Intelligent driving safety assistance management method and system

Abstract

The present invention is applicable to the field of driving safety management and provides an intelligent driving safety auxiliary management method and system, the system including: a road condition data acquisition module, a traffic risk assessment module, a multi-perception risk identification module, a warning information transmission module, and a secondary state analysis module. This solution not only predicts the driving trajectory of the truck, but also can determine the blind spots of the truck's vision 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 of vision, and match the positions and behavior patterns of other road participants. Through the overlap detection function, the system can effectively identify the presence of other road participants in the blind spots of the truck's vision and assess the potential collision risks. Through this method, the system can detect possible collision hazards in advance, generate early warning information in a timely manner, and avoid accidents.

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 safe operation in autonomous driving mode. These measures cover every stage from technology development to practical application, ensuring the system can operate stably and safely in a variety of 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, trucks are large in size and have many blind spots. In addition, trucks have limited technological capabilities and are not equipped with holographic images like most current vehicles. Therefore, when driving on complex roads, blind spots may lead to dangerous incidents, especially at intersections, where pedestrians and non-motor vehicles may seize space, and cars may illegally overtake. 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 existing technology 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 at intersections, identify whether there are trucks at the intersection, and identify vehicle locations, traffic light status, and the movement of other road users;

[0007] Based on the truck's lane, headlight status, speed data, and traffic light status at the intersection, the truck's driving trajectory is predicted in real time, and the truck's blind spots within the driving trajectory are determined;

[0008] Based on the truck's trajectory and real-time road dynamics, and matching the locations and behavior patterns of other road users, the system performs overlap detection on the predicted possible driving paths. If there are other road users in the truck's blind spot, the system identifies the risk of collision.

[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. 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 include:

[0012] Analyze the images collected by the intersection monitoring equipment, extract image features, and identify whether there are truck types;

[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 truck's visual blind spot within the driving trajectory specifically include:

[0015] Determine the truck's driving intention based on the truck's lane, traffic light status, and truck headlight status, and obtain the truck's trajectory prediction result;

[0016] Analyze the collected images, identify the truck's size, and combine the truck's trajectory prediction results to determine the truck's potential blind spots 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 angle between the camera chamber and the horizontal angle.

[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 users in the truck's blind spot, the collision risk is identified, specifically including:

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

[0023] The potential blind spot collision risk is assessed by combining the trajectory prediction results of the truck and other road users, combined with the potential blind spots of the truck during driving. 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 polygons 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 radius 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's location, traffic light status, and the movement of other road participants;

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

[0033] The multi-sensing risk identification module detects overlap with the predicted possible driving path based on the truck's driving trajectory and real-time road dynamics, and matches the location and behavior patterns of other road users. If other road users are in the truck's blind spot, collision risk is identified.

[0034] Warning information transmission module, 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 acquisition 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 vehicle;

[0038] The vehicle driving status judgment unit is used to 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.

[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 truck's driving intention based on the truck's lane, traffic light status, and truck headlight status, and obtain the truck's trajectory prediction result;

[0041] The blind spot judgment unit is used to analyze the collected images, identify the size of the truck, and combine the truck's trajectory prediction results to determine the potential blind spots of the truck during driving. 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 chamber and the horizontal angle.

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

[0047] Target 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 users, and 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 polygons 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 radius 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 truck's trajectory but also identifies any blind spots within the truck's path. This precise identification allows the system to better monitor the safety conditions surrounding the truck, particularly potential risks within the blind spot, and match the location and behavior patterns of other road users. By accurately analyzing the real-time location and behavior patterns of other road users, the system dynamically adjusts its prediction of the truck's path, ensuring the accuracy and timeliness of the analysis results. The overlap detection function allows the system to effectively identify the presence of other road users in the truck's blind spot and assess potential collision risks. This method enables the system to proactively detect potential collision hazards, generate timely warnings, and prevent 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 a truck is present at the current intersection, and identifying the vehicle's location, traffic light status, and movement of other road participants, provided by an embodiment of the present invention;

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

[0060] Figure 4 A flowchart of an embodiment of the present invention for detecting overlap of predicted possible driving paths and identifying collision risks if other road users are in the truck's blind spot.

[0061] Figure 5 This is 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 in an embodiment of the present invention;

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

[0065] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to 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 herein may be used 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, 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 without departing from the scope of this application.

[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 from the intersection area, identifies whether there are trucks at the current intersection, and identifies the vehicle's location, traffic light status, and movement of other road users;

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

[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 location, traffic light status, and movement of other road participants specifically include:

[0071] S110, analyzing the image collected by the intersection monitoring equipment, extracting image features, and identifying whether there is a truck type 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 users.

[0073] S200 predicts the truck's trajectory in real time based on the truck's lane, headlight status, speed data, and traffic light status at the intersection, and determines the truck's blind spots within the 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 truck's lane, traffic light status, and the truck's headlights (such as turn signals and brake lights). Furthermore, by combining the truck's speed and acceleration data, the system can more finely infer its driving intention, ensuring accurate predictions. The system then uses a machine learning model, combined with historical data and current real-time traffic conditions, to predict the truck's possible trajectories under different driving intentions. Taking into account the truck's size, weight, and inertia, the system accurately predicts the truck's trajectory. Furthermore, the system conducts in-depth analysis of the captured images to identify the truck's specific size and shape. Combined with previously predicted truck trajectories, it determines potential blind spots during the truck's travel. These blind spots include those in front of the truck, especially when turning or changing lanes; those on the sides of the truck, especially when merging or negotiating narrow roads; and those behind the truck, especially when slowing down or stopping.

[0075] By comprehensively analyzing a truck's driving intentions, predicted trajectories, and identified blind spots, the system can more accurately predict the truck's path and potential risks, thereby improving road traffic safety. The system utilizes advanced machine learning models and image analysis technology, enabling it to adapt to complex and changing traffic environments, significantly enhancing the intelligence level of intelligent driving safety assistance management. Furthermore, the system's real-time data processing and rapid prediction capabilities ensure rapid response to traffic changes, prompt warnings, and timely decision-making to effectively prevent traffic accidents. These advantages collectively ensure that this intelligent driving safety assistance management method can more effectively prevent and reduce traffic accidents in practical applications, thereby improving overall road traffic safety and operational efficiency.

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

[0077] S210, judging the driving intention of the truck based on the lane the truck is in, the state of the traffic light, and the state of the truck's lights, and obtaining a predicted trajectory result of the truck;

[0078] S210: Analyze the collected images, identify the size of the truck, and, based on the truck trajectory prediction results, 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 angle between the camera chamber and the horizontal angle.

[0083] S300, based on the truck's trajectory and real-time road dynamics, and matching the locations and behavior patterns of other road users, performs overlap detection on the predicted possible driving paths. If other road users are in the truck's blind spot, collision risk is identified.

[0084] In this step, all road users, including but not limited to pedestrians, cyclists, motorcycles, and other vehicles, are identified and tracked. Using high-precision sensors and advanced image recognition technology, the system captures and analyzes the positions and movements of these users in real time. The system then integrates the predicted trajectories of the truck and other road users, as well as any potential blind spots in the truck's field of view, to conduct a comprehensive collision risk assessment.

[0085] Specifically, a point-in-polygon detection algorithm is used to determine whether each road user's current position lies within the truck's blind spot polygons. This algorithm accurately determines whether other road users are within the truck's blind spot. The system also calculates the relative distances between the truck and other road users at any given moment, further assessing collision risk based on the truck's dimensions and the collision radius of the other road users. If a road user is within the truck's blind spot and their relative distance to the truck is less than or equal to the sum of their collision radii, the system determines a potential collision exists.

[0086] By integrating the truck's trajectory, blind spots, and the real-time location and behavior patterns of other road users, the system effectively prevents potential traffic accidents. The system processes and analyzes large amounts of traffic data in real time, rapidly responding to dynamic changes on the road and promptly detecting and warning of potential collision risks, achieving comprehensive safety coverage for the entire transportation system. Furthermore, based on advanced algorithms and data analysis technologies, the system provides intelligent decision-making support, helping traffic managers more effectively dispatch traffic and manage safety. This provides efficient and accurate safety assurance 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 and detected. If there are other road users in the truck's blind spot, the collision risk is identified, specifically including:

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

[0089] S330 integrates the trajectory prediction results of the truck and other road users, and considers the potential blind spots of the truck during driving to assess 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 polygons 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 radius 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 alerts tailored to different road users based on the identified collision risk. These alerts are intended to promptly notify and warn potentially affected pedestrians, cyclists, motorcyclists, and other drivers. The system customizes the content and format of these alerts based on the risk level and the affected parties, ensuring effective communication and reception.

[0098] Specifically, the system will issue warning information through various channels, including but not limited to the flashing changes of traffic lights, real-time updates of electronic display screens at intersections, voice prompts from on-board devices, push notifications from mobile 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 cyclists 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 alert them to potential collision risks through specific flashing patterns of traffic lights or warning prompts from 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 further collects real-time traffic data at the intersection to monitor and determine if a collision has occurred. This step ensures real-time monitoring of traffic conditions at the intersection through continuous data collection and analysis. The system pays special attention to the movements of the truck and other road users in its blind spot, as well as changes in traffic light status, to accurately determine if a collision has occurred.

[0101] Specifically, the system utilizes high-precision sensors and advanced image recognition technology to capture real-time traffic conditions at intersections. By comparing the previous and subsequent data, the system can identify unusual traffic behavior, such as sudden stops, deviations from the planned trajectory, and signs of vehicle damage, which could indicate a collision. Once the system detects these unusual behaviors, combined with other evidence (such as sudden changes in traffic light status and emergency evasive maneuvers by other road users), it determines 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 This is 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 includes:

[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's location, traffic light status, and the movement of other road participants;

[0105] Traffic risk assessment module 200, used to predict the truck's driving trajectory in real time based on the truck's lane, headlight status, speed data, and traffic light status at the intersection, and to determine the truck's blind spot within the driving trajectory;

[0106] The multi-sensing risk identification module 300 is used to detect overlap with the predicted possible driving path based on the truck's driving trajectory and real-time road dynamics, and to match the location and behavior patterns of other road users. If other road users are in the truck's blind spot, collision risk is identified;

[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 real-time traffic data of the intersection again, determine whether a collision event occurs, and automatically issue an alarm if a collision event occurs.

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

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

[0111] The vehicle driving state judgment unit 120 is used to 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.

[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 based on the lane the truck is in, the status of the traffic light and the status of the truck's lights, and obtain the truck's trajectory prediction result;

[0114] The blind spot determination unit 220 is used to analyze the collected images, identify the size of the truck, and determine the potential blind spots of the truck during driving based on the truck trajectory prediction results. 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 angle between the camera chamber and the horizontal angle.

[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 integrate the trajectory prediction results of the truck and other road users, and combine the potential blind spots of the truck during driving to assess the potential blind spot collision risk. 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 polygons 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 radius 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 the various steps in the flow chart of each embodiment of the present invention are shown in sequence according to the indication of the arrows, these steps are not necessarily performed in sequence according to the order indicated by the arrows. Unless otherwise specified herein, the execution of these steps is not strictly limited in order, 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 will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. 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 can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various 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-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned 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-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended 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 scope of protection of the present invention.

Claims

1. An intelligent driving safety assistance management method, characterized in that: The method comprises: Collect real-time traffic data at intersections, identify whether there are trucks at the intersection, and identify vehicle locations, traffic light status, and the movement of other road users; Based on the truck's lane, headlight status, speed data, and traffic light status at the intersection, the truck's driving trajectory is predicted in real time, and the truck's blind spots within the driving trajectory are determined; Based on the truck's trajectory and real-time road dynamics, and matching the locations and behavior patterns of other road users, the system performs overlap detection on the predicted possible driving paths. If there are other road users in the truck's blind spot, the system identifies the risk of collision. Generate warning information for different road participants and use traffic lights and electronic display screens to warn other traffic participants; Collect real-time traffic data at the intersection again to determine whether a collision has occurred, and automatically issue an alarm if one occurs; The overlap detection of the predicted possible driving paths is performed, and if there are other road users in the truck's blind spot, the collision risk is identified, specifically including: Identify and track the location and movement of road participants; The potential blind spot collision risk is assessed by combining the trajectory prediction results of the truck and other road users, combined with the potential blind spots of the truck during driving. Specifically: Use point-in-polygon detection to determine the current location of road users Is it inside the truck's blind spot polygons to check the current position of other road participants B? Whether it is in the blind spot of truck A; Calculate the truck A and other road participants B at any given moment The relative distance : ； in,( , ) indicates that at time At time , the location coordinates of truck A, ( , ) indicates that at time At time , the position coordinates of other road participant B; like In the blind spot of vision, and at a relatively close distance Less than or equal to the sum of the collision radius of truck A and other road participants B , it means there is a collision event; 。 2. The method according to claim 1, characterized in that The identification of whether there is a truck at the current intersection, and the identification of the vehicle's location, 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 are truck types; 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 truck's driving trajectory and the determination of the truck's blind spot within the driving trajectory specifically include: Determine the truck's driving intention based on the truck's lane, traffic light status, and truck headlight status, and obtain the truck's trajectory prediction result; Analyze the collected images, identify the truck's size, and combine the truck's trajectory prediction results to determine the truck's potential blind spots during driving. Specifically: Front blind spot: ; Left and right blind spots: ; Rear blind spot: ; in, Indicates the width of the truck. Indicates the length of the truck, Indicates the horizontal field of view of the camera. Indicates the distance from the front of the truck to the camera, Indicates the depression angle of the camera cabin and the horizontal angle.

4. 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's location, traffic light status, and the movement of other road participants; Traffic risk assessment module, used to predict the truck's driving trajectory in real time based on the truck's lane, headlight status, speed data and traffic light status at the intersection, and determine the truck's blind spots in the driving trajectory; The multi-sensing risk identification module detects overlap with the predicted possible driving path based on the truck's driving trajectory and real-time road dynamics, and matches the location and behavior patterns of other road users. If other road users are in the truck's blind spot, collision risk is identified. The 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 and automatically issue an alarm if one has occurred. The multi-sensing risk identification module includes: Target 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 users, and the potential blind spots of the truck during driving to assess the potential blind spot collision risk. Specifically: Use point-in-polygon detection to determine the current location of road users Is it inside the truck's blind spot polygons to check the current position of other road participants B? Whether it is in the blind spot of truck A; Calculate the truck A and other road participants B at any given moment The relative distance : ； in,( , ) indicates that at time At time , the location coordinates of truck A, ( , ) indicates that at time At time , the position coordinates of other road participant B; like In the blind spot of vision, and at a relatively close distance Less than or equal to the sum of the collision radius of truck A and other road participants B , it means there is a collision event; 。 5. The system according to claim 4, characterized in that The road condition data acquisition module includes: 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 vehicle; The vehicle driving status judgment unit is used to 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.

6. The system according to claim 5, characterized in that The traffic risk assessment module includes: A trajectory prediction unit is used to determine the truck's driving intention based on the truck's lane, traffic light status, and truck headlight status, and obtain the truck's trajectory prediction result; The blind spot judgment unit is used to analyze the collected images, identify the size of the truck, and combine the truck's 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 spot: ; in, Indicates the width of the truck. Indicates the length of the truck, Indicates the horizontal field of view of the camera. Indicates the distance from the front of the truck to the camera, Indicates the depression angle of the camera cabin and the horizontal angle.

Images