, the process of acquiring traffic flow data based on road video surveillance data is implemented using a neural network model.

[0016] An improved traffic conflict risk assessment system based on TTC indicators and relative speed difference includes:

[0017] Traffic flow data analysis module: Acquires road video surveillance data and obtains traffic flow data based on the road video surveillance data;

[0018] Traffic conflict preliminary identification module: Reads multiple frames of data within one second in chronological order, stores the vehicle numbers appearing in the multiple frames within this second, and determines that a conflict has occurred if the number of vehicle numbers is greater than the vehicle number threshold.

[0019] Traffic Conflict Index Calculation Module: Based on the number of seconds since the conflict occurred, the traffic conflict index is calculated for each frame in which two vehicles coexist. The traffic conflict index includes the TTC-IM index.

[0020] The TTC-IM metrics are as follows:

[0021]

[0022] In the formula, x i-1 (t) represents the position of the preceding vehicle i-1 at time t; x i (t) represents the position of vehicle i after the current vehicle at time t; i-1 The length of the preceding vehicle i-1; Let be the speed of car i after time t; Let λ be the speed of vehicle i-1 ahead at time t; λ1 is the relative speed correction coefficient; λ2 is the vehicle length-to-distance ratio correction coefficient; and λ3 is the safety distance coefficient.

[0023] Conflict risk assessment module: Evaluates traffic conflict risk based on traffic conflict indicators.

[0024] Furthermore, the road video surveillance data refers to video surveillance data from highways.

[0025] Furthermore, the threshold for the number of vehicles is set to 1.

[0026] Furthermore, the process of acquiring traffic flow data based on road video surveillance data is implemented using a neural network model.

[0027] A computer storage medium storing at least one instruction, the at least one instruction being loaded and executed by a processor, wherein the improved traffic conflict risk assessment system based on TTC index and relative speed difference is disclosed.

[0028] An improved traffic conflict risk assessment device based on TTC index and relative speed difference is disclosed. The device includes a processor and a memory. The memory stores at least one instruction, which is loaded and executed by the processor.

[0029] The beneficial effects of this invention are as follows:

[0030] This invention analyzes traffic conflict risk under different speed-distance combinations when the following vehicle's speed is less than the preceding vehicle's speed. It addresses the issue of negative TTC (Traffic Conflict Risk) indices when the following vehicle's speed is less than the preceding vehicle's speed, better quantifying the degree of traffic conflict risk in this specific situation. Furthermore, it can more finely differentiate traffic conflict risks under different distance and speed combinations, improving the accuracy of risk assessment. By effectively integrating the above two analytical methods, based on the TTC conflict assessment index and considering different speed-distance combinations, an improved traffic conflict risk assessment method is proposed. This method effectively quantifies the degree of traffic conflict risk when the following vehicle's speed is less than the preceding vehicle's speed and more finely distinguishes traffic conflicts under different distance-speed combinations, enhancing the comprehensiveness and systematic nature of the assessment method. This invention is particularly applicable to the field of safety risk prediction for extra-long tunnels on mountainous highways, helping to identify and warn of potential safety hazards in advance, reducing traffic accidents, ensuring driver safety, and improving the traffic safety management level of extra-long tunnels on mountainous highways. Attached Figure Description

[0031] Figure 1This is a flowchart of an improved traffic conflict risk assessment based on TTC indicators and relative speed difference.

[0032] Figure 2 The following are example diagrams of four vehicle models for the driving data used in this invention.

[0033] Figure 3 This is a chart for verifying the accuracy of TTC-IM.

[0034] Figure 4 This is a chart for verifying the accuracy of TTC.

[0035] Figure 5 This is a chart for verifying the accuracy of DRAC.

[0036] Figure 6 This is a readability test chart for TTC-IM.

[0037] Figure 7 This is a readability test chart for TTC.

[0038] Figure 8 This is a DRAC readability test chart. Detailed Implementation

[0039] Specific implementation method one: Combining Figure 1 This implementation method is described below.

[0040] This implementation method is an improved traffic conflict risk assessment method based on TTC indicators and relative speed difference, including the following steps:

[0041] Step 1: Utilizing the existing surveillance cameras deployed every 150m-500m and at the entrances and exits of the Guming Tunnel and Jiangmaoshan Tunnel on the Sannan Expressway (Xinliunan Section) in Guangxi Zhuang Autonomous Region, considering factors such as vehicle direction, speed, and field of vision requirements, as well as avoiding obstruction and shadows, the cameras are installed on the right-hand tunnel walls inside the expressway tunnels (both directions) and on the light poles in the central median strip at the tunnel entrances and exits to obtain the best field of vision and coverage. The video surveillance data already acquired is shown in Table 1.

[0042] Table 1 shows the video data that has been collected.

[0043]

[0044]

[0045] Step 2: Based on this, traffic flow data is obtained through video detection and image recognition technology based on YOLOv7, including the vehicle type, instantaneous speed, acceleration, displacement trajectory of each vehicle, as well as traffic volume, traffic composition, and average speed in each fixed time period (30s), providing a theoretical basis for subsequent traffic conflict analysis.

[0046] Examples of specific data types involved are as follows:

[0047] (1) Instantaneous speed of the vehicle (m / s)

[0048] The instantaneous speed of the vehicle is acquired in each frame. The data is then preliminarily processed to calculate the average speed and standard deviation per second. Taking vehicle number 2 as an example, its instantaneous speed within 1 second is shown in Table 2.

[0049] Table 2 Instantaneous speed data of vehicles

[0050]

[0051] (2) Instantaneous acceleration of the vehicle (m / s²) 2 )

[0052] The instantaneous acceleration of a vehicle is calculated from the instantaneous velocity of the vehicle in each frame. The instantaneous acceleration of a vehicle can be obtained from the instantaneous velocity of every 13 consecutive frames. Taking vehicle number 2 as an example, its acceleration is shown in Table 3.

[0053] Table 3 Instantaneous acceleration data of vehicles

[0054]

[0055] (3) Vehicle displacement (m)

[0056] The vehicle displacement is acquired frame by frame. The distance between the vehicle and the detection starting point is measured at each frame. Taking vehicle number 2 as an example, its displacement is shown in Table 4.

[0057] Table 4 Vehicle Displacement Data

[0058]

[0059] (4) Vehicle type

[0060] Vehicle types are divided into four categories: cars, buses, vans, and trucks. See the attached image for examples of specific vehicle types. Figure 2 Among them, (a) is a car, (b) is a bus, (c) is a van, and (d) is a truck.

[0061] (5) Traffic volume in 30 seconds (pcu)

[0062] Traffic volume is calculated every 30 seconds. The total traffic volume and the traffic volume of small and large vehicles in the 30 seconds prior to the current moment are calculated. The data from the 31st to the 42nd second are used as an example, as shown in Table 5.

[0063] Table 5 Traffic volume data in 30 seconds

[0064]

[0065]

[0066] (6) Average velocity over 30 seconds (m / s)

[0067] The average speed is calculated every 30 seconds. The total average speed of the previous 30 seconds and the average speed of small and large vehicles are calculated. The data from the 31st to the 42nd second are used as an example, as shown in Table 6.

[0068] Table 6. Average vehicle speed data in 30 seconds

[0069]

[0070] Step 3: Perform preliminary conflict identification on traffic flow data. Since the acquired data is 30 frames of instantaneous data within one second, while the required data is conflict data in seconds, the first step is to perform preliminary identification on the number of seconds in which conflicts occurred. The basic logic for filtering is to read 30 frames of data within one second in chronological order and store the vehicle numbers that appear in the 30 frames of this second. If the number of vehicle numbers is greater than 1, it is determined that a conflict has occurred. Taking the conflict data of the 4th second as an example, the data of some frames is shown in Table 7.

[0071] Table 7 Example of Conflict Data

[0072]

[0073]

[0074] Step 4: Based on the number of seconds of the conflict extracted above, calculate the traffic conflict index for each frame in which two vehicles are present at the same time, including the TTC value (Time to Collision) and the DRAC value (Deceleration Rate to Avoid the Crush).

[0075] TTC is the distance between two objects divided by their relative velocity. The calculation formula is shown in equation (1):

[0076]

[0077] In the formula, x i-1 (t)——The position of the preceding vehicle i-1 at time t, m; x i (t)——The position of the following vehicle i at time t, m; l i-1 —The length of the preceding vehicle i-1, in meters; —The speed of the vehicle i-1 at time t, in m / s; —The velocity of car i after time t, in m / s.

[0078] DRAC is the square of the velocity difference between two objects divided by twice the distance between them. The calculation formula is shown in equation (2):

[0079]

[0080] In the formula, x i-1 (t)——The position of the preceding vehicle i-1 at time t, m; x i (t)——The position of the following vehicle i at time t, m; l i-1 —The length of the preceding vehicle i-1, in meters; —The velocity of car i after time t, in m / s; —The speed of the vehicle i-1 at time t, in m / s.

[0081] The minimum TTC and maximum DRAC values ​​within one second are selected as representative values ​​for each traffic conflict index under that number of seconds. The conflict evaluation index values ​​at some conflict moments are used as examples, and the data examples are shown in Table 8.

[0082] Table 8 shows the values ​​of various conflict assessment indicators at different times of conflict.

[0083]

[0084]

[0085] Step 5: Improve the TTC indicator expression:

[0086] (1) Calculate the reciprocal of the original TTC index;

[0087] (2) Based on the improvement of TTC in (1), a relative speed component is introduced, with an exponential function as the base function and the difference between the speed of the following vehicle and the speed of the preceding vehicle as the independent variable. The specific expression is shown in equation (3):

[0088]

[0089] In the formula, —The speed of the vehicle i-1 at time t, in m / s; —The velocity of vehicle i after time t, in m / s; λ1—Relative velocity correction coefficient.

[0090] When the speed of the following vehicle is greater than the speed of the preceding vehicle, the relative speed component is greater than 0, and the value of formula (3) is greater than 1, increasing exponentially with the increase of relative speed. When the speed of the following vehicle is less than the speed of the preceding vehicle, the relative speed component is less than 1, decreasing with the increase of relative speed. The relative speed correction coefficient λ1 (0.2 in this embodiment) is used to correct the growth of the exponential function, in order to better measure the traffic conflict risk when the speed of the following vehicle is less than the speed of the preceding vehicle.

[0091] (3) Based on the improvement of TTC in (2), the vehicle length-distance ratio is introduced. The vehicle length-distance ratio uses an exponential function as the base function and the ratio of vehicle length to headway is the independent variable. The specific expression is shown in equation (4).

[0092]

[0093] In the formula x i-1 (t)——The position of the preceding vehicle i-1 at time t, m; x i (t)——The position of the following vehicle i at time t, m; l i-1 — Vehicle length of the preceding vehicle i-1, in meters; λ2 — Vehicle length to distance ratio correction factor; λ3 — Safety distance factor.

[0094] The ratio of vehicle length to headway must be less than or equal to 1. The smaller the headway, the closer the ratio is to 1, and the larger the corresponding exponential function value will be; conversely, the larger the headway, the smaller the ratio, and the smaller the corresponding exponential function value will be. The safety distance coefficient λ3 is the ratio of the average vehicle length of 5m to the recommended safety distance of 100m (the recommended safety distance at 100km / h), where λ3 = 0.05. The length-to-distance ratio correction coefficient λ2 (taken as 0.2 in this implementation) is used to correct the degree of growth of the exponential function, aiming to differentiate the risk of traffic conflicts under different distance-speed combinations.

[0095] (4) Substitute the relative speed part and the vehicle length-distance ratio part from (2) and (3) into the numerator of the improved TTC index in (1), and multiply the numerator by the speed of the following vehicle to obtain the comprehensive improved TTC-IM index. The specific expression of TTC-IM is shown in equation (5):

[0096]

[0097] In the formula x i-1 (t)——The position of the preceding vehicle i-1 at time t, m; x i (t)——The position of the following vehicle i at time t, m; l i-1 —The length of the preceding vehicle i-1, in meters; —The velocity of car i after time t, in m / s; —The speed of the vehicle i-1 at time t, in m / s; λ1—Relative speed correction coefficient; λ2—Vehicle length-to-distance ratio correction coefficient; λ3—Safety distance coefficient.

[0098] Step 6: Compare and verify the accuracy of the TTC-IM, TTC, and DRAC indicators to validate the advantages of the TTC-IM indicator as a traffic conflict assessment indicator in terms of accuracy, precision, and comprehensiveness. The verification data comes from the 1-hour (15:42:32-16:42:32) traffic conflict data of the high-risk section (K352+368) of the Jiangmaoshan Tunnel obtained through video surveillance in Step 2, and the second-sequence data of the TTC and DRAC indicators calculated in Step 4. The accuracy verification of TTC, DRAC, and TTC-IM is based on existing relevant traffic conflict research, using manual verification as the benchmark standard to evaluate the accuracy of the three conflict indicators in detecting traffic conflicts.

[0099] First, based on video detection data, the number of seconds since the traffic conflict occurred was manually selected, resulting in 209 conflict data points out of 3600 data points. The data was then divided into two equal parts according to time sequence: a training set (127 / 1800) for selecting the thresholds for TTC, DRAC, and TTC-IM, and a test set (82 / 1800) for verifying the accuracy of TTC, DRAC, and TTC-IM.

[0100] The corresponding TTC, DRAC, and TTC-IM values ​​are extracted from the training set and averaged, as shown in equations (6), (7), and (8).

[0101] TTC 平均 =2.778s (6)

[0102] DRAC 平均 =2.854m / s 2 (7)

[0103] TTC-IM 平均 =0.51s -1 (8)

[0104] The above values ​​were used as thresholds for traffic conflict analysis indicators of TTC, DRAC, and TTC-IM, respectively, and were tested in the test set.

[0105] (1) TTC test results

[0106] Based on the TTC's threshold, 70 data points below the threshold were selected, representing 70 detected traffic conflict seconds. These data were then manually verified via video. The verification revealed that 65 of the 70 data points were identified as traffic conflict events, 5 were false positives, and 16 traffic conflict data points went undetected. Therefore, the TTC Traffic Conflict Risk Index achieved an accuracy of 98.8% [(65+1713) / 1800*100%], a precision of 92.9% [65 / 70*100%], and a recall of 79.3% [65 / 82*100%]. The specific confusion matrix is ​​attached. Figure 3 .

[0107] (2) DRAC test results

[0108] Based on the TTC-IM thresholds, 66 data points exceeding the threshold were selected, and 66 traffic conflict seconds were detected. These data were then manually verified via video. The verification revealed that 60 of the 66 data points were identified as traffic conflict events, 6 were false positives, and 22 conflict data points went undetected. Therefore, the DRAC traffic conflict risk index achieved an accuracy of 98.4% [(60+1712) / 1800*100%], a precision of 90.9% [60 / 66*100%], and a recall of 73.1% [60 / 82*100%]. The specific confusion matrix is ​​attached. Figure 4 .

[0109] (3) TTC-IM test results

[0110] Based on the TTC-IM thresholds, 79 data points exceeding the threshold were selected, representing 79 detected traffic conflict seconds. These data were then manually verified via video. The verification revealed that 78 out of the 79 data points were identified as traffic conflict events, 1 was a false positive, and 4 traffic conflict data points went undetected. Therefore, the TTC-IM traffic conflict risk indicator achieved an accuracy rate of 99.7% [(78+1717) / 1800*100%], a precision rate of 98.7% [78 / 79*100%], and a recall rate of 95.1% [78 / 82*100%]. The specific confusion matrix is ​​attached. Figure 5 .

[0111] (4) Comprehensive comparative analysis

[0112] Table 9 shows a comparison of the accuracy, precision, and recall of the three conflict metrics:

[0113] Table 9 Comparison of Accuracy in Conflict Indicator Identification

[0114]

[0115] As shown in the table, TTC-IM has the highest accuracy, precision, and recall rate, all exceeding 95%, indicating that this traffic conflict analysis indicator is quite accurate.

[0116] Step 7: Conduct a readability comparison test on the TTC-IM, TTC, and DRAC indicators to verify the advantages of the TTC-IM indicator as a traffic conflict evaluation indicator in terms of accuracy, precision, and comprehensiveness. The test data comes from 209 traffic conflict data points within 1 hour (15:42:32-16:42:32) at the high-risk section (K352+368) of the Jiangmaoshan Tunnel obtained through video surveillance in Step 2. The readability test of TTC, DRAC, and TTC-IM is based on mathematical statistics principles, using the frequency histogram and probability distribution of the indicators as the benchmark evaluation criteria to assess the readability of the three conflict indicators in detecting traffic conflicts, and to test the continuity, uniformity, and readability of the three evaluation indicators. Statistical histogram analysis was performed on a portion of the 209 conflict data points detected, comparing TTC, DRAC, and TTC-IM. The TTC-IM frequency histogram is attached. Figure 6 TTC frequency histogram attached Figure 7 DRAC frequency histogram attached Figure 8 .

[0117] As shown in the figure, the TTC value is generally dispersed and has a relatively obvious risk level threshold. However, since it cannot estimate the situation where the speed of the following vehicle is less than the speed of the vehicle in front, it will miss some traffic conflict risk situations. Furthermore, because its threshold is relatively high, it is difficult to estimate the degree of change in conflict risk more sensitively.

[0118] DRAC exhibits an approximate Weibull distribution, indicating that it has a low risk sensitivity and is difficult to better estimate the degree of conflict risk among similar values. At the same time, compared with TTC, the thresholds for classifying each risk level are also difficult to determine with precise values.

[0119] TTC-IM exhibits an exponential distribution and compensates for the shortcomings of the two indicators mentioned above. For example, when the speed of the following vehicle is less than that of the vehicle in front, TTC-IM can accurately assess the degree of conflict risk. Furthermore, the TTC-IM values ​​are relatively evenly distributed, ensuring that moderate sensitivity can be obtained in more detailed micro-level traffic conflict analysis, thereby better classifying the degree of risk.

[0120] The above embodiments are merely one example and do not limit the scope of the invention. The data in the examples are only for reference in the specific application of the method of the invention and do not guarantee that the exemplified data is completely true and reasonable. It should be understood that the data calculations in the examples may result in slight differences in some results due to differences in the number of significant figures retained; since they are only for reference in the calculation process, the retention of significant figures in the original data and calculation results (including intermediate and final results) in the examples does not consider practical rationality. In actual applications, a reasonable number of significant figures should be retained according to the actual meaning and calculation accuracy requirements. The invention may also have other various embodiments. Without departing from the spirit and essence of the invention, those skilled in the art can make various corresponding changes and modifications according to the invention, but these corresponding changes and modifications should all fall within the protection scope of the appended claims. Specific Implementation Method Two:

[0122] This embodiment describes an improved traffic conflict risk assessment system based on TTC indicators and relative speed difference. It is essentially a program product or computer software corresponding to an improved traffic conflict risk assessment method based on TTC indicators and relative speed difference. Specifically, this improved traffic conflict risk assessment system based on TTC indicators and relative speed difference includes:

[0123] Traffic flow data analysis module: acquires road video surveillance data and obtains traffic flow data based on the road video surveillance data; furthermore, the road video surveillance data is video surveillance data of highways, and the process of obtaining traffic flow data based on the road video surveillance data is implemented using a neural network model.

[0124] Traffic conflict preliminary identification module: Reads multiple frames of data within one second in chronological order, stores the vehicle numbers appearing in the multiple frames within this second, and determines that a conflict has occurred if the number of vehicle numbers is greater than the vehicle number threshold; further, the vehicle number threshold is set to 1.

[0125] Traffic Conflict Index Calculation Module: Based on the number of seconds since the conflict occurred, the traffic conflict index is calculated for each frame in which two vehicles coexist. The traffic conflict index includes the TTC-IM index.

[0126] The TTC-IM metrics are as follows:

[0127]

[0128] In the formula, x i-1 (t) represents the position of the preceding vehicle i-1 at time t; x i (t) represents the position of vehicle i after the current vehicle at time t; i-1 The length of the preceding vehicle i-1; Let be the speed of car i after time t; Let λ be the speed of vehicle i-1 ahead at time t; λ1 is the relative speed correction coefficient; λ2 is the vehicle length-to-distance ratio correction coefficient; and λ3 is the safety distance coefficient.

[0129] Conflict risk assessment module: Evaluates traffic conflict risk based on traffic conflict indicators. Specific implementation method three:

[0131] This embodiment is a computer storage medium that stores at least one instruction, which is loaded and executed by a processor to provide an improved traffic conflict risk assessment system based on TTC index and relative speed difference.

[0132] It should be understood that the instructions include computer program products, software, or computerized methods corresponding to any method described in this invention; the instructions can be used to program computer systems or other electronic devices. Computer storage media may include readable media on which instructions are stored, and may include, but are not limited to, magnetic storage media, optical storage media; magneto-optical storage media include read-only memory (ROM), random access memory (RAM), erasable programmable memory (e.g., EPROM and EEPROM), and flash memory layers, or other types of media suitable for storing electronic instructions. Specific implementation method four:

[0134] This embodiment is an improved traffic conflict risk assessment device based on TTC index and relative speed difference. The device includes a processor and a memory. It should be understood that this includes any device including a processor and a memory described in this invention. The device may also include other units and modules that perform display, interaction, processing, control and other functions through signals or instructions.

[0135] The memory stores at least one instruction, which is loaded and executed by the processor to provide an improved traffic conflict risk assessment system based on TTC index and relative speed difference.

[0136] Those skilled in the art will understand that at least one stored instruction constitutes a computer program product corresponding to a method or system. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can 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. The solutions in the embodiments of this application can be implemented using various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0137] This application is described with reference to flowchart illustrations and / or block diagrams of methods, systems, and computer program products according to embodiments of this application, and can also be used with corresponding devices. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0138] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0139] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0140] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0141] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

[0142] The above examples of the present invention are merely illustrative of the computational model and process of the present invention, and are not intended to limit the implementation of the present invention. Those skilled in the art will recognize that other variations or modifications can be made based on the above description. It is impossible to exhaustively list all possible implementations here. Any obvious variations or modifications derived from the technical solutions of the present invention are still within the scope of protection of the present invention.

Claims

1. An improved traffic conflict risk assessment method based on TTC index and relative speed difference, characterized in that, Includes the following steps: First, obtain road video surveillance data, and then obtain traffic flow data based on the road video surveillance data; Then, read multiple frames of data within one second in chronological order and store the vehicle numbers that appear in the multiple frames within this second. If the number of vehicle numbers is greater than the vehicle number threshold, it is determined that a conflict has occurred. Based on the number of seconds since the conflict occurred, a traffic conflict index is calculated for each frame in which two vehicles coexist. The traffic conflict index includes the TTC-IM index. The TTC-IM metrics are as follows: In the formula, x i-1 (t) represents the position of the preceding vehicle i-1 at time t; x i (t) represents the position of vehicle i after the current vehicle at time t; i-1 The length of the preceding vehicle i-1; Let be the speed of car i after time t; Let λ1 be the speed of vehicle i-1 ahead at time t; λ2 be the relative speed correction coefficient; λ3 be the vehicle length-to-distance ratio correction coefficient; and λ4 be the safety distance coefficient. Finally, the risk of traffic conflict is evaluated based on traffic conflict indicators.

2. The improved traffic conflict risk assessment method based on TTC index and relative speed difference according to claim 1, characterized in that, The road video surveillance data refers to video surveillance data from highways.

3. The improved traffic conflict risk assessment method based on TTC index and relative speed difference according to claim 2, characterized in that, The threshold for the number of vehicles is set to 1.

4. An improved traffic conflict risk assessment method based on TTC index and relative speed difference according to any one of claims 1 to 3, characterized in that, The process of acquiring traffic flow data based on road video surveillance data is implemented using a neural network model.

5. An improved traffic conflict risk assessment system based on TTC index and relative speed difference, characterized in that, include: Traffic flow data analysis module: Acquires road video surveillance data and obtains traffic flow data based on the road video surveillance data; Traffic conflict preliminary identification module: Reads multiple frames of data within one second in chronological order, stores the vehicle numbers appearing in the multiple frames within this second, and determines that a conflict has occurred if the number of vehicle numbers is greater than the vehicle number threshold. Traffic Conflict Index Calculation Module: Based on the number of seconds since the conflict occurred, the traffic conflict index is calculated for each frame in which two vehicles coexist. The traffic conflict index includes the TTC-IM index. The TTC-IM metrics are as follows: In the formula, x i-1 (t) represents the position of the preceding vehicle i-1 at time t; x i (t) represents the position of vehicle i after the current vehicle at time t; i-1 The length of the preceding vehicle i-1; Let be the speed of car i after time t; Let λ1 be the speed of vehicle i-1 ahead at time t; λ2 be the relative speed correction coefficient; λ3 be the vehicle length-to-distance ratio correction coefficient; and λ4 be the safety distance coefficient. Conflict risk assessment module: Evaluates traffic conflict risk based on traffic conflict indicators.

6. An improved traffic conflict risk assessment system based on TTC index and relative speed difference according to claim 5, characterized in that, The road video surveillance data refers to video surveillance data from highways.

7. An improved traffic conflict risk assessment system based on TTC index and relative speed difference according to claim 6, characterized in that, The threshold for the number of vehicles is set to 1.

8. An improved traffic conflict risk assessment system based on TTC index and relative speed difference according to any one of claims 5 to 7, characterized in that, The process of acquiring traffic flow data based on road video surveillance data is implemented using a neural network model.

9. A computer storage medium, characterized in that, The storage medium stores at least one instruction, which is loaded and executed by a processor as described in any one of claims 5 to 8: an improved traffic conflict risk assessment system based on TTC index and relative speed difference.

10. An improved traffic conflict risk assessment device based on TTC index and relative speed difference, characterized in that, The device includes a processor and a memory, the memory storing at least one instruction, which is loaded and executed by the processor as described in any one of claims 5 to 8: an improved traffic conflict risk assessment system based on TTC index and relative speed difference.

Images