Intelligent driving safety auxiliary management method and system

Abstract

The invention is suitable for the field of driving safety management, and provides an intelligent driving safety auxiliary management method and system, and the system comprises a road condition data collection module, a traffic risk assessment module, a multi-perception risk identification module, a warning information transmission module, and a secondary state analysis module. According to the scheme, the driving track of the truck is predicted, and the view blind area of the truck in the driving track can be judged. Through the accurate identification, the system can better monitor the safety condition around the truck, especially potential risks in a view blind area, and matches the positions and behavior modes of other road participants. Through the coincidence detection function, the system can effectively identify the existence of other road participants in the view blind area of the truck and evaluate the potential collision risk. Through the method, the system can find possible collision danger in advance, early warning information is generated in time, and accidents are avoided.

Description

Technical Field

[0001] The present invention belongs to the field of driving safety management, and in particular relates to an intelligent driving safety auxiliary management method and system. Background Art

[0002] Intelligent driving safety management refers to a series of technical and management measures implemented in autonomous vehicles to ensure the safe operation of the vehicle in autonomous driving mode. These measures cover all aspects from technology development to practical application, ensuring that the system can operate stably and safely in various complex environments. Intelligent driving safety management aims to minimize the risks that autonomous vehicles may encounter during operation and ensure the safety of passengers and other road users. With the continuous advancement of technology and the improvement of regulations, the safety of intelligent driving will be further improved.

[0003] Currently in terms of driving safety, due to the large size of trucks, there are many blind spots in the field of vision, and the technological level of trucks is limited. They are not equipped with holographic images like most current vehicles. Therefore, when driving on complex roads, dangerous incidents may occur due to blind spots in the field of vision, especially at intersections, including pedestrians and non-motor vehicles occupying positions, and small cars illegally overtaking, etc., and the safety factor is extremely low. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent driving safety assistance management method and system, aiming to solve the technical problems existing in the prior art identified in the background technology.

[0005] The present invention is implemented as follows: an intelligent driving safety auxiliary management method, the method comprising:

[0006] Collect real-time traffic data in the intersection area, identify whether there are trucks at the intersection, and identify the vehicle location, traffic light status, and movement of other road participants;

[0007] According to the lane the truck is in, the status of its lights, speed data and the status of traffic lights at the intersection, the driving trajectory of the truck is predicted in real time, and the blind spots of the truck’s vision in the driving trajectory are determined;

[0008] Based on the truck's driving trajectory and real-time road dynamics, and matching the positions and behavior patterns of other road users, the predicted possible driving paths are checked for overlap. If there are other road users in the truck's blind spot, the risk of collision is identified.

[0009] Generate warning information for different road participants and use traffic lights and electronic display screens to warn other traffic participants;

[0010] Real-time traffic data at the intersection is collected again to determine whether a collision has occurred, and if so, an automatic alarm is issued.

[0011] As a further solution of the present invention, the identification of whether there is a truck vehicle at the current intersection, and the identification of the vehicle position, traffic light status, and movement of other road participants specifically includes:

[0012] Analyze the images collected by the intersection monitoring equipment, extract image features, and identify whether there is a truck type of vehicle;

[0013] Capture the status of traffic lights and lane markings at intersections in real time, and analyze the lanes and current positions of trucks and other road participants.

[0014] As a further solution of the present invention, the real-time prediction of the driving trajectory of the truck and the determination of the blind spot of the truck vision in the driving trajectory specifically include:

[0015] According to the lane the truck is in, the status of the traffic lights and the status of the truck lights, the driving intention of the truck is judged and the trajectory prediction result of the truck is obtained;

[0016] Analyze the collected images, identify the size of the truck, and combine the truck trajectory prediction results to determine the potential blind spots of the truck during driving. Specifically:

[0017] Front blind spot:

[0018] Left and right blind spots:

[0019] Rear Blind Distance = L v ;

[0020] Among them, W v Indicates the width of the truck, L v Indicates the length of the truck, FOV h Indicates the horizontal field of view of the camera, D r represents the distance from the front of the truck to the camera, and θ represents the depression angle between the camera cabin and the horizontal plane.

[0021] As a further solution of the present invention, the overlap detection of the predicted possible driving paths is performed, and if there are other road participants in the blind spot of the truck, the collision risk is identified, which specifically includes:

[0022] Identify and track the location and movement of road participants;

[0023] The prediction results of the trajectories of trucks and other road users are combined with the potential blind spots of the trucks during driving to assess the potential blind spot collision risks. Specifically:

[0024] Use the point-in-polygon detection algorithm to determine the current position P of the road participant B (t) Whether it is inside the blind spot polygon of the truck, so as to check the current position P of other road participants B B (t) Whether it is in the blind spot of truck A;

[0025] Calculate the relative distance d(t) between truck A and other road participants B at any given time t:

[0026]

[0027] Among them, (P A (t) x , P A (t) y ) represents the position coordinates of truck A at time t, (P B (t) x , P B (t) y ) represents the position coordinates of other road participant B at time t;

[0028] If P B (t) is in the blind spot, and the relative distance d(t) is less than or equal to the sum of the collision radii R of the truck A and other road participants B. A +R B , it means there is a collision event;

[0029]

[0030] Another object of the present invention is to provide an intelligent driving safety assistance management system, the system comprising:

[0031] The road condition data collection module is used to collect real-time traffic data in the intersection area, identify whether there are truck-type vehicles at the current intersection, and identify the vehicle location, traffic light status, and movement of other road participants;

[0032] Traffic risk assessment module, which is used to predict the driving trajectory of the truck in real time based on the lane the truck is in, the status of its lights, speed data and the status of traffic lights at the intersection, and to determine the blind spots of the truck's vision in the driving trajectory;

[0033] The multi-sensing risk identification module is used to detect overlaps with the predicted possible driving paths based on the truck's driving trajectory and real-time road dynamics, and to match the positions and behavior patterns of other road participants. If there are other road participants in the truck's blind spot, the collision risk is identified;

[0034] A warning information transmission module is used to generate warning information for different road participants and use traffic lights and electronic display screens to warn other traffic participants;

[0035] The secondary state analysis module is used to collect real-time traffic data at the intersection again to determine whether a collision has occurred. If so, an automatic alarm will be issued.

[0036] As a further solution of the present invention, the road condition data collection module includes:

[0037] The vehicle shape analysis unit is used to analyze the images collected by the intersection monitoring equipment, extract image features, and identify whether there is a truck type of vehicle;

[0038] The vehicle driving status judgment unit is used to capture the status of traffic lights and lane line markings at intersections in real time, and analyze the lanes and current positions of trucks and other road participants.

[0039] As a further solution of the present invention, the traffic risk assessment module includes:

[0040] A trajectory prediction unit is used to determine the driving intention of the truck according to the lane in which the truck is located, the state of the traffic light and the state of the truck lights, and obtain the trajectory prediction result of the truck;

[0041] The blind spot judgment unit is used to analyze the collected images, identify the size of the truck, and judge the potential blind spots of the truck during driving in combination with the prediction results of the truck's trajectory. Specifically:

[0042] Front blind spot:

[0043] Left and right blind spots:

[0044] Rear Blind Distance = L v ;

[0045] Among them, W v Indicates the width of the truck, L v Indicates the length of the truck, FOV h Indicates the horizontal field of view of the camera, D r represents the distance from the front of the truck to the camera, and θ represents the angle between the camera cabin and the horizontal plane.

[0046] As a further solution of the present invention, the multi-sensing risk identification module includes:

[0047] Object detection and tracking unit, used to identify and track the position and movement trajectory of road participants;

[0048] The blind spot collision risk assessment unit is used to integrate the trajectory prediction results of the truck and other road participants, and combine the potential blind spots of the truck during driving to assess the potential blind spot collision risk. Specifically:

[0049] Use the point-in-polygon detection algorithm to determine the current position P of the road participant B (t) Whether it is inside the blind spot polygon of the truck, so as to check the current position P of other road participants B B (t) Whether it is in the blind spot of truck A;

[0050] Calculate the relative distance d(t) between truck A and other road participants B at any given time t:

[0051]

[0052] Among them, (P A (t) x , P A (t) y ) represents the position coordinates of truck A at time t, (P B (t) x , P B (t) y ) represents the position coordinates of other road participant B at time t;

[0053] If P B (t) is in the blind spot, and the relative distance d(t) is less than or equal to the sum of the collision radii R of the truck A and other road participants B. A +R B , it means there is a collision event;

[0054]

[0055] The beneficial effects of the present invention are:

[0056] This solution not only predicts the driving trajectory of the truck, but also determines the blind spots of the truck during the driving trajectory. Through this precise identification, the system can better monitor the safety conditions around the truck, especially the potential risks in the blind spots, and match the positions and behavior patterns of other road participants. Through accurate analysis of the real-time positions and behavior patterns of other road participants, the system can dynamically adjust the prediction of the truck's driving path to ensure the accuracy and timeliness of the analysis results. Through the overlap detection function, the system can effectively identify the presence of other road participants in the truck's blind spots and assess the potential risk of collision. In this way, the system can detect possible collision hazards in advance, generate early warning information in a timely manner, and avoid accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 A flowchart of an intelligent driving safety assistance management method provided by an embodiment of the present invention;

[0058] Figure 2 A flowchart for identifying whether there is a truck-type vehicle at the current intersection, and identifying the vehicle position, traffic light status, and movement of other road participants provided by an embodiment of the present invention;

[0059] Figure 3 A flowchart of predicting the driving trajectory of a truck in real time and determining the blind spot of the truck's field of vision in the driving trajectory provided by an embodiment of the present invention;

[0060] Figure 4 A flowchart for performing overlap detection on predicted possible driving paths and identifying collision risks if there are other road participants in the blind spot of the truck provided by an embodiment of the present invention;

[0061] Figure 5 A structural block diagram of an intelligent driving safety assistance management system provided by an embodiment of the present invention;

[0062] Figure 6 A structural block diagram of a road condition data acquisition module provided in an embodiment of the present invention;

[0063] Figure 7 A structural block diagram of a traffic risk assessment module provided by an embodiment of the present invention;

[0064] Figure 8 This is a structural block diagram of a multi-sensing risk identification module provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0065] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0066] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script.

[0067] Figure 1 A flowchart of an intelligent driving safety assistance management method provided by an embodiment of the present invention is shown in FIG. Figure 1 As shown, the method includes:

[0068] S100, collects real-time traffic data in the intersection area, identifies whether there are truck-type vehicles at the current intersection, and identifies the vehicle location, traffic light status, and movement of other road participants;

[0069] This step captures real-time images of the intersection area and uses deep learning algorithms to identify and classify vehicles in the image, especially truck models. At the same time, the system also analyzes the vehicle's position, direction and speed in the image, as well as its relative position to other road participants. Image processing technology is used to identify the color and state of traffic lights (red, yellow, green), and edge detection and pattern recognition technology are used to accurately capture lane markings at intersections to ensure accurate judgment of the lanes in which trucks and other vehicles are located.

[0070] like Figure 2 As shown, the identification of whether there is a truck vehicle at the current intersection, and the identification of the vehicle position, traffic light status, and movement of other road participants specifically include:

[0071] S110, analyzing the image collected by the intersection monitoring device, extracting image features, and identifying whether there is a truck type of vehicle;

[0072] S120 captures the status of traffic lights and lane markings at intersections in real time, and analyzes the lanes and current positions of trucks and other road participants.

[0073] S200, based on the truck’s lane, headlight status, speed data and traffic light status at the intersection, predicts the truck’s driving trajectory in real time and determines the truck’s blind spot in the driving trajectory;

[0074] This step first determines the truck's driving intention, such as whether it is about to turn, change lanes or stop, by analyzing the lane the truck is in, the status of traffic lights, and the display of the truck's lights (such as turn signals and brake lights). At the same time, combined with the speed and acceleration data of the truck, the system can infer its driving intention in more detail to ensure the accuracy of the prediction. Subsequently, the system uses a machine learning model to combine historical data and current real-time traffic conditions to predict the possible trajectory of the truck under different driving intentions. Considering the size, weight and inertia of the truck, the system accurately predicts the driving trajectory of the truck. In addition, the system also conducts in-depth analysis of the collected images to identify the specific size and shape of the truck, and combines the previously predicted truck trajectory to determine the possible blind spots of the truck during driving. These blind spots include the blind spots in front of the truck, especially when turning or changing lanes; the blind spots on both sides of the truck, especially when merging or passing through narrow sections; and the blind spots behind the truck, especially when slowing down or stopping.

[0075] By comprehensively analyzing the truck's driving intention, predicted trajectory, and identified blind spots, the system can more accurately predict the truck's driving path and potential risks, thereby improving road traffic safety. The system uses advanced machine learning models and image analysis technology, which can adapt to complex and changing traffic environments, and significantly improve the intelligence level of intelligent driving safety assistance management. At the same time, the system has the ability to process real-time data and make rapid predictions, ensuring that it can respond quickly to traffic changes, issue warnings and make decisions in a timely manner, and effectively prevent traffic accidents. These advantages together ensure that the intelligent driving safety assistance management method can more effectively prevent and reduce traffic accidents in actual applications, thereby improving the overall safety and operating efficiency of road traffic.

[0076] like Figure 3 As shown, the real-time prediction of the driving trajectory of the truck and the determination of the blind spot of the truck vision in the driving trajectory specifically include:

[0077] S210, judging the driving intention of the truck according to the lane in which the truck is located, the state of the traffic light and the state of the truck lights, and obtaining a predicted trajectory result of the truck;

[0078] S210, analyzing the collected images, identifying the size of the truck, and combining the truck trajectory prediction result to determine the potential blind spots of the truck during driving. Specifically:

[0079] Front blind spot:

[0080] Left and right blind spots:

[0081] Rear Blind Distance = L v ;

[0082] Among them, W v Indicates the width of the truck, L v Indicates the length of the truck, FOV h Indicates the horizontal field of view of the camera, D r represents the distance from the front of the truck to the camera, and θ represents the depression angle between the camera cabin and the horizontal plane.

[0083] S300, based on the truck's driving trajectory and real-time road dynamics, and matching the positions and behavior patterns of other road users, performs overlap detection on the predicted possible driving paths, and identifies collision risks if there are other road users in the truck's blind spot.

[0084] In this step, all participants on the road are first identified and tracked, including but not limited to pedestrians, bicycles, motorcycles and other vehicles. The system uses high-precision sensors and advanced image recognition technology to capture and analyze the positions and movement trajectories of these participants in real time. Then, the system combines the trajectory prediction results of trucks and other road participants, as well as the possible blind spots of the truck during driving, to conduct a comprehensive collision risk assessment.

[0085] Specifically, the point-in-polygon detection algorithm is used to determine whether the current position of each road participant is within the blind spot polygons of the truck. This algorithm can accurately determine whether other road participants are in the truck's blind spot. At the same time, the system calculates the relative distance between the truck and other road participants at any given time, and further evaluates the collision risk based on the size of the truck and the collision radius of other participants. If a road participant is in the truck's blind spot and its relative distance to the truck is less than or equal to the sum of the collision radius of the two, the system will determine that there is a potential collision event.

[0086] By combining the truck's driving trajectory, blind spots, and the real-time location and behavior patterns of other road participants, potential traffic accidents can be effectively prevented. The system can process and analyze a large amount of traffic data in real time, quickly respond to dynamic changes on the road, and promptly detect and warn of potential collision risks, achieving comprehensive safety coverage of the entire traffic system. In addition, based on advanced algorithms and data analysis technology, the system provides intelligent decision support to help traffic managers more effectively dispatch traffic and manage safety, thereby providing efficient and accurate safety protection in complex traffic environments, significantly improving the safety and smoothness of road traffic.

[0087] like Figure 4 As shown, the predicted possible driving paths are overlapped with each other, and if there are other road participants in the blind spot of the truck, the collision risk is identified, specifically including:

[0088] S310, identifying and tracking the position and movement trajectory of road participants;

[0089] S330, based on the trajectory prediction results of the truck and other road users, and combined with the potential blind spots of the truck during driving, evaluates the potential blind spot collision risk. Specifically:

[0090] Use the point-in-polygon detection algorithm to determine the current position P of the road participant B (t) Whether it is inside the blind spot polygon of the truck, so as to check the current position P of other road participants B B (t) Whether it is in the blind spot of truck A;

[0091] Calculate the relative distance d(t) between truck A and other road participants B at any given time t:

[0092]

[0093] Among them, (P A (t) x , P A (t) y ) represents the position coordinates of truck A at time t, (P B (t) x , P B (t) y ) represents the position coordinates of other road participant B at time t;

[0094] If P B (t) is in the blind spot, and the relative distance d(t) is less than or equal to the sum of the collision radii R of the truck A and other road participants B. A +R B , it means there is a collision event;

[0095]

[0096] S400, generating warning information for different road participants, and using traffic lights and electronic display screens to warn other traffic participants;

[0097] This step generates warning messages for different road participants based on the identified collision risks. These warning messages are intended to promptly notify and alert pedestrians, cyclists, motorcyclists, and other vehicle drivers who may be affected. The system will customize the warning content and form based on the risk level and the affected objects to ensure effective communication and reception of the information.

[0098] Specifically, the system will issue warning information through multiple channels, including but not limited to the flashing changes of traffic lights, real-time updates of electronic display screens at intersections, voice prompts of on-board devices, push notifications of mobile phone applications, etc. For example, for pedestrians, the system may guide them to pay attention to safety through pedestrian lights and ground LED indicators at intersections; for bicycle and motorcycle riders, the system may issue sound or vibration warnings through their smart helmets or on-board devices; for other vehicle drivers, the system may remind them of potential collision risks through specific flashing patterns of traffic lights or warning prompts of the on-board navigation system.

[0099] S500, real-time traffic data of the intersection is collected again to determine whether a collision event occurs, and if so, an automatic alarm is issued.

[0100] This step will collect real-time traffic data at the intersection again to monitor and determine whether a collision has occurred. This step ensures real-time monitoring of traffic conditions at the intersection through continuous data collection and analysis. The system will pay special attention to the dynamics of the truck and other road users in its blind spot, as well as changes in the status of traffic lights, to accurately determine whether a collision has occurred.

[0101] Specifically, the system uses high-precision sensors and advanced image recognition technology to capture traffic conditions in the intersection area in real time. By comparing the differences between the previous and next data, the system can identify abnormal traffic behaviors, such as sudden stops, deviations from the planned trajectory, vehicle damage, etc., which may be indicators of a collision event. Once the system detects these abnormal behaviors and combines them with other evidence (such as sudden changes in the status of traffic lights, emergency avoidance behaviors of other road participants, etc.), the system will determine that a collision may have occurred.

[0102] Once a collision is detected, the system will automatically execute the alarm procedure and notify the relevant rescue and management departments to ensure timely handling of the accident and reduce the risk of secondary injuries.

[0103] Figure 5 A structural block diagram of an intelligent driving safety assistance management system provided by an embodiment of the present invention, such as Figure 5 As shown, the system comprises:

[0104] The road condition data collection module 100 is used to collect real-time traffic data in the intersection area, identify whether there are truck-type vehicles at the current intersection, and identify the vehicle position, traffic light status and movement of other road participants;

[0105] Traffic risk assessment module 200, used to predict the driving trajectory of the truck in real time based on the lane the truck is in, the status of its lights, speed data and the status of traffic lights at the intersection, and to determine the blind spots of the truck's vision in the driving trajectory;

[0106] The multi-sensing risk identification module 300 is used to detect the overlap of the predicted possible driving paths based on the driving trajectory of the truck and the real-time road dynamics, and to match the positions and behavior patterns of other road participants, and to identify the collision risk if there are other road participants in the blind spot of the truck;

[0107] The warning information transmission module 400 is used to generate warning information for different road participants and use traffic lights and electronic display screens to warn other traffic participants;

[0108] The secondary state analysis module 500 is used to collect the real-time traffic data of the intersection again, determine whether a collision event occurs, and execute automatic alarm if it occurs.

[0109] like Figure 6 As shown, the road condition data collection module includes:

[0110] The vehicle shape analysis unit 110 is used to analyze the image collected by the intersection monitoring device, extract image features, and identify whether there is a truck type of vehicle;

[0111] The vehicle driving state judgment unit 120 is used to capture the state of traffic lights and lane markings at intersections in real time, and analyze the lanes and current positions of trucks and other road participants.

[0112] like Figure 7 As shown, the traffic risk assessment module includes:

[0113] The trajectory prediction unit 210 is used to determine the driving intention of the truck according to the lane where the truck is located, the state of the traffic light and the state of the truck lights, and obtain the trajectory prediction result of the truck;

[0114] The blind spot judgment unit 220 is used to analyze the collected images, identify the size of the truck, and judge the potential blind spots of the truck during driving in combination with the prediction results of the truck's trajectory. Specifically:

[0115] Front blind spot:

[0116] Left and right blind spots:

[0117] Rear Blind Distance = L v ;

[0118] Among them, W v Indicates the width of the truck, L v Indicates the length of the truck, FOV h Indicates the horizontal field of view of the camera, D r represents the distance from the front of the truck to the camera, and θ represents the depression angle between the camera cabin and the horizontal plane.

[0119] like Figure 8 As shown, the multi-sensing risk identification module includes:

[0120] The target detection and tracking unit 310 is used to identify and track the position and movement trajectory of road participants;

[0121] The blind spot collision risk assessment unit 320 is used to assess the potential blind spot collision risk by integrating the trajectory prediction results of the truck and other road participants and combining the potential blind spots of the truck during driving. Specifically:

[0122] Use the point-in-polygon detection algorithm to determine the current position P of the road participant B(t) Whether it is inside the blind spot polygon of the truck, so as to check the current position P of other road participants B B (t) Whether it is in the blind spot of truck A;

[0123] Calculate the relative distance d(t) between truck A and other road participants B at any given time t:

[0124]

[0125] Among them, (P A (t) x , P A (t) y ) represents the position coordinates of truck A at time t, (P B (t) x , P B (t) y ) represents the position coordinates of other road participant B at time t;

[0126] If P B (t) is in the blind spot, and the relative distance d(t) is less than or equal to the sum of the collision radii R of the truck A and other road participants B. A +R B , it means there is a collision event;

[0127]

[0128] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0129] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0130] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0131] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0132] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent driving safety assistance management method, characterized in that: The method comprises: Collect real-time traffic data in the intersection area, identify whether there are trucks at the intersection, and identify the vehicle location, traffic light status, and movement of other road participants; According to the lane the truck is in, the status of its lights, speed data and the status of traffic lights at the intersection, the driving trajectory of the truck is predicted in real time, and the blind spots of the truck’s vision in the driving trajectory are determined; Based on the truck's driving trajectory and real-time road dynamics, and matching the positions and behavior patterns of other road users, the predicted possible driving paths are checked for overlap. If there are other road users in the truck's blind spot, the risk of collision is identified. Generate warning information for different road participants and use traffic lights and electronic display screens to warn other traffic participants; Real-time traffic data at the intersection is collected again to determine whether a collision has occurred, and if so, an automatic alarm is issued.

2. The method according to claim 1, characterized in that The identification of whether there is a truck vehicle at the current intersection, and the identification of the vehicle position, traffic light status, and movement of other road participants specifically includes: Analyze the images collected by the intersection monitoring equipment, extract image features, and identify whether there is a truck type of vehicle; Capture the status of traffic lights and lane markings at intersections in real time, and analyze the lanes and current positions of trucks and other road participants.

3. The method according to claim 2, characterized in that The real-time prediction of the driving trajectory of the truck and the determination of the blind spot of the truck vision in the driving trajectory specifically include: According to the lane the truck is in, the status of the traffic lights and the status of the truck lights, the driving intention of the truck is judged and the trajectory prediction result of the truck is obtained; Analyze the collected images, identify the size of the truck, and combine the truck trajectory prediction results to determine the potential blind spots of the truck during driving. Specifically: Front blind spot: Left and right blind spots: Rear Blind Distance = L v ; Among them, W v Indicates the width of the truck, L v Indicates the length of the truck, FOV h Indicates the horizontal field of view of the camera, D r represents the distance from the front of the truck to the camera, and θ represents the depression angle between the camera cabin and the horizontal plane.

4. The method according to claim 3, characterized in that The predicted possible driving paths are overlapped with each other, and if there are other road participants in the blind spot of the truck, the collision risk is identified, specifically including: Identify and track the location and movement of road participants; The prediction results of the trajectories of trucks and other road users are combined with the potential blind spots of the trucks during driving to assess the potential blind spot collision risks. Specifically: Use the point-in-polygon detection algorithm to determine the current position P of the road participant B (t) Whether it is inside the blind spot polygon of the truck, so as to check the current position P of other road participants B B (t) Whether it is in the blind spot of truck A; Calculate the relative distance d(t) between truck A and other road participants B at any given time t: Among them, (P A (t) x , P A (t) y ) represents the position coordinates of truck A at time t, (P B (t) x , P B (t) y ) represents the position coordinates of other road participant B at time t; If P B (t) is in the blind spot, and the relative distance d(t) is less than or equal to the sum of the collision radii R of the truck A and other road participants B. A +R B , it means there is a collision event; 5. An intelligent driving safety assistance management system, characterized in that: The system comprises: The road condition data collection module is used to collect real-time traffic data in the intersection area, identify whether there are truck-type vehicles at the current intersection, and identify the vehicle location, traffic light status, and movement of other road participants; Traffic risk assessment module, which is used to predict the driving trajectory of the truck in real time based on the lane the truck is in, the status of its lights, speed data and the status of traffic lights at the intersection, and to determine the blind spots of the truck's vision in the driving trajectory; The multi-sensing risk identification module is used to detect overlaps with the predicted possible driving paths based on the truck's driving trajectory and real-time road dynamics, and to match the positions and behavior patterns of other road participants. If there are other road participants in the truck's blind spot, the collision risk is identified; A warning information transmission module is used to generate warning information for different road participants and use traffic lights and electronic display screens to warn other traffic participants; The secondary state analysis module is used to collect real-time traffic data at the intersection again to determine whether a collision has occurred. If so, an automatic alarm will be issued.

6. The system according to claim 5, characterized in that The road condition data collection module comprises: The vehicle shape analysis unit is used to analyze the images collected by the intersection monitoring equipment, extract image features, and identify whether there is a truck type of vehicle; The vehicle driving status judgment unit is used to capture the status of traffic lights and lane line markings at intersections in real time, and analyze the lanes and current positions of trucks and other road participants.

7. The system according to claim 6, characterized in that The traffic risk assessment module includes: A trajectory prediction unit is used to determine the driving intention of the truck according to the lane in which the truck is located, the state of the traffic light and the state of the truck lights, and obtain the trajectory prediction result of the truck; The blind spot judgment unit is used to analyze the collected images, identify the size of the truck, and judge the potential blind spots of the truck during driving in combination with the prediction results of the truck's trajectory. Specifically: Front blind spot: Left and right blind spots: Rear Blind Distance = L v ; Among them, W v Indicates the width of the truck, L v Indicates the length of the truck, FOV h Indicates the horizontal field of view of the camera, D r represents the distance from the front of the truck to the camera, and θ represents the depression angle between the camera cabin and the horizontal plane.

8. The system according to claim 7, characterized in that The multi-sensing risk identification module includes: Object detection and tracking unit, used to identify and track the position and movement trajectory of road participants; The blind spot collision risk assessment unit is used to integrate the trajectory prediction results of the truck and other road participants, and combine the potential blind spots of the truck during driving to assess the potential blind spot collision risk. Specifically: Use the point-in-polygon detection algorithm to determine the current position P of the road participant B (t) Whether it is inside the blind spot polygon of the truck, so as to check the current position P of other road participants B B (t) Whether it is in the blind spot of truck A; Calculate the relative distance d(t) between truck A and other road participants B at any given time t: Among them, (P A (t) x , P A (t) y ) represents the position coordinates of truck A at time t, (P B (t) x , P B (t) y ) represents the position coordinates of other road participant B at time t; If P B (t) is in the blind spot, and the relative distance d(t) is less than or equal to the sum of the collision radii R of the truck A and other road participants B. A +R B , it means there is a collision event;

Images