Data processing system of intelligent traffic monitoring system based on artificial intelligence

Abstract

The invention relates to the technical field of intelligent traffic monitoring, and discloses a data processing system of an intelligent traffic monitoring system based on artificial intelligence, comprising: collecting information of all waiting vehicles on a signal regulation and control intersection, the information comprising historical violation records and waiting positions; the driving risk rate of each waiting vehicle is predicted based on the information, dangerous vehicles and safe vehicles in different passing directions are identified according to the driving risk rates, the passing speed of the waiting vehicles at the signal regulation and control intersection is predicted, and the passing duration of the waiting vehicles passing through the signal regulation and control intersection is calculated according to the waiting positions; in a fixed signal period, the green light duration is dynamically regulated and controlled based on the distribution of dangerous vehicles going straight and turning left; according to the method, the risk of parallel driving of dangerous vehicles on adjacent lanes is reduced, the risk of parallel driving of dangerous vehicles on adjacent lanes is calculated, and traffic conflicts caused by the dangerous vehicles are reduced based on a set parallel risk threshold value and the dangerous vehicles which turn right.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent transportation monitoring, and particularly to a data processing system for an intelligent transportation monitoring system based on artificial intelligence. Background Art

[0002] At traffic signal intersections, dynamically adjusting the green light duration according to vehicle information can effectively improve traffic flow efficiency. By identifying the number and type of vehicles in different directions and lanes, the system can reasonably allocate the passing duration for each direction, ensuring that vehicles can pass through the intersection in the shortest time, reducing congestion and increasing the overall traffic flow.

[0003] There are multiple deficiencies in the existing technology for traffic signal regulation. Firstly, the allocation of the green light duration is usually based on a fixed cycle or simple vehicle counting, lacking in-depth analysis of vehicle risks, especially ignoring the special handling of dangerous vehicles. Secondly, the existing technology usually cannot distinguish between dangerous and safe vehicles in different passing directions, resulting in the mixed passing of dangerous and ordinary vehicles and increasing the likelihood of traffic accidents. In addition, in terms of the control of right-turning vehicles, the existing technology often cannot effectively identify the interference of right-turning vehicles on straight-going vehicles, especially when the right-turn lane and the straight-going lane run parallel, traffic conflicts are likely to occur. Finally, the existing technology cannot notify drivers in real time that they cannot pass through the signal intersection this time, resulting in hesitation or running through the red light of some vehicles at the intersection, further increasing the risk of traffic accidents.

[0004] The present invention proposes a data processing system for an intelligent transportation monitoring system based on artificial intelligence, which significantly improves the flexibility and safety of signal regulation by collecting vehicle historical information, evaluating driving risks, dynamically predicting the passing duration, and intelligently regulating the green light duration. Summary of the Invention

[0005] The present invention provides a data processing system for an intelligent transportation monitoring system based on artificial intelligence to help solve the problems mentioned in the above background art.

[0006] The present invention provides the following technical solution: A data processing system for an intelligent transportation monitoring system based on artificial intelligence,

[0007] A dynamic vehicle information collection module, which is used to collect information of all waiting vehicles at the signal regulation intersection, and the information includes historical violation records and waiting positions;

[0008] An intelligent risk classification module, which is used to predict the driving risk rate of each waiting vehicle based on the information, and identify dangerous and safe vehicles in different passing directions according to the driving risk rate;

[0009] The passing directions are straight, left turn, and right turn respectively;

[0010] The passing time prediction module is used to predict the passing speed of waiting vehicles at a signal-controlled intersection and calculate the passing time through the signal-controlled intersection according to the waiting position.

[0011] The green light duration dynamic regulation module is used to dynamically regulate the green light duration based on the distribution of dangerous vehicles in the straight and left-turn directions within a fixed signal cycle.

[0012] The right-turn traffic flow restriction control module is used to restrict dangerous vehicles turning right, reducing the risk of dangerous vehicles driving side by side in adjacent lanes, specifically including:

[0013] When the waiting vehicle going straight passes through the signal-controlled intersection, the waiting vehicle turning right and the waiting vehicle going straight drive in adjacent lanes.

[0014] Calculate the risk of dangerous vehicles driving side by side in adjacent lanes and restrict dangerous vehicles turning right based on a set side-by-side risk threshold.

[0015] Optionally, the dynamic vehicle information collection module is used to collect information on all waiting vehicles at the signal-controlled intersection, and the information includes historical violation records and waiting positions, including:

[0016] The signal-controlled intersection includes two main roads that intersect vertically, where each main road includes two branch roads with opposite driving directions.

[0017] Each branch road includes three roads, namely the left-turn road, the straight road, and the right-turn road.

[0018] Name the two main roads as main channel one and main channel two respectively.

[0019] Name the two branch roads of main channel one as sub-channel one and sub-channel two respectively, and name the two branch roads of main channel two as sub-channel three and sub-channel four respectively.

[0020] Set four groups of traffic lights at the signal-controlled intersection, corresponding to the four branch roads respectively. Each group of traffic lights includes a straight-ahead signal light and a left-turn signal light, which respectively control the straight-ahead and left-turn of waiting vehicles.

[0021] Optionally, the intelligent risk classification module is used to predict the driving risk rate of each waiting vehicle based on the information and identify dangerous vehicles and safe vehicles in different driving directions according to the driving risk rate, including:

[0022] Set roads for each driving direction. Specifically, the driving directions of left turn, straight ahead, and right turn respectively correspond to the left-turn road, the straight road, and the right-turn road of the branch road.

[0023] The historical violation record includes the historical violation time and violation type.

[0024] Calculate the driving risk rate of each waiting vehicle, specifically as follows:

[0025] Obtain the violation time of the i-th violation record of the waiting vehicle ;

[0026] Obtain the current time ;

[0027] Calculate the time decay weight of the i-th violation, where λ is the set time decay coefficient used to control the influence of the violation time on the currently calculated driving risk rate, and e is the exponential , where λ is the set time decay coefficient for controlling the impact of the violation time on the currently calculated driving risk rate, and e is the exponential;

[0028] Set weights for each violation type and obtain the weight corresponding to the violation type of the i-th violation record ;

[0029] Calculate the risk rate of the i-th violation record = , calculate the sum of the risk rates of all the violation records in the history of this waiting vehicle, and record the result as the driving risk rate of the waiting vehicle;

[0030] Set a risk rate threshold and compare the driving risk rate of the waiting vehicle with the risk rate threshold;

[0031] If the driving risk rate is less than the risk rate threshold, then this waiting vehicle is a safe vehicle;

[0032] If the driving risk rate is greater than or equal to the risk rate threshold, then this waiting vehicle is a dangerous vehicle.

[0033] Optionally, the passing duration prediction module is used to predict the passing speed of the waiting vehicle at the signal control intersection, and calculate the passing duration through the signal control intersection according to the waiting position, including:

[0034] For any waiting vehicle:

[0035] Obtain the historical passing speeds of the waiting vehicle passing through the signal control intersection, calculate the sum of all passing speeds, calculate the average value, and record the result as the average passing speed;

[0036] Determine that the passing speed of the waiting vehicle passing through the signal control intersection this time is the average passing speed;

[0037] Obtain the entrance position of the waiting vehicle passing through the signal control intersection, and calculate the passing distance from the waiting position of the waiting vehicle to the entrance position;

[0038] Calculate the passing distance divided by the passing speed this time, and record it as the passing duration;

[0039] Set a safety factor for increasing the passing duration of dangerous vehicles;

[0040] If the passing vehicle is a dangerous vehicle, calculate the passing duration. (1 + safety factor), and the result is used as the final passing duration.

[0041] Optionally, the green light duration dynamic regulation module is used to dynamically regulate the green light duration based on the distribution of dangerous vehicles in straight and left turns within a fixed signal cycle, including:

[0042] The fixed signal cycle is divided into four stages in chronological order;

[0043] The first stage is that sub-channel one and sub-channel two go straight simultaneously;

[0044] The second stage is that sub-channel one and sub-channel two turn left simultaneously;

[0045] The third stage is that sub-channel three and sub-channel four go straight simultaneously;

[0046] The fourth stage is that sub-channel three and sub-channel four turn left simultaneously;

[0047] Obtain the total green light duration H in the fixed signal cycle, calculate the total green light duration divided by 4, and record the result as the initial green light duration of each stage ;

[0048] Obtain the total number of dangerous vehicles in the j-th stage ;

[0049] Obtain the total number of dangerous vehicles R at the signal-regulated intersection;

[0050] Calculate the green light allocation coefficient for the j-th stage , ;

[0051] Set the adjustment coefficient , which is used to control the adjustment range of the green light duration;

[0052] Calculate the green light duration for the j-th stage , .

[0053] Optionally, the green light duration dynamic regulation module is used to dynamically regulate the green light duration based on the distribution of dangerous vehicles in straight and left turns within a fixed signal cycle, and further includes:

[0054] Update the green light duration of the j-th stage to ensure that the total green light duration in the fixed signal cycle remains unchanged;

[0055] The updated green light duration of the j-th stage is , ;

[0056] For any sub-channel in the j-th stage, obtain the passing time of each waiting vehicle on the sub-channel, and compare the passing time with the green light duration for comparison;

[0057] Obtain the waiting vehicle corresponding to the minimum passing time greater than the green light duration and denote it as the marked vehicle;

[0058] Notify the marked vehicle that it cannot pass through the signal-controlled intersection this time.

[0059] Optionally, calculating the risk of dangerous vehicles driving side by side in adjacent lanes and restricting the right-turning dangerous vehicles based on a set side-by-side risk threshold includes:

[0060] Establish a right-turn road relationship, specifically:

[0061] The right-turn lane of sub-channel two leads to the right-turn lane of sub-channel four, and the right-turn lane of sub-channel three leads to the right-turn lane of sub-channel two;

[0062] The right-turn lane of sub-channel one leads to the right-turn lane of sub-channel three, and the right-turn lane of sub-channel four leads to the right-turn lane of sub-channel one;

[0063] For the k-th stage of straight-ahead driving, obtain the green light duration of the k-th stage ;

[0064] Obtain the average passing speed of all waiting vehicles passing through the signal-controlled intersection, calculate the mean value, and denote the result as the standard passing speed ;

[0065] Obtain any sub-channel in the k-th stage and denote it as the target sub-channel;

[0066] Obtain the sub-channel in the right-turn road relationship that leads to the right-turn lane of the target sub-channel and denote it as the associated right-turn sub-channel.

[0067] Optionally, calculating the risk of dangerous vehicles driving side by side in adjacent lanes and restricting the right-turning dangerous vehicles based on a set side-by-side risk threshold further includes:

[0068] Calculate and denote the result as the right-turn distance;

[0069] Obtain the total number of dangerous vehicles turning right within the right-turn distance in the associated right-turn sub-channel and denote it as the right-turn total;

[0070] Obtain the total number of dangerous vehicles on the target sub-channel with a passing time less than the green light duration and denote it as the straight-ahead total;

[0071] Obtain the minimum value between the right-turn total and the straight-ahead total and denote it as the maximum number of side-by-side vehicles;

[0072] Calculate the maximum number of parallel vehicles / (total number of right turns + total number of straight runs), and record the result as the risk of dangerous vehicles driving in parallel on the associated right-turn sub-channel and the target sub-channel;

[0073] If the risk is greater than or equal to the parallel risk threshold, restrict the right-turning dangerous vehicles on the associated right-turn sub-channel, and the number of dangerous vehicles allowed to pass through at one time is the total number of right turns (1 - risk).

[0074] The present invention has the following beneficial effects:

[0075] 1. The data processing system of the intelligent transportation monitoring system based on artificial intelligence can construct an accurate vehicle information database by collecting information on various vehicles on two main roads and their branch roads, especially distinguishing different driving directions of left turns, straight runs, and right turns. By reasonably dividing sub-channels one to four and combining the traffic signal states on each channel, the specific driving directions of each waiting vehicle can be obtained, which helps the subsequent operation of the vehicle risk classification and passing duration prediction modules, and ensures real-time perception of the vehicle distribution on each lane within any fixed signal cycle.

[0076] 2. The data processing system of the intelligent transportation monitoring system based on artificial intelligence, through the intelligent risk classification module, accurately evaluates the driving risk rate of waiting vehicles based on their historical violation records. Considering both the violation time and violation type, by setting a time decay coefficient, it ensures that the impact of earlier violation records on the current risk assessment gradually weakens, thereby improving the timeliness of risk assessment. At the same time, by setting the weights of violation types, different types of violation behaviors have different influences in risk assessment. For example, serious violations have a greater impact, while minor violations have a smaller impact. It effectively distinguishes dangerous vehicles from safe vehicles and provides data support for subsequent green light duration regulation and parallel driving control.

[0077] 3. The data processing system of the intelligent transportation monitoring system based on artificial intelligence, through the passing duration prediction module, predicts the passing duration of waiting vehicles at signal-regulated intersections based on their historical passing speeds. In the calculation of the passing duration, the actual waiting positions of waiting vehicles are combined, which can ensure that the calculation of the passing duration conforms to the actual road conditions. For dangerous vehicles, a safety factor is set to increase their passing duration, ensuring that dangerous vehicles have sufficient reaction time when passing through the intersection. This not only improves the safety and passing efficiency of the overall traffic flow but also provides reliable data support for subsequent green light duration regulation.

[0078] 4. The data processing system of the intelligent transportation monitoring system based on artificial intelligence can ensure the basic passing time for each passing direction by dividing the fixed signal cycle into four phases and calculating the initial green light duration for each phase respectively. According to the number of dangerous vehicles in each phase, it dynamically adjusts the green light duration for each phase, so that the phases with more dangerous vehicles can obtain a longer green light time. This not only ensures the stability of the overall traffic flow but also reduces the traffic conflict risk of dangerous vehicles, significantly improving the safety and passing efficiency of the intersection.

[0079] 5. When the data processing system of the intelligent transportation monitoring system based on artificial intelligence detects that there are dangerous vehicles on both the right-turn lane and the straight-through lane at the same time, it calculates the parallel risk and determines whether to trigger the traffic restriction measure based on the set risk threshold. If the risk exceeds the threshold, it automatically restricts the right-turn vehicles to ensure that dangerous vehicles do not enter the intersection area simultaneously. This effectively reduces the traffic conflict risk that may be brought by the parallel driving of dangerous vehicles, and at the same time improves the passing efficiency through dynamic traffic restriction. It can dynamically notify and release vehicles in batches when there are too many vehicles in the right-turn lane, thus improving the passing safety and stability of the intersection.

[0080] 6. The data processing system of the intelligent transportation monitoring system based on artificial intelligence reminds the marked vehicles that cannot pass through the signal-controlled intersection this time, reducing the hesitation of drivers due to uncertainty about whether they can pass, thereby improving the passing efficiency and traffic safety. This not only ensures the stability of the overall traffic flow but also reduces the possible traffic conflict risk of dangerous vehicles, significantly improving the safety and passing efficiency of the intersection. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] Figure 1 It is a schematic diagram of the module functions of the present invention.

[0082] Figure 2 It is a schematic diagram of the signal-controlled intersection of the present invention.

[0083] Figure 3 It is a schematic diagram of three roads of Sub-channel 2 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0084] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0085] Embodiment 1. Refer to Figure 1 , a data processing system of an intelligent transportation monitoring system based on artificial intelligence, including:

[0086] The dynamic vehicle information collection module is used to collect information of all waiting vehicles at the signal-regulated intersection, and the information includes historical violation records and waiting positions.

[0087] The technical means for collecting information of all waiting vehicles at the signal-regulated intersection is: installing high-resolution cameras at the intersection and combining computer vision technology for vehicle detection and recognition.

[0088] Collection content: Obtain the license plate number through license plate recognition, and combine with the historical database to retrieve the historical violation records of the vehicle corresponding to the license plate.

[0089] Real-time identify the current position and queuing order of the vehicle at the intersection.

[0090] In this embodiment, referring to Figure 2 , at the signal-regulated intersection in the city, the intersection is two main roads that intersect vertically, namely Main Channel 1 and Main Channel 2, and each main road has two branch roads:

[0091] Main Channel 1 includes:

[0092] Sub-channel 1: From north to south, including a left-turn lane, a straight-through lane, and a right-turn lane.

[0093] Sub-channel 2: From south to north, in this embodiment, referring to Figure 3 , including a left-turn lane, a straight-through lane, and a right-turn lane.

[0094] Main Channel 2 includes:

[0095] Sub-channel 3: From east to west, including a left-turn lane, a straight-through lane, and a right-turn lane.

[0096] Sub-channel 4: From west to east, including a left-turn lane, a straight-through lane, and a right-turn lane.

[0097] Four groups of traffic lights are set at the signal-regulated intersection to control the straight-through and left-turn of each branch road respectively. The right-turn lane does not need to wait for the red light, and right-turn vehicles can pass freely, but they need to pay attention to the risk of parallel driving with straight-through vehicles.

[0098] The system real-time collects information of all waiting vehicles at the signal-regulated intersection. Taking 4 waiting vehicles as an example, including:

[0099] Vehicle A: In the left-turn lane of Sub-channel 1, with 3 historical violation records (1 speeding, 2 red-light running), and the waiting position is the 2nd.

[0100] Vehicle B: In the straight-through lane of Sub-channel 2, without violation records, and the waiting position is the 1st.

[0101] Vehicle C: In the right-turn lane of Sub-channel 3, with 1 speeding record, and the waiting position is the 3rd.

[0102] Vehicle D: In the straight lane of Sub-channel 4, there are 2 violation records (1 lane-changing violation and 1 speeding violation), and the waiting position is the 2nd.

[0103] Intelligent risk classification module, used to predict the driving risk rate of each waiting vehicle based on the information, and identify dangerous vehicles and safe vehicles in different traffic directions according to the driving risk rate;

[0104] The system predicts the driving risk rate of each waiting vehicle based on the vehicle's historical violation records:

[0105] Vehicle A:

[0106] Violation 1: Speeding, within 1 year, the violation weight is 0.6, the time decay is 0.8, and the risk rate = 0.6 × 0.8 = 0.48.

[0107] Violation 2: Running a red light, within 2 years, the violation weight is 0.9, the time decay is 0.6, and the risk rate = 0.9 × 0.6 = 0.54.

[0108] Violation 3: Running a red light, within 3 years, the violation weight is 0.9, the time decay is 0.5, and the risk rate = 0.9 × 0.5 = 0.45.

[0109] Total risk rate = 0.48 + 0.54 + 0.45 = 1.47 (higher than the set threshold of 1.0, marked as a dangerous vehicle).

[0110] Vehicle B: No violation records, total risk rate = 0 (marked as a safe vehicle).

[0111] Vehicle C:

[0112] Violation 1: Speeding, within 2 years, the violation weight is 0.6, the time decay is 0.6, and the risk rate = 0.6 × 0.6 = 0.36.

[0113] Total risk rate = 0.36 (lower than the threshold of 1.0, marked as a safe vehicle).

[0114] Vehicle D:

[0115] Violation 1: Lane-changing violation, within 1 year, the violation weight is 0.7, the time decay is 0.8, and the risk rate = 0.7 × 0.8 = 0.56.

[0116] Violation 2: Speeding, within 2 years, the violation weight is 0.6, the time decay is 0.6, and the risk rate = 0.6 × 0.6 = 0.36.

[0117] Total risk rate = 0.56 + 0.36 = 0.92 (lower than the threshold of 1.0, marked as a safe vehicle).

[0118] The traffic directions are straight, left turn, and right turn respectively;

[0119] The passing time prediction module is used to predict the passing speed of the waiting vehicles at the signal-regulated intersection and calculate the passing time through the signal-regulated intersection according to the waiting position;

[0120] Obtain the passing speed of the waiting vehicles at the signal-regulated intersection based on in-vehicle GPS data:

[0121] Principle: The waiting vehicles upload real-time position data through the in-vehicle GPS module or the vehicle networking terminal.

[0122] Implementation: Obtain the GPS positions of the vehicle at consecutive time points, calculate the position change amount and the time interval, and deduce the speed.

[0123] Vehicle A (left turn): The average passing speed is 20 km / h, the distance from the waiting position to the intersection is 40 meters, the passing time = 40 / (20×1000 / 3600) = 7.2 seconds (because it is a dangerous vehicle, the safety factor is 0.2), and the actual passing time = 7.2×1.2 = 8.64 seconds.

[0124] Vehicle B (straight): The average passing speed is 30 km / h, the waiting distance is 50 meters, and the passing time = 50 / (30×1000 / 3600) = 6 seconds.

[0125] Vehicle C (right turn): The average passing speed is 25 km / h, the waiting distance is 30 meters, and the passing time = 30 / (25×1000 / 3600) = 4.32 seconds.

[0126] Vehicle D (straight): The average passing speed is 30 km / h, the waiting distance is 60 meters, and the passing time = 60 / (30×1000 / 3600) = 7.2 seconds.

[0127] The green light duration dynamic regulation module is used to dynamically regulate the green light duration based on the distribution of dangerous vehicles in the straight and left turn directions within a fixed signal cycle;

[0128] Assume that the total signal cycle length H = 120 seconds, which is divided into four stages (the initial green light duration of each stage is 30 seconds):

[0129] The first stage: Straight in sub-channels one and two.

[0130] The second stage: Left turn in sub-channels one and two.

[0131] The third stage: Straight in sub-channels three and four.

[0132] The fourth stage: Left turn in sub-channels three and four.

[0133] Assume that the number of dangerous vehicles in each stage is respectively:

[0134] Phase 1: 10 vehicles;

[0135] Phase 2: 5 vehicles;

[0136] Phase 3: 15 vehicles;

[0137] Phase 4: 20 vehicles;

[0138] Total number of dangerous vehicles R = 10 + 5 + 15 + 20 = 50;

[0139] Calculate the distribution coefficient for each phase: First phase: 10 / 50 = 0.2.

[0140] Second phase: 5 / 50 = 0.1 second.

[0141] Third phase: 15 / 50 = 0.3 second.

[0142] Fourth phase: 20 / 50 = 0.4 second.

[0143] Assume the adjustment coefficient β = 0.5, then the green light duration for each phase is:

[0144] First phase: 33 seconds.

[0145] Second phase: 31.5 seconds.

[0146] Third phase: 34.5 seconds.

[0147] Fourth phase: 36 seconds.

[0148] Ensure that the total green light duration remains unchanged:

[0149] 33 + 31.5 + 34.5 + 36 = 135s;

[0150] The adjusted green light durations are respectively:

[0151] First phase: (33 / 135) × 120 = 29.33 seconds.

[0152] Second phase: (31.5 / 135) × 120 = 28 seconds.

[0153] Third phase: (34.5 / 135) × 120 = 30.67 seconds.

[0154] Fourth phase: (36 / 135) × 120 = 32 seconds.

[0155] Calculate the passing duration of all waiting vehicles in each direction, assuming the following:

[0156] Minimum passing duration in Phase 1: 28s;

[0157] Minimum passing time for Phase 2: 27 s;

[0158] Minimum passing time for Phase 3: 31 s;

[0159] Minimum passing time for Phase 4: 30 s;

[0160] For Phase 3: The passing time of 31 s > the green light time of 30.67 s. Mark the vehicle with a passing time of 31 s.

[0161] Notify the marked vehicle that it cannot pass through the signal-controlled intersection this time. Through the vehicle-mounted communication module (such as 4G / 5G communication or vehicle networking communication protocol), the system sends a "no passing" instruction to the in-vehicle terminal of the marked vehicle. The content of the instruction includes the specific time period and reason for not passing.

[0162] Reduce the hesitation of drivers due to uncertainty about whether they can pass, and the possibility of traffic accidents during signal conversion, improve traffic efficiency and traffic safety. It not only ensures the stability of the overall traffic flow, but also reduces the possible traffic conflict risks of dangerous vehicles, and significantly improves the safety and traffic efficiency of intersections.

[0163] The right-turn traffic restriction control module is used to restrict dangerous vehicles turning right and reduce the risk of dangerous vehicles driving side by side in adjacent lanes, specifically including:

[0164] When the waiting vehicle going straight passes through the signal-controlled intersection, the waiting vehicle turning right and the waiting vehicle going straight drive in adjacent lanes;

[0165] Calculate the risk of dangerous vehicles driving side by side in adjacent lanes, and restrict dangerous vehicles turning right based on the set side-by-side risk threshold.

[0166] Assume that in Phase 3 (Straight Sub-channels Three and Four):

[0167] The standard passing speed is 10 m / s. Here, the standard passing speed comes from all waiting vehicles, including all waiting vehicles turning left, going straight, and turning right. Since the signal-controlled intersection is where vehicles from all parties converge, it is considered that the passing speed of each waiting vehicle will affect other waiting vehicles and be affected by other waiting vehicles at the same time.

[0168] The target sub-channel is Sub-channel Three (going straight);

[0169] The associated right-turn sub-channel is Sub-channel One (turning right);

[0170] Calculate the right-turn distance: 30.67 × 10 = 306.7 m;

[0171] Obtain the information of dangerous vehicles turning right and going straight:

[0172] Total number of dangerous vehicles turning right within 306.7 meters on Sub-channel 1: 8 vehicles;

[0173] Total number of dangerous vehicles passing through Sub-channel 3 in less than 30.67 s: 12 vehicles;

[0174] Calculate the risk of parallel driving:

[0175] Minimum value of dangerous vehicles turning right and going straight: 8 vehicles;

[0176] Calculate the risk of parallel driving: 8 / 20 = 0.4;

[0177] Judge traffic restrictions:

[0178] Assume that the parallel risk threshold is 0.3, and the current risk is 0.4 > 0.3, triggering the traffic restriction strategy.

[0179] Restrict the dangerous vehicles turning right on the right-turn sub-channel (Sub-channel 1):

[0180] Number of dangerous vehicles allowed to pass through at a time: 8×(1 - 0.4) = 4.8, approximately equal to 4 vehicles;

[0181] That is, during this green light cycle, only 4 dangerous vehicles turning right on Sub-channel 1 are allowed to pass through.

[0182] In this embodiment, the system sends a notice to the restricted right-turn vehicles through the vehicle-mounted communication module (such as 4G / 5G communication or vehicle networking protocol), informing them that right-turning is temporarily prohibited.

[0183] Risk factors for parallel driving of dangerous vehicles are as follows:

[0184] I. Superposition of driving behavior risks:

[0185] Multiple dangerous vehicles running in parallel: Each dangerous vehicle has a higher accident risk, and these risks are superimposed on each other when running in parallel.

[0186] Increased probability of unsafe driving behaviors: Behaviors such as speeding, frequent lane changes, and cutting in are more common among dangerous vehicles, and parallel driving increases the probability of their mutual influence.

[0187] II. Mutual interference under limited space:

[0188] Limited lane space: Parallel driving leads to a reduction in the distance between vehicles, leaving less space for drivers to react and operate.

[0189] Lateral interference: When parallel dangerous vehicles attempt to change lanes, turn right, or accelerate through an intersection, lateral collisions are likely to occur.

[0190] III. Sudden risk propagation effect:

[0191] The loss of control of a dangerous vehicle can affect the vehicles running side by side: for example, sudden braking, skidding or accelerating, making it difficult for other dangerous vehicles to quickly avoid.

[0192] Visual occlusion: Running side by side will block the driver's line of sight. In particular, the vehicle turning right is very likely to be blocked by the adjacent vehicle going straight, resulting in accidents.

[0193] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device.

[0194] The above are only the preferred embodiments of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the technical principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A data processing system for an intelligent transportation monitoring system based on artificial intelligence, characterized in that, Including: A dynamic vehicle information collection module, which is used to collect information of all waiting vehicles at a signal-regulated intersection, and the information includes historical violation records and waiting positions; An intelligent risk classification module, which is used to predict the driving risk rate of each waiting vehicle based on the information, and identify dangerous vehicles and safe vehicles in different driving directions according to the driving risk rate; The driving directions are straight, left turn and right turn respectively; A passing duration prediction module, which is used to predict the passing speed of a waiting vehicle at a signal-regulated intersection, and calculate the passing duration through the signal-regulated intersection according to the waiting position; A green light duration dynamic regulation module, which is used to dynamically regulate the green light duration based on the distribution of dangerous vehicles in straight and left turns within a fixed signal cycle; A right-turn traffic flow restriction control module, which is used to restrict dangerous vehicles turning right and reduce the risk of dangerous vehicles driving side by side in adjacent lanes, specifically including: After the waiting vehicle going straight passes through the signal-regulated intersection, the waiting vehicle turning right and the waiting vehicle going straight drive in adjacent lanes; Calculate the risk of dangerous vehicles driving side by side in adjacent lanes, and restrict dangerous vehicles turning right based on a set side-by-side risk threshold.

2. The data processing system of the intelligent transportation monitoring system based on artificial intelligence according to claim 1, characterized in that, The dynamic vehicle information collection module, which is used to collect information of all waiting vehicles at a signal-regulated intersection, and the information includes historical violation records and waiting positions, includes: The signal-regulated intersection includes two main roads that intersect vertically, and each main road includes two branch roads with opposite driving directions; Each branch road includes three roads, namely a left-turn road, a straight road and a right-turn road; Name the two main roads as main channel one and main channel two respectively; Name the two branch roads of main channel one as sub-channel one and sub-channel two respectively, and name the two branch roads of main channel two as sub-channel three and sub-channel four respectively; Set four groups of traffic lights at the signal-regulated intersection, corresponding to the four branch roads respectively. Each group of traffic lights includes a straight-ahead signal light and a left-turn signal light, which respectively control the straight-ahead and left-turn of waiting vehicles.

3. The data processing system of the intelligent transportation monitoring system based on artificial intelligence according to claim 2, wherein The intelligent risk classification module, which is used to predict the driving risk rate of each waiting vehicle based on the information, and identify dangerous vehicles and safe vehicles in different driving directions according to the driving risk rate, includes: Set roads for each driving direction. Specifically, the driving directions of left turn, straight ahead and right turn respectively correspond to the left-turn road, straight road and right-turn road of the branch road; The historical violation record includes the historical violation time and violation type; Calculate the driving risk rate of each waiting vehicle, specifically: Obtain the violation time of the i-th violation record of the vehicle in transit ; Get the current time ; Calculate the time decay weight of the i-th violation , where λ is the set time decay coefficient used to control the impact of the violation time on the currently calculated driving risk rate, and e is the exponent; Set weights for each type of violation and obtain the weight corresponding to the type of violation in the i-th violation record ; Calculate the risk rate of the i-th violation record = , calculate the sum of the risk rates of all violation records in the history of the vehicle waiting to go, and record the result as the driving risk rate of the vehicle waiting to go; Set a risk rate threshold, and compare the driving risk rate of the waiting vehicle with the risk rate threshold; If the driving risk rate is less than the risk rate threshold, the waiting vehicle is a safe vehicle; If the driving risk rate is greater than or equal to the risk rate threshold, the waiting vehicle is a dangerous vehicle.

4. The data processing system of the intelligent transportation monitoring system based on artificial intelligence according to claim 3, characterized in that, The passing duration prediction module, which is used to predict the passing speed of a waiting vehicle at a signal-regulated intersection, and calculate the passing duration through the signal-regulated intersection according to the waiting position, includes: For any waiting vehicle: Obtain the historical passing speed of the waiting vehicle passing through the signal-regulated intersection, calculate the sum of all passing speeds, calculate the average value, and record the result as the average passing speed; It is determined that the passing speed of the vehicle waiting to pass through the signal-controlled intersection this time is the average passing speed; Obtain the entrance position of the vehicle waiting to pass through the signal-controlled intersection, and calculate the passing distance from the waiting position of the vehicle waiting to pass to the entrance position; Calculate the passing distance divided by the passing speed this time, and record it as the passing duration; Set a safety factor to increase the passing duration of dangerous vehicles; If the vehicle waiting to pass is a dangerous vehicle, calculate the passing time (1 + safety factor), and the result is used as the final passing time.

5. The data processing system of the intelligent transportation monitoring system based on artificial intelligence according to claim 2, wherein The green light duration dynamic regulation module is used to dynamically regulate the green light duration based on the distribution of dangerous vehicles going straight and turning left within a fixed signal cycle, including: The fixed signal cycle is divided into four stages in chronological order; The first stage is that sub-channel one and sub-channel two go straight simultaneously; The second stage is that sub-channel one and sub-channel two turn left simultaneously; The third stage is that sub-channel three and sub-channel four go straight simultaneously; The fourth stage is that sub-channel three and sub-channel four turn left simultaneously; Obtain the total green light duration H in a fixed signal cycle, calculate the total green light duration divided by 4, and record the result as the initial green light duration for each stage ; Obtain the total number of dangerous vehicles on two sub-channels in the j-th stage ; Obtain the total number R of dangerous vehicles at the signal-controlled intersection; Calculate the green light allocation coefficient for the j-th stage , ; Set the adjustment coefficient , which is used to control the adjustment range of the green light duration; Calculate the green light duration in the j-th stage , .

6. The data processing system of the intelligent transportation monitoring system based on artificial intelligence according to claim 5, characterized in that, The green light duration dynamic regulation module is used to dynamically regulate the green light duration based on the distribution of dangerous vehicles going straight and turning left within a fixed signal cycle, and further includes: Update the green light duration of the j-th stage to ensure that the total green light duration in the fixed signal cycle remains unchanged; The green light duration in the j-th stage after the update is , ; For any sub-channel in the j-th stage, obtain the passing time of each vehicle waiting to pass on the sub-channel, and compare the passing time with the green light duration for comparison; Obtain the waiting vehicles corresponding to the minimum passing duration greater than the green light duration and record them as marked vehicles; Notify the marked vehicle that it cannot pass through the signal-controlled intersection this time.

7. The data processing system of the intelligent transportation monitoring system based on artificial intelligence according to claim 1, characterized in that Calculate the risk of dangerous vehicles driving side by side in adjacent lanes, and restrict the right-turning dangerous vehicles based on the set side-by-side risk threshold, including: Establish a right-turn road relationship, specifically: The right-turn lane of sub-channel two leads to the right-turn lane of sub-channel four, and the right-turn lane of sub-channel three leads to the right-turn lane of sub-channel two; The right-turn lane of sub-channel one leads to the right-turn lane of sub-channel three, and the right-turn lane of sub-channel four leads to the right-turn lane of sub-channel one; For the k-th stage of going straight, obtain the green light duration of the k-th stage ; Obtain the average passing speed of all vehicles waiting to pass through the signal-regulated intersection, calculate the mean value, and record the result as the standard passing speed ; Obtain any sub-channel in the k-th stage, denoted as the target sub-channel; Obtain the sub-channel leading to the right-turn lane of the target sub-channel in the right-turn road relationship, denoted as the associated right-turn sub-channel.

8. The data processing system of the artificial intelligence-based intelligent transportation monitoring system according to claim 7, characterized in that, Calculate the risk of dangerous vehicles driving side by side in adjacent lanes, and restrict the right-turning dangerous vehicles based on the set side-by-side risk threshold, and further includes: Calculation , and the result is recorded as the right-turn distance; Obtain the total number of dangerous vehicles turning right within the right-turn distance from the signal-controlled intersection in the associated right-turn sub-channel, denoted as the total right-turn number; Obtain the total number of dangerous vehicles with a passing duration less than or equal to the green light duration on the target sub-channel, denoted as the total number of straight-through vehicles; ​ Obtain the minimum value between the total right-turn number and the total straight-through number, denoted as the maximum number of side-by-side vehicles; Calculate the maximum number of side-by-side vehicles / (total right-turn number + total straight-through number), and record the result as the risk of dangerous vehicles driving side by side on the associated right-turn sub-channel and the target sub-channel; If the risk is greater than or equal to the parallel risk threshold, dangerous vehicles turning right on the restricted right-turn sub-channel are restricted. The number of dangerous vehicles allowed to pass through at a time is the total number of right-turns (1 - risk).

Images