Collision early warning method and system

Abstract

The invention discloses a collision early warning method and system, and relates to the technical field of luggage tractor collision early warning, the system comprises a vehicle distance influence analysis module, a road congestion analysis module, a weather influence analysis module and a collision alarm module, the spacing distance between a luggage tractor and a nearest monitoring vehicle is obtained, the running speed of the monitoring vehicle is obtained, and the collision warning module is used for warning collision. Calculating a vehicle distance influence coefficient according to the driving speed; analyzing a pedestrian flow and a traffic flow of an area where the luggage tractor is located; calculating a road congestion coefficient of the area where the luggage tractor is located; searching a weather condition of a city where the luggage tractor is located, and analyzing a weather influence coefficient of the area where the luggage tractor is located by considering the weather condition; according to the method, the collision early-warning coefficient of the luggage tractor is comprehensively judged, when the collision early-warning coefficient reaches a set value of the system, the system gives a collision alarm to responsible personnel, the collision early-warning coefficient of the luggage tractor is judged by combining the vehicle distance influence coefficient, the road congestion coefficient and the weather influence coefficient, and therefore collision early-warning service is accurately provided.

Description

Technical Field

[0001] The present invention relates to the technical field of collision warning for baggage tractors, and specifically to a collision warning method and system. Background Art

[0002] With the prosperous development of the tourism industry and the diversification of people's lifestyles, people's demand for travel has gradually increased. With the increase in the number of civil aviation enterprises in China, the number of times people choose to travel and go on business trips by air has also gradually increased. With the development of safety technology and the increase in public safety awareness, the collision warning function has received increasing attention and has gradually become an important function considered for baggage tractors in airports.

[0003] Existing collision warning systems often use the method of vehicle distance monitoring to warn users, and cannot take into account the limitation of the towing vehicle speed on the towing vehicle distance. Especially when the towing vehicle speed is relatively fast, it is impossible to give users a timely and effective warning. On the one hand, with the continuous increase in the per capita vehicle occupancy rate and the rapid development of the tourism industry, the changes in the passenger flow and vehicle flow in airports are extremely large, and existing collision warning systems are difficult to comprehensively analyze the degree of road congestion. On the other hand, in poor weather conditions, such as heavy rain or foggy weather, users need a longer reaction time to take measures to respond to collision warnings, and existing collision warning systems are difficult to accurately consider the weather conditions to provide collision warnings for users.

[0004] Therefore, people need a collision warning method and system to solve the above problems. Summary of the Invention

[0005] The purpose of the present invention is to provide a collision warning method and system to solve the problems raised in the above background art.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: A collision warning method includes the following steps:

[0007] S1: Obtain the interval distance between the baggage tractor and the nearest monitored vehicle, obtain the driving speed of the monitored vehicle, and calculate the vehicle distance influence coefficient by comprehensively considering the driving speed of the baggage tractor;

[0008] S2: The system analyzes the passenger flow and vehicle flow in the area where the baggage tractor is located, and calculates the road congestion coefficient in the area where the baggage tractor is located;

[0009] S3: The system searches for the weather conditions in the city where the baggage tractor is located, and analyzes the weather influence coefficient in the area where the baggage tractor is located by considering the current weather conditions and the predicted weather conditions;

[0010] S4: The collision warning coefficient of the luggage tractor is determined by comprehensively considering the vehicle distance influence coefficient, the road congestion coefficient and the weather influence coefficient. When the collision warning coefficient reaches the maximum threshold of the collision warning coefficient, the system issues a collision alarm to the person in charge of the luggage tractor.

[0011] Furthermore, in step S1, at any airport, the system uses a deep learning target monitoring method to monitor vehicles within a circle with a radius of R and a center of the baggage tractor, and obtains the baggage tractor A through infrared ranging. 0 With monitoring vehicle A i The spacing distance B i , the system collects the speed of the baggage tractor as C 0 , obtain the driving speed C of the monitored vehicle through infrared speed measurement i , A i Indicates the i-th vehicle among the I vehicles monitored by the system, and calculates the vehicle distance influence coefficient D i :

[0012]

[0013] Among them B A Baggage tractor A 0 The safe distance between vehicles in the area, C A For vehicle A 0 The maximum allowed speed in the area, the safe distance between vehicles is confirmed by the airport tractor responsible person and stored in the system, K B is the influence weight of the real vehicle distance on the vehicle distance influence coefficient, K C is the influence weight of the speed difference between the baggage tractor and the monitoring vehicle on the vehicle distance influence coefficient. The actual vehicle distance is the distance between the baggage tractor and the monitoring vehicle. Substitute {i=1,2,…,I} one by one to calculate the vehicle distance influence coefficient {D 1 ,D 2 ,…,D I}, Infrared ranging has the advantages of non-contact and high precision, low cost and easy use;

[0014] Furthermore, in step S2, the system is connected to the remote sensing satellite through the Internet of Vehicles, and the number of vehicles in the circle with the baggage tractor as the center and r as the radius is collected as E A , the number of people in the circle is F A , analyze the road congestion coefficient G in the area where the baggage tractor is located A :

[0015]

[0016] Where K E is the weight of the impact of vehicle density on road congestion coefficient, KF Let \( \omega \) be the influence weight of population density on the road congestion coefficient. The electromagnetic wave bands used in remote sensing range from X-rays to microwaves, far beyond the visible light range, and can collect the number of people and vehicles in the area where the luggage tractor is located more accurately.

[0017] Furthermore, in step S3, the system obtains the weather conditions of the city where the luggage tractor is located through the network and calculates the current weather influence degree \( H \). A :

[0018] \( H \) A = \( K_1 \) a * \( a \) A + \( K_2 \) b * \( b \) A ;

[0019] where \( a \) A is the precipitation in the city where the current luggage tractor is located, \( b \) A is the visibility in the city where the current luggage tractor is located, \( K_1 \) a is the influence weight of precipitation on the weather influence degree, \( K_2 \) b is the influence weight of visibility on the weather influence degree. The predicted precipitation and predicted visibility after time \( t \) are collected through the network. Similarly, considering the predicted precipitation and predicted visibility after time \( t \), the predicted weather influence degree \( H_{t} \) after time \( t \) is calculated. A_t Considering the current weather influence degree and the predicted weather influence degree, the weather influence coefficient \( J \) of the area where the luggage tractor A is located is analyzed. 0 : A :

[0020]

[0021] Taking into account the difficulties brought by the current weather and future weather to the operation of the luggage tractor helps to improve the accuracy of collision warning.

[0022] Furthermore, in step S4, by comprehensively considering the vehicle distance influence coefficient, road congestion coefficient, and weather influence coefficient, the collision warning coefficient \( W \) of the \( i \)-th detected vehicle with respect to the luggage tractor A is analyzed. 0 : i :

[0023] \( W \) i = \( K_3 \) D * \( D \) i + \( K_4 \) G * \( G \) A + \( K_5 \) J * \( J \) A ;

[0024] where \( K_3 \) D is the set influence weight of the vehicle distance influence coefficient on the collision warning coefficient, \( K_4 \) JK is the influence weight of the set weather influence coefficient on the collision warning coefficient G is the influence weight of the road congestion coefficient to be calculated on the collision warning coefficient, and calculates the influence weight K of the road congestion coefficient on the collision warning coefficient G :

[0025]

[0026] Substitute one by one {i = 1, 2, …, I}, and calculate the collision warning coefficients {W 0 , W 1 , …, W 2 , …, W I} of the I monitored vehicles on the baggage tractor A. When there exists {i = 1, 2, …, I} such that W i ≥ W, the system issues a collision alarm to the user, where W is the maximum threshold of the collision warning coefficient set by the system

[0027] A collision warning system, the system includes: a vehicle distance influence analysis module, a road congestion analysis module, a weather influence analysis module and a collision alarm module

[0028] Obtain the interval distance between the baggage tractor and the nearest monitored vehicle through the vehicle distance influence analysis module, obtain the driving speed of the monitored vehicle, and calculate the vehicle distance influence coefficient by synthesizing the driving speed of the baggage tractor

[0029] Analyze the pedestrian flow and vehicle flow in the area where the baggage tractor is located through the road congestion analysis module, and calculate the road congestion coefficient in the area where the baggage tractor is located

[0030] Search for the weather conditions in the city where the baggage tractor is located through the weather influence analysis module, and analyze the weather influence coefficient in the area where the baggage tractor is located considering the current weather conditions and the predicted weather conditions

[0031] Judge the collision warning coefficient of the baggage tractor through the collision alarm module by synthesizing the vehicle distance influence coefficient, the road congestion coefficient and the weather influence coefficient. When the collision warning coefficient reaches the maximum threshold of the collision warning coefficient, the system issues a collision alarm to the user

[0032] Furthermore, the vehicle distance influence analysis module includes a deep learning camera and an infrared sensor. The nearest monitored vehicle to the baggage tractor is found through the deep learning camera, and the interval distance between the baggage tractor and the nearest monitored vehicle is obtained through the infrared sensor

[0033] Furthermore, the road congestion analysis module is connected to the remote sensing satellite through the vehicle network. After setting the monitoring range, the pedestrian flow and vehicle flow in the area where the baggage tractor is located are calculated, so as to calculate the road congestion coefficient in the area where the baggage tractor is located

[0034] Further, the weather impact analysis module searches for the weather conditions of the city where the baggage tractor is located through the network. The weather conditions include precipitation and visibility. The current weather conditions are analyzed by comprehensively considering the current precipitation and visibility, and the predicted weather conditions are analyzed by comprehensively considering the predicted precipitation and visibility. The weather impact coefficient of the area where the baggage tractor is located is calculated.

[0035] Further, the collision warning module includes a core processor. The core processor sets the maximum threshold of the collision warning coefficient. When the collision warning coefficient of the monitoring vehicle against the baggage tractor reaches the maximum threshold of the collision warning coefficient, the system issues a collision warning to the user.

[0036] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: on the one hand, the vehicle area near the baggage tractor is monitored in real time, and the vehicle distance impact coefficient is calculated by considering the speed of the tractor and the speed of the monitoring vehicle; on the other hand, the pedestrian flow and vehicle flow in the area where the baggage tractor is located are comprehensively analyzed, and the road congestion coefficient of the area where the baggage tractor is located is calculated; on the other hand, the system searches for the weather conditions of the city where the baggage tractor is located, analyzes the weather impact coefficient of the area where the baggage tractor is located by considering the current weather conditions and the predicted weather conditions, and judges the collision warning coefficient of the baggage tractor by comprehensively considering the vehicle distance impact coefficient, the road congestion coefficient and the weather impact coefficient, so as to provide a more accurate collision warning service for users. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention, and do not constitute a limitation to the present invention. In the drawings:

[0038] Figure 1 is a structural diagram of a collision warning system of the present invention;

[0039] Figure 2 is a flowchart of a collision warning method of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0040] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to 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 the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0041] Please refer to Figure 1 and Figure 2 , the present invention provides a technical solution: a collision warning method, including the following steps:

[0042] S1: Obtain the distance between the baggage tractor and the nearest monitoring vehicle, obtain the driving speed of the monitoring vehicle, and calculate the vehicle distance influence coefficient by synthesizing the driving speed of the baggage tractor;

[0043] S2: The system analyzes the pedestrian flow and vehicle flow in the area where the baggage tractor is located, and calculates the road congestion coefficient of the area where the baggage tractor is located;

[0044] S3: The system searches for the weather conditions in the city where the baggage tractor is located, and analyzes the weather influence coefficient of the area where the baggage tractor is located considering the current weather conditions and the predicted weather conditions;

[0045] S4: Synthesize the vehicle distance influence coefficient, the road congestion coefficient and the weather influence coefficient to judge the collision warning coefficient of the baggage tractor. When the collision warning coefficient reaches the maximum threshold of the collision warning coefficient, the system sends a collision alarm to the person in charge of the baggage tractor.

[0046] In step S1, in any airport, the system uses the deep learning target monitoring method to monitor the vehicles in the area of the circle with the position of the baggage tractor as the center and a radius of R. The distance B between the baggage tractor A 0 and the monitoring vehicle A i is obtained through infrared ranging. The system collects the driving speed of the baggage tractor as C i , and the driving speed C of the monitoring vehicle is obtained through infrared speed measurement 0 . A i represents the i-th vehicle among the I vehicles monitored by the system. Calculate the vehicle distance influence coefficient D i :

[0047]

[0048] where B A is the safe vehicle distance of the vehicles in the area where the baggage tractor A 0 is located, C A is the maximum allowable driving speed in the area where vehicle A 0 is located. The safe vehicle distance is confirmed by the person in charge of the airport tractor and stored in the system. K B is the influence weight of the actual vehicle distance on the vehicle distance influence coefficient, and K C is the influence weight of the speed difference between the baggage tractor and the monitoring vehicle on the vehicle distance influence coefficient. The actual vehicle distance is the distance between the baggage tractor and the monitoring vehicle. Substitute one by one {i = 1, 2,..., I} to calculate the vehicle distance influence coefficients {D 1 , D 2 ,..., D I} of the I monitored vehicles. Infrared ranging has the advantages of non-contact, high precision, low use cost and convenience;

[0049] ​Further, in step S2, the system connects to a remote sensing satellite through the vehicle networking, and collects the number of vehicles E in a circle with the baggage tractor as the center and a radius of r. A , and the number of people in the circle is F. A , and analyzes the road congestion coefficient G in the area where the baggage tractor is located. A :

[0050]

[0051] Where K E is the influence weight of vehicle density on the road congestion coefficient, and K F is the influence weight of population density on the road congestion coefficient. The electromagnetic wave band used in remote sensing ranges from X-rays to microwaves, far beyond the visible light range, and can collect the number of people and vehicles in the area where the baggage tractor is located more accurately.

[0052] In step S3, the system obtains the weather conditions of the city where the baggage tractor is located through the network, and calculates the current weather influence degree H A :

[0053] H A =K a *a A +K b *b A ;

[0054] Where a A is the precipitation in the city where the current baggage tractor is located, and b A is the visibility in the city where the current baggage tractor is located. Similarly, considering the predicted precipitation and predicted visibility after t time, the predicted weather influence degree H A_t is calculated, and the weather influence coefficient J in the area where the baggage tractor A 0 is located is analyzed considering the current weather influence degree and the predicted weather influence degree. A :

[0055]

[0056] Considering the difficulties brought by the current weather and future weather to the operation of the baggage tractor helps to improve the accuracy of collision warning.

[0057] Further, in step S4, by synthesizing the vehicle distance influence coefficient, road congestion coefficient, and weather influence coefficient, the collision warning coefficient W of the i-th detected vehicle with respect to the baggage tractor A 0 is analyzed. i :

[0058] W i =K D *D i +K G *GA +K J *J A ;

[0059] where K D is the influence weight of the set vehicle distance influence coefficient on the collision warning coefficient, and K J is the influence weight of the set weather influence coefficient on the collision warning coefficient, and K G is the influence weight of the road congestion coefficient to be calculated on the collision warning coefficient. Calculate the influence weight K of the road congestion coefficient on the collision warning coefficient G :

[0060]

[0061] Substitute one by one into {i = 1, 2,..., I}, and calculate the collision warning coefficients {W 0 of the I monitored vehicles with respect to the baggage tractor A 1 , W 2 ,..., W I}. When there exists {i = 1, 2,..., I} such that W i ≥ W, the system issues a collision alarm to the user, where W is the maximum threshold of the collision warning coefficient set by the system.

[0062] A collision warning system, the system includes: a vehicle distance influence analysis module, a road congestion analysis module, a weather influence analysis module, and a collision alarm module;

[0063] Obtain the interval distance between the baggage tractor and the nearest monitored vehicle through the vehicle distance influence analysis module, obtain the driving speed of the monitored vehicle, and calculate the vehicle distance influence coefficient by integrating the driving speed of the baggage tractor;

[0064] Analyze the pedestrian flow and vehicle flow in the area where the baggage tractor is located through the road congestion analysis module, and calculate the road congestion coefficient in the area where the baggage tractor is located;

[0065] Search for the weather conditions in the city where the baggage tractor is located through the weather influence analysis module, and analyze the weather influence coefficient in the area where the baggage tractor is located considering the current weather conditions and the predicted weather conditions;

[0066] Judge the collision warning coefficient of the baggage tractor by integrating the vehicle distance influence coefficient, the road congestion coefficient, and the weather influence coefficient through the collision alarm module. When the collision warning coefficient reaches the maximum threshold of the collision warning coefficient, the system issues a collision alarm to the user.

[0067] The vehicle distance influence analysis module includes a deep learning camera and an infrared sensor. The nearest monitored vehicle to the baggage tractor is found through the deep learning camera, and the interval distance between the baggage tractor and the nearest monitored vehicle is obtained through the infrared sensor.

[0068] The road congestion analysis module is connected to a remote sensing satellite through the vehicle network. After setting the monitoring range, it calculates the pedestrian flow and vehicle flow in the area where the baggage tractor is located, and thus calculates the road congestion coefficient in the area where the baggage tractor is located.

[0069] The weather impact analysis module searches for the weather conditions in the city where the baggage tractor is located through the network. The weather conditions include precipitation and visibility. It comprehensively considers the current precipitation and visibility to analyze the current weather conditions, and comprehensively considers the predicted precipitation and visibility to analyze the predicted weather conditions, and calculates the weather impact coefficient in the area where the baggage tractor is located.

[0070] The collision alarm module includes a core processor. The core processor sets the maximum threshold of the collision warning coefficient. When the collision warning coefficient of a monitored vehicle against the baggage tractor reaches the maximum threshold of the collision warning coefficient, the system issues a collision alarm to the user.

[0071] Example 1: The system uses the deep learning target monitoring method to monitor the vehicles in a circle with a radius of 0.5 centered on the baggage tractor. The distance B between the baggage tractor A 0 and the monitored vehicle A 1 is 0.2. The system collects the driving speed of the baggage tractor as C 1 which is 80, and obtains the driving speed C of the monitored vehicle through infrared speed measurement 0 which is 85. A i represents the i-th vehicle among the I vehicles monitored by the system. Calculate the vehicle distance impact coefficient D i : 1 :

[0072]

[0073] where B A is the safe vehicle distance of the vehicle in the area where the baggage tractor A 0 is located, and the query is 0.2. C A is the maximum allowable driving speed in the area where vehicle A 0 is located, and the query is 80. The safe vehicle distance is confirmed by the responsible person of the airport tractor and stored in the system. K B is the influence weight of the actual vehicle distance on the vehicle distance impact coefficient, which is set to 0.8. K C is the influence weight of the speed difference between the baggage tractor and the monitored vehicle on the vehicle distance impact coefficient, which is set to 0.2. The actual vehicle distance is the distance between the baggage tractor and the monitored vehicle. Substitute one by one {i = 1, 2,..., I} to calculate the vehicle distance impact coefficients {D 1 , D 2 , …, D 20, infrared ranging has the advantages of non-contact, high precision, low usage cost and convenience;

[0074] The system is connected to remote sensing satellites through the vehicle network, and collects the number of vehicles E within a circle with the baggage tractor as the center and a radius of 0.5 A is 10, and the number of people F A is 10, and analyzes the road congestion coefficient G in the area where the baggage tractor is located A :

[0075]

[0076] where K E is the influence weight of vehicle density on the road congestion coefficient, set to 0.6, K F is the influence weight of population density on the road congestion coefficient, set to 0.4. The electromagnetic wave band used in remote sensing ranges from X-rays to microwaves, far beyond the visible light range, and can collect the number of people and vehicles in the area where the baggage tractor is located more accurately.

[0077] The system obtains the weather conditions of the city where the baggage tractor is located through the network, and calculates the current weather influence degree H A :

[0078] H A = 0.4 * 0 + 0.6 * 40 = 24;

[0079] where a A is the precipitation in the city where the current baggage tractor is located, and the weather precipitation collected through the network is 0, b A is the visibility in the city where the current baggage tractor is located, and the visibility collected through the network is 40, K b is the influence weight of visibility on the weather influence degree, set to 0.6. Similarly, considering the predicted weather conditions after 1 time, the predicted weather influence degree H after t = 1 time is calculated A_1 = 16. Considering the current weather influence degree and the predicted weather influence degree, analyze the weather influence coefficient J in the area where the baggage tractor A 0 is located A :

[0080]

[0081] Considering the difficulties brought by the current weather and future weather to the operation of the baggage tractor, it helps to improve the accuracy of collision warning.

[0082] Combining the vehicle distance influence coefficient, road congestion coefficient and weather influence coefficient, analyze the collision warning coefficient W of the first detected vehicle on the baggage tractor A 0 i : ​

[0083] W i = K D * D i + K G * G A + K J * J A ;

[0084] Where K D is the influence weight of the set vehicle distance influence coefficient on the collision warning coefficient, set to 0.9, K J is the influence weight of the set weather influence coefficient on the collision warning coefficient, set to 0.1, K G is the influence weight of the road congestion coefficient to be calculated on the collision warning coefficient, calculate the influence weight K of the road congestion coefficient on the collision warning coefficient G :

[0085]

[0086] Substitute K G Calculate W i = 17.3, substitute one by one into {i = 1, 2,..., I}, calculate the collision warning coefficients {W 0 , W 1 ,..., W 2 ,..., W 20} of the 20 monitored vehicles for the baggage tractor A i When there exists {i = 1, 2,..., I} such that W

[0087] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present invention. Any reference signs in the claims should not be regarded as limiting the claimed rights involved.

Claims

1. A collision warning method, characterized in that: The following steps are involved: S1: Obtain the distance between the baggage tractor and the nearest monitoring vehicle, obtain the driving speed of the monitoring vehicle, and calculate the vehicle distance influence coefficient based on the driving speed of the baggage tractor; S2: The system analyzes the flow of people and vehicles in the area where the baggage tractor is located, and calculates the road congestion coefficient in the area where the baggage tractor is located; S3: The system searches for weather conditions in the city where the baggage tractor is located, and analyzes the weather impact coefficient of the area where the baggage tractor is located by considering the current weather conditions and the predicted weather conditions; S4: The collision warning coefficient of the luggage tractor is determined by comprehensively considering the vehicle distance influence coefficient, road congestion coefficient and weather influence coefficient. When the collision warning coefficient reaches the system set value, the system sends a collision alarm to the person in charge of the luggage tractor.

2. A collision warning method according to claim 1, characterized in that: In step S1, at any airport, the system uses a deep learning target monitoring method to monitor vehicles within a circle with a radius of R and a center of the baggage tractor. The system obtains the distance between the baggage tractor A0 and the monitoring vehicle A1 through infrared ranging. i The spacing distance B i The system collects the speed of the baggage tractor as C0, and obtains the speed of the monitored vehicle C through infrared speed measurement. i , A i Indicates the i-th vehicle among the I vehicles monitored by the system, and calculates the vehicle distance influence coefficient D i : Among them B A is the safe distance between vehicles in the area where the baggage tractor A0 is located, C A is the maximum allowed speed in the area where vehicle A0 is located, K B is the influence weight of the real vehicle distance on the vehicle distance influence coefficient, K C is the influence weight of the speed difference between the baggage tractor and the monitoring vehicle on the vehicle distance influence coefficient. The actual vehicle distance is the distance between the baggage tractor and the monitoring vehicle. Substitute {i=1,2,…,I} one by one to calculate the vehicle distance influence coefficients {D1,D2,…,D I }.

3. A collision warning method according to claim 2, characterized in that: In step S2, the system connects to the remote sensing satellite through the Internet of Vehicles and collects the number of vehicles in a circle with the baggage tractor as the center and r as the radius, which is E. A , the number of people in the circle is F A , analyze the road congestion coefficient G in the area where the baggage tractor is located A : Where K E is the weight of the impact of vehicle density on road congestion coefficient, K F is the weight of the impact of population density on the road congestion coefficient.

4. A collision warning method according to claim 3, characterized in that: In step S3, the system obtains the weather conditions of the city where the baggage tractor is located through the network and calculates the current weather impact level H A : H A =K a *a A +K b *b A where a A is the precipitation in the city where the baggage tractor is currently located, b A is the visibility of the city where the baggage tractor is currently located, K a is the weight of the impact of precipitation on weather, K b is the influence weight of visibility on weather impact. Similarly, considering the predicted precipitation and visibility after time t, the predicted weather impact after time t is calculated. A_t Considering the current weather impact and the predicted weather impact, the weather impact coefficient J of the area where the baggage tractor A0 is located is analyzed. A :

5. A collision warning method according to claim 4, characterized in that: In step S4, the vehicle distance influence coefficient, road congestion coefficient and weather influence coefficient are comprehensively analyzed to analyze the collision warning coefficient W of the i-th detected vehicle to the luggage tractor A0. i : W i =K D *D i +K G *G A +K J *J A Where K D K is the influence weight of the vehicle distance influence coefficient on the collision warning coefficient. J K is the influence weight of the set weather influence coefficient on the collision warning coefficient, G is the influence weight of the road congestion coefficient to be calculated on the collision warning coefficient, and the influence weight K of the road congestion coefficient on the collision warning coefficient is calculated. G : Substitute {i=1,2,…,I} one by one and calculate the collision warning coefficients {W1,W2,…,W I }, when there exists {i=1,2,…,I} such that W i ≥W, the system issues a collision alert to the user, where W is the maximum threshold of the collision warning coefficient.

6. A collision warning system, characterized in that: The system comprises: a vehicle distance impact analysis module, a road congestion analysis module, a weather impact analysis module and a collision alarm module; The vehicle distance impact analysis module is used to obtain the interval between the baggage tractor and the nearest monitoring vehicle, obtain the driving speed of the monitoring vehicle, and calculate the vehicle distance impact coefficient based on the driving speed of the baggage tractor; Analyze the flow of people and vehicles in the area where the luggage tractor is located by the road congestion analysis module, and calculate the road congestion coefficient of the area where the luggage tractor is located; Search the weather conditions of the city where the luggage tractor is located through the weather impact analysis module, and analyze the weather impact coefficient of the area where the luggage tractor is located by considering the current weather conditions and the predicted weather conditions; The collision warning module determines the collision warning coefficient of the luggage tractor by comprehensively considering the vehicle distance influence coefficient, the road congestion coefficient and the weather influence coefficient. When the collision warning coefficient reaches the system set value, the system issues a collision warning to the user.

7. A collision warning system according to claim 6, characterized in that: The vehicle distance impact analysis module includes a deep learning camera and an infrared sensor. The deep learning camera is used to find the monitoring vehicle closest to the baggage tractor, and the infrared sensor is used to obtain the distance between the baggage tractor and the nearest monitoring vehicle.

8. A collision warning system according to claim 6, characterized in that: The road congestion analysis module is connected to the remote sensing satellite through the Internet of Vehicles, and calculates the pedestrian flow and vehicle flow in the area where the luggage tractor is located after setting the monitoring range, thereby calculating the road congestion coefficient in the area where the luggage tractor is located.

9. The collision warning system according to claim 6, characterized in that: The weather impact analysis module searches the weather conditions of the city where the luggage tractor is located through the network, the weather conditions including precipitation and visibility, analyzes the current weather conditions by comprehensively considering the current precipitation and visibility, analyzes the predicted weather conditions by comprehensively considering the predicted precipitation and visibility, and calculates the weather impact coefficient of the area where the luggage tractor is located.

10. A collision warning system according to claim 6, characterized in that: The collision alarm module includes a core processor, which sets a maximum threshold value of a collision warning coefficient. When the collision warning coefficient of the monitored vehicle to the luggage tractor reaches the maximum threshold value of the collision warning coefficient, the system issues a collision alarm to the user.

Images