Collision early warning method, vehicle and storage medium

Abstract

The invention provides a collision early warning method, a vehicle and a storage medium. The method comprises the following steps: acquiring traffic light information of a signal light intersection and traffic data of the vehicle; according to the traffic data, target driving time is determined, and the target driving time comprises first driving time needed by a to-be-detected vehicle located behind the vehicle to arrive at the vehicle position of the vehicle and second driving time needed by the vehicle to pass through the signal lamp intersection; and based on the traffic light information, the first driving time and the second driving time, predicting a target vehicle colliding with the vehicle from the to-be-detected vehicles. According to the invention, the driving safety of the vehicle can be improved.

Description

Technical Field

[0001] This application belongs to the technical field of intelligent transportation, and particularly relates to a collision warning method, a vehicle, and a storage medium. Background Art

[0002] With the popularization of vehicles and the increase in the number of vehicles, the pressure on road traffic has increased, and the vehicle collision risk has also increased accordingly. To reduce vehicle collisions, a vehicle collision warning system can be configured in the vehicle. For example, information about the vehicles in front and behind can be obtained through sensors such as cameras, and the collision risk between the vehicles in front and behind and the vehicle itself can be calculated through algorithms.

[0003] However, in the related art, collision warning cannot be performed when the vehicle passes through a signalized intersection, reducing the safety of vehicle driving. Summary of the Invention

[0004] Embodiments of this application provide a collision warning method, a vehicle, and a storage medium to solve the problem that the safety of vehicle driving is reduced due to collisions at signalized intersections.

[0005] In a first aspect, an embodiment of this application provides a collision warning method applied to a vehicle. The method includes: obtaining traffic light information of a signalized intersection and traffic data of the vehicle; determining a target driving time according to the traffic data, where the target driving time includes a first driving time required for a vehicle to be measured located behind the vehicle to reach the vehicle position of the vehicle, and a second driving time required for the vehicle to pass through the signalized intersection; and predicting a target vehicle that collides with the vehicle from the vehicles to be measured based on the traffic light information, the first driving time, and the second driving time.

[0006] In a second aspect, an embodiment of this application provides a collision warning device applied to a vehicle. The device includes: an information acquisition module for obtaining traffic light information of a signalized intersection and traffic data of the vehicle; a time determination module for determining a target driving time according to the traffic data, where the target driving time includes a first driving time required for a vehicle to be measured located behind the vehicle to reach the vehicle position of the vehicle, and a second driving time required for the vehicle to pass through the signalized intersection; and a collision prediction module for predicting a target vehicle that collides with the vehicle from the vehicles to be measured based on the traffic light information, the first driving time, and the second driving time.

[0007] In a third aspect, an embodiment of this application further provides a vehicle, which includes a processor and a memory. When the processor executes a computer program stored in the memory, the above-mentioned collision warning method is implemented.

[0008] Fourthly, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and the computer program is executed by a processor to implement the above-mentioned collision warning method.

[0009] The above-mentioned collision warning method provided by the embodiment of the present application obtains the traffic light information of the signal light intersection and the traffic data of the vehicle; determines a target driving time according to the traffic data, where the target driving time includes a first driving time required for a to-be-detected vehicle behind the vehicle to reach the vehicle position of the vehicle, and a second driving time required for the vehicle to pass through the signal light intersection; predicts a target vehicle that collides with the vehicle from the to-be-detected vehicles based on the traffic light information, the first driving time, and the second driving time. The above method analyzes the traffic light information and the traffic data of the vehicle. Based on the traffic light information, it can determine the vehicles waiting for the signal light or passing through the signal light intersection. Based on the traffic data of the vehicle, it can determine the first driving time required for the to-be-detected vehicle behind the vehicle to reach the vehicle position of the vehicle and the second driving time required for the vehicle to pass through the signal light intersection. Based on the traffic light information, the first driving time, and the second driving time, it predicts a target vehicle that collides with the vehicle from the to-be-detected vehicles. By quantifying the movement trends of the vehicle and the to-be-detected vehicles from the time dimension, it can effectively detect the possibility of a collision occurring behind the vehicle at the signal light intersection, avoid the rear vehicle from colliding with the vehicle, and improve the safety of vehicle driving. Description of the Drawings

[0010] Figure 1 It is a device diagram of a collision warning method provided by an embodiment of the present application.

[0011] Figure 2 It is a flowchart of a collision warning method provided by an embodiment of the present application.

[0012] Figure 3 It is a schematic diagram of a to-be-detected vehicle provided by an embodiment of the present application.

[0013] Figure 4 It is a flowchart for determining a speed threshold provided by an embodiment of the present application.

[0014] Figure 5 It is a schematic flowchart of a method for determining a target vehicle in a red light scenario provided by an embodiment of the present application.

[0015] Figure 6 It is a schematic flowchart of a method for determining a target vehicle in a green light scenario provided by an embodiment of the present application.

[0016] Figure 7 It is a schematic structural diagram of a collision warning device provided by an embodiment of the present application. Detailed implementation manners

[0017] In order to make the technical problems, technical solutions and beneficial effects solved by the present application more clear and understandable, the present application will be further described in detail below in conjunction with embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0018] It should be noted that the terms "first" and "second" in the specification, claims and drawings of the present application are used to distinguish similar objects, rather than to describe a specific order or sequence. The "plurality" in the present application means two or more.

[0019] In addition, it should be noted that for the method disclosed in the embodiments of the present application or the method shown in the flowchart, which includes one or more steps for implementing the method, without departing from the scope of the claims, the execution order of multiple steps can be interchanged with each other, and some steps can also be deleted.

[0020] With the popularization of vehicles and the increase in the number of vehicles, the pressure on road traffic has increased, and the risk of vehicle collisions has also increased. When a vehicle passes through a signalized intersection, for example, when the vehicle is waiting for a signal (e.g., a red light), or when the vehicle is passing through a signalized intersection (e.g., a green light intersection), there will be problems such as the rear vehicle hitting due to fatigue driving, trying to catch the green light or other emergencies, resulting in a decrease in the driving safety of the vehicle.

[0021] In view of this, the embodiments of the present application provide a collision warning method, which obtains the traffic light information of a signalized intersection and the traffic data of the vehicle; determines a target driving time according to the traffic data, where the target driving time includes a first driving time required for a to-be-detected vehicle located behind the vehicle to reach the vehicle position of the vehicle, and a second driving time required for the vehicle to pass through the signalized intersection; and predicts a target vehicle that collides with the vehicle from the to-be-detected vehicles based on the traffic light information, the first driving time and the second driving time.

[0022] The present application analyzes the traffic light information and the traffic data of the vehicle. Based on the traffic light information, it can determine the vehicles that are waiting for the signal or passing through the signalized intersection. Based on the traffic data of the vehicle, it can determine the first driving time required for the to-be-detected vehicle located behind the vehicle to reach the vehicle position of the vehicle and the second driving time required for the vehicle to pass through the signalized intersection. Based on the traffic light information, the first driving time and the second driving time, it predicts a target vehicle that collides with the vehicle from the to-be-detected vehicles. By quantifying the motion trends of the vehicle and the to-be-detected vehicles from the time dimension, it can effectively detect the possibility of a collision occurring behind the vehicle at the signalized intersection, avoid the rear vehicle hitting the vehicle itself, and improve the driving safety of the vehicle.

[0023] Some embodiments will be described below in conjunction with the accompanying drawings. Without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0024] Combine Figure 1 Describe the device diagram of a collision warning method provided by an embodiment of the present application. The collision warning method can be applied to vehicle 10, and vehicle 10 can include a hybrid vehicle, a pure fuel vehicle, and a pure electric vehicle, which are not limited herein. As Figure 1 shown, vehicle 10 includes a radar 101, a camera device 102, a communication module 103, a memory 104, a processor 105, an input / output (I / O) interface 106, and a bus 107. The processor 105 is respectively coupled to the radar 101, the camera device 102, the communication module 103, the memory 104, and the input / output interface 106 through the bus 107.

[0025] In some embodiments, the radar 101 can include a millimeter-wave radar, a lidar, etc. In this embodiment of the present application, the radar 101 is taken as an example of a lidar for description. The radar 101 is connected to the processor 105, and the radar 101 is used to obtain the traffic data of the vehicle 10 and transmit the traffic data to the processor 105. Among them, the traffic data can include first traffic data and second traffic data. The first traffic data can represent the driving conditions of the vehicle (for ease of description, abbreviated as "vehicle to be measured" in this application) behind the vehicle 10. For example, the first traffic data can include information such as the driving speed, acceleration, length of the vehicle to be measured, and the vehicle distance between the vehicle to be measured and the vehicle. The second traffic data can represent the driving conditions of the vehicle 10. For example, the second traffic data can include information such as the driving speed, acceleration, and the distance of the vehicle 10 from the signal light intersection. Considering that the detection range of the lidar is farther, the present application uses the lidar to be able to detect the driving conditions of multiple vehicles to be measured behind the vehicle 10, and can perform collision warning earlier, improving the effect of collision warning.

[0026] In some embodiments, the camera device 102 is connected to the processor 105. The camera device 102 is used to collect an image of the signal light and transmit the image of the signal light to the processor 105, so that the processor 105 processes the image of the signal light to obtain traffic light information. Among them, the image of the signal light includes the signal light and its countdown display. The traffic light information is used to identify the color of the signal light and the remaining time, and the signal light can include a red light and a green light.

[0027] In some embodiments, the communication module 103 may be a wired communication module and / or a wireless communication module. The communication module 103 may be connected to a traffic signal processor or a Road Side Unit (RSU) installed at a signalized intersection for obtaining traffic light information real-time monitored by the traffic signal processor or the RSU. The communication module 103 is connected to the processor 105 for sending the traffic light information to the processor 105.

[0028] In some embodiments, the memory 104 may include one or more random access memories (RAM) and one or more non-volatile memories (NVM). The memory 104 is used for storing one or more computer programs. The one or more computer programs are configured to be executed by the processor 105. The one or more computer programs include a plurality of instructions, and when the plurality of instructions are executed by the processor 105, a collision warning method executable on the vehicle 10 can be implemented.

[0029] In some embodiments, the processor 105 provides computing and control capabilities. For example, the processor 105 is used for executing the computer program stored in the memory 104 to implement the above-mentioned collision warning method.

[0030] In some embodiments, the input / output interface 106 is used for providing a channel for user input or output. For example, the input / output interface 106 can be used to connect various input / output devices, such as a mouse, a keyboard, a touch device, a display screen, etc., so that a user can input information or visualize information.

[0031] In some embodiments, in a collision warning scenario, the processor 105 is used for obtaining traffic data of the vehicle 10. The traffic data may include the driving speed, acceleration, vehicle length of the vehicle 10, the distance between the vehicle 10 and the signalized intersection, and the driving speed, acceleration, length of the vehicle to be measured behind the vehicle 10, the vehicle distance between the vehicle to be measured and the vehicle 10, etc. The processor 105 is further used for determining the traffic light information based on an image of the traffic light collected by the imaging device 102, or receiving the traffic light information transmitted by the communication module 103. The processor 105 realizes collision warning for the vehicle 10 by analyzing the traffic data and the traffic light information. In some embodiments, the processor 105 determines a target driving time according to the traffic data. The target driving time includes a first driving time required for the vehicle to be measured behind the vehicle 10 to reach the vehicle position of the vehicle 10, and a second driving time required for the vehicle 10 to pass through the signalized intersection; thereafter, the processor 105 predicts a target vehicle that may collide with the vehicle 10 from the vehicles to be measured based on the traffic light information, the first driving time, and the second driving time.

[0032] In the vehicle 10 provided in the embodiment of the present application, radar 101 is used to obtain traffic data of the vehicle 10, a camera device 102 or a communication module 103 is used to obtain traffic light information, and a processor 105 is used to analyze the traffic data of the vehicle 10 and the traffic light information. For a vehicle 10 that is waiting for a traffic signal or passing through a traffic signal, the possibility of a collision occurring behind the vehicle 10 can be effectively detected, avoiding a collision of the vehicle behind with the vehicle 10 and improving the driving safety of the vehicle 10.

[0033] Figure 2 is a flowchart of a collision warning method provided in an embodiment of the present application. This collision warning method is applied to a vehicle (for example, Figure 1 the vehicle 10 in Figure 2 ). As

[0034] shown, this collision warning method may include the following steps. According to different requirements, the order of the steps in this flowchart may be changed, and some may be omitted.

[0035] In some embodiments, the traffic light information is used to identify the color of the traffic light and the remaining time. The traffic light may include a red light and a green light. The traffic light information includes the remaining time of the red light and the remaining time of the green light. The traffic light information may be determined by visual recognition technology, vehicle-to-everything (V2X) technology, or from relevant navigation software.

[0036] Exemplarily, an image capturing device in a vehicle is used to capture an image including a traffic signal, and the image is processed by a preset image recognition model to determine whether the current traffic signal is red or green, and the remaining time of the red light or the remaining time of the green light. Among them, the image recognition model can be a neural network model. For example, the image recognition model can be a Convolutional Neural Networks (CNNs) model, a Recurrent Neural Networks (RNNs) model, a Generative Adversarial Networks (GANs) model, etc., which are not limited herein. The training method of the image recognition model can include a supervised training method and an unsupervised training method. In this embodiment of the present application, the supervised training method is taken as an example for the training method of the image recognition model. When training the image recognition model, an image including a traffic signal and a countdown display is used as input data, and the traffic light information is used as output data to train the image recognition model. During the training process, the image recognition model adjusts the weights and biases of the model based on the accuracy of the model output results, so as to obtain a detection model with an accuracy greater than a preset accuracy threshold. Among them, the preset accuracy threshold can be set according to actual needs. For example, the preset accuracy threshold can be 95%, 98%, etc. The training process of the model can refer to related technologies and will not be elaborated herein.

[0037] Exemplarily again, a traffic signal controller or a roadside unit installed at a traffic signal intersection is used to monitor the traffic light information in real time, including the color (red, green, yellow) of the traffic signal and the remaining time. The traffic light information is transmitted to the vehicle through wireless communication technologies such as dedicated short-range communication or cellular networks.

[0038] Exemplarily again, the vehicle can be connected to the driver's mobile terminal (such as a mobile phone, a tablet, etc.). The mobile terminal is equipped with applications such as navigation software. The navigation software can obtain the traffic light information and transmit the traffic light information to the vehicle.

[0039] In some embodiments, the traffic data includes first traffic data and second traffic data. The first traffic data may represent the driving conditions of a vehicle to be measured located behind the vehicle. For example, the first traffic data may include the driving speed of the vehicle to be measured located behind the vehicle (for ease of description, referred to as the "first driving speed" in this application), acceleration (for ease of description, referred to as the "first acceleration" in this application), the length of the vehicle to be measured, and the vehicle distance between the vehicle to be measured and the vehicle, etc. The second traffic data may represent the driving conditions of the vehicle. For example, the second traffic data may include the driving speed of the vehicle (for ease of description, referred to as the "second driving speed" in this application), acceleration (for ease of description, referred to as the "second acceleration" in this application), the distance between the vehicle and the signalized intersection, etc.

[0040] In some embodiments, when the signal light is red, the vehicle needs to wait at the signalized intersection. At this time, the target vehicle that may collide with the rear of the vehicle (e.g., the rear of the car) can be predicted based on the first traffic data of the vehicle and the traffic light information. When the signal light is green, the vehicle will pass through the signalized intersection. At this time, the target vehicle that may collide with the rear of the vehicle can be predicted based on the first traffic data, the second traffic data of the vehicle, and the traffic light information. Based on this, the method for obtaining the traffic data of the vehicle may include: if the traffic light information indicates that the signal light in front of the vehicle is red, then determining the first traffic data of the vehicle as the traffic data; if the traffic light information indicates that the signal light in front of the vehicle is green, then determining the first traffic data and the second traffic data of the vehicle as the traffic data. In the embodiments of the present application, the data to be collected for collision warning is determined based on the traffic light information. The first traffic data of the vehicle is collected when the signal light is red, and the first traffic data and the second traffic data of the vehicle are used when the signal light is green. Appropriate traffic data is selected according to different signal light scenarios for collision warning, which can improve the accuracy of collision warning.

[0041] In some embodiments, the number of vehicles to be measured can be determined according to the detection range of the lidar installed in the vehicle. Combining Figure 3 to illustrate the schematic diagram of the vehicle to be measured provided by the embodiments of the present application, as Figure 3 shown, vehicles A, B, C, D, E, and F are at the signalized intersection. For vehicle A, the vehicles to be measured may include vehicle B located behind vehicle A (i.e., the vehicle to be measured B), vehicle C located behind the vehicle to be measured B (i.e., the vehicle to be measured C), and vehicle D located behind the vehicle to be measured C (i.e., the vehicle to be measured D). Vehicles E and F located behind vehicle A are not vehicles to be measured.

[0042] S12. Determine a target travel time based on the traffic data. The target travel time includes a first travel time required for a vehicle to be measured, which is behind the vehicle, to reach the vehicle position of the vehicle, and a second travel time required for the vehicle to pass through the signalized intersection.

[0043] In at least one embodiment of the present application, the target travel time includes a first travel time and a second travel time. The first travel time can represent the time required for a vehicle to be measured, which is behind the vehicle, to reach the vehicle position of the vehicle, and the second travel time can represent the time required for the vehicle to pass through the signalized intersection. In some embodiments, if the traffic light information indicates that the traffic light in front of the vehicle is red, it is determined that the vehicle is in a red light scenario, and the traffic data is analyzed to obtain the first travel time required for each vehicle to be measured, which is behind the vehicle, to reach the vehicle position of the vehicle. If the traffic light information indicates that the traffic light in front of the vehicle is green, it is determined that the vehicle is in a green light scenario, and the traffic data is analyzed to obtain the first travel time required for each vehicle to be measured, which is behind the vehicle, to reach the vehicle position of the vehicle, and the second travel time required for the vehicle to pass through the signalized intersection. In the embodiment of the present application, the first travel time is determined when the vehicle is in a red light scenario, and the first travel time and the second travel time are determined when the vehicle is in a green light scenario. By determining the time dimension information required for collision warning according to different signal light scenarios, the accuracy of collision warning can be improved.

[0044] S13. Predict a target vehicle that may collide with the vehicle from the vehicles to be measured based on the traffic light information, the first travel time, and the second travel time.

[0045] In at least one embodiment of the present application, the target vehicle can represent a vehicle to be measured that is directly behind the vehicle and may collide with the rear of the vehicle. The number of target vehicles can be 0, 1, or more, which is not limited herein. The traffic light information can include the remaining red light time and the remaining green light time. In some embodiments, if the traffic light information indicates that the traffic light in front of the vehicle is red, it is determined that the vehicle is in a red light scenario, and a target vehicle that may collide with the vehicle is predicted from the vehicles to be measured based on the remaining red light time and the first travel time. If the traffic light information indicates that the traffic light in front of the vehicle is green, it is determined that the vehicle is in a green light scenario, and a target vehicle that may collide with the vehicle is predicted from the vehicles to be measured based on the remaining green light time, the first travel time, and the second travel time. In the embodiment of the present application, corresponding collision warning strategies are determined according to different signal light scenarios, and the target vehicles that may collide with the rear of the vehicle are predicted by using the collision warning strategies, which can improve the accuracy of collision warning.

[0046] The above-mentioned collision warning method provided by the embodiments of the present application analyzes the traffic light information and the traffic data of the vehicle. For a vehicle waiting for a traffic light or passing through a traffic light, it can effectively detect the possibility of a collision occurring behind the vehicle, avoid the rear vehicle from colliding with the vehicle itself, and improve the safety of vehicle driving.

[0047] In at least one embodiment of the present application, when the traffic light is red, the vehicle needs to wait at the traffic light intersection. At this time, if the first driving speeds of multiple vehicles to be measured located behind the vehicle are relatively fast, it is predicted that the probability of a collision between the vehicle to be measured and the rear of the vehicle is relatively high. Based on this, after obtaining the traffic light information of the traffic light intersection and the traffic data of the vehicle, the method further includes: if the traffic light information indicates that the traffic light in front of the vehicle is red, determining that the vehicle is in a red light scenario, parsing the traffic data, and obtaining the first driving speed of each vehicle to be measured located behind the vehicle; determining the vehicle to be measured with the first driving speed greater than or equal to the speed threshold as the first target vehicle. The speed threshold can be set according to actual needs. For example, the speed threshold can be 50 km / h, 60 km / h, 70 km / h, etc., and is not limited here.

[0048] Combined with Figure 4 Illustrate the flow chart for determining the speed threshold provided by the embodiments of the present application. As Figure 4 shown, the traffic data includes the first driving speeds of multiple vehicles to be measured located behind the vehicle. By parsing the traffic data, the first driving speeds of multiple vehicles to be measured can be obtained. Compare the first driving speeds of multiple vehicles to be measured with the speed threshold. If the first driving speed is greater than or equal to the speed threshold, then determine the vehicle to be measured as the first target vehicle. If the first driving speed is less than the speed threshold, based on the traffic data of the vehicle (such as the first traffic data), determine the first driving time required for the vehicle to be measured located behind the vehicle to reach the vehicle position of the vehicle, and use the first driving time and the traffic light information (such as the remaining time of the red light) to predict the target vehicle that may collide with the vehicle from the vehicles to be measured.

[0049] The warning collision method provided by the embodiments of the present application, when the vehicle is in a red light scenario, by parsing the traffic data, obtaining the first driving speeds of multiple vehicles to be measured located behind the vehicle, and using the first driving speeds to compare with the speed threshold, can monitor and warn the vehicle to be measured with a relatively fast first driving speed behind, and improve the effect of collision warning.

[0050] In at least one embodiment of the present application, when the traffic light is red, the vehicle needs to wait at the traffic light intersection. At this time, the target vehicle that may collide with the rear of the vehicle can be predicted based on the first traffic data of the vehicle and the traffic light information. Figure 5It is a schematic flowchart of a method for determining a target vehicle in a red light scenario provided by an embodiment of the present application. The method for determining a target vehicle in a red light scenario is applied to a vehicle. As Figure 5 shown, the method includes the following steps: S21, if the traffic light information indicates that the traffic light in front of the vehicle is a red light, then analyze the traffic data to obtain the first travel time required for each vehicle to be measured located behind the vehicle to reach the vehicle position of the vehicle.

[0051] In at least one embodiment of the present application, the traffic data includes first traffic data, and the first traffic data may include the first travel speed, the first acceleration of the vehicle to be measured, and the vehicle distance between the vehicle to be measured and the vehicle. The number of vehicles to be measured can be determined according to the detection range of the lidar installed in the vehicle, and no limitation is made here. For example, for vehicle A, the vehicles to be measured may include vehicle B directly behind vehicle A, vehicle C directly behind vehicle B, and vehicle D directly behind vehicle C. Vehicles E and F located behind vehicle A on the side are not vehicles to be measured.

[0052] In some embodiments, based on the first travel speed, the first acceleration of the vehicle to be measured, and the vehicle distance between the vehicle to be measured and the vehicle, the first travel time required for the vehicle to be measured to reach the vehicle position of the vehicle can be determined. Exemplarily, based on the first travel speed, the first acceleration, and the vehicle distance between the vehicle to be measured and the vehicle, using the following formula 1, the first travel time required for the vehicle to be measured to reach the vehicle position of the vehicle can be determined.

[0053] Formula 1: S1 = V 01 t1 + 1 / 2a1t1 2 .

[0054] Wherein, S1 represents the vehicle distance between the vehicle to be measured and the vehicle, V 01 represents the first travel speed of the vehicle to be measured, a1 represents the first acceleration of the vehicle to be measured, and t1 represents the first travel time.

[0055] Based on the first travel speed, the first acceleration, and the vehicle distance of the vehicle to be measured, the embodiment of the present application can quickly and accurately determine the first travel time required for the vehicle to be measured to reach the vehicle position of the vehicle, improve the accuracy and efficiency of determining the first travel time, and then improve the accuracy and efficiency of vehicle collision warning.

[0056] S22, determine the vehicles to be measured with the first travel time less than or equal to the remaining red light time as the second target vehicles.

[0057] In at least one embodiment of the present application, the traffic light information includes the remaining time of the red light. Predicting a target vehicle that may collide with the vehicle from the to-be-detected vehicles based on the traffic light information, the first travel time, and the second travel time includes: if the traffic light information indicates that the traffic light in front of the vehicle is red, determining a to-be-detected vehicle whose first travel time is less than or equal to the remaining time of the red light as a second target vehicle. Wherein, the first travel time being less than or equal to the remaining time of the red light indicates that the to-be-detected vehicle will reach the vehicle position where the vehicle is located before the vehicle starts, that is, the risk of collision between the to-be-detected vehicle and the rear of the vehicle is relatively high.

[0058] Exemplarily, in a red light scenario, for vehicle A, the to-be-detected vehicles include vehicle B, vehicle C, and vehicle D. The remaining time of the red light is 10 seconds. The first travel time required for vehicle B to reach the vehicle position of vehicle A is 5 seconds, the first travel time required for vehicle C to reach the vehicle position of vehicle A is 6 seconds, and the first travel time required for vehicle D to reach the vehicle position of vehicle A is 11 seconds. Since 10 seconds is greater than 5 seconds and 6 seconds, but 10 seconds is less than 11 seconds, it indicates that vehicle B and vehicle C will reach the vehicle position where vehicle A is located before vehicle A starts, while vehicle D cannot reach the vehicle position where vehicle A is located before vehicle A starts. Based on this, vehicle B and vehicle C are used as the second target vehicles.

[0059] In some other embodiments, the time ratio of the remaining time of the red light to the first travel time can also be determined, and a to-be-detected vehicle with a time ratio greater than a time threshold is used as the second target vehicle. Wherein, the time threshold can be set according to actual requirements.

[0060] In the collision warning method provided by the embodiments of the present application, in a red light scenario, by combining the first travel time for the to-be-detected vehicle to reach the vehicle position of the vehicle and the remaining time of the red light, predicting the target vehicle that may collide with the rear of the vehicle can realize the collision prediction of the rear of the vehicle in a red light scenario, avoid collisions at the rear of the vehicle, and improve the driving safety of the vehicle; and the present application quantifies the movement trends of the vehicle and the to-be-detected vehicles based on time dimension information, can accurately detect the possibility of a collision at the rear of the vehicle in a red light scenario, and improve the effect of collision warning.

[0061] In at least one embodiment of the present application, when the traffic light is green, the vehicle directly passes through the traffic light intersection. At this time, the target vehicle that may collide with the rear of the vehicle can be predicted based on the first traffic data, the second traffic data, and the traffic light information of the vehicle. Figure 6 It is a schematic flowchart of a method for determining a target vehicle in a green light scenario provided by an embodiment of the present application. The method for determining a target vehicle in a green light scenario is applied to a vehicle. As Figure 6 shown, it includes the following steps: S31. If the traffic light information indicates that the signal light in front of the vehicle is green, then analyze the traffic data to obtain the first travel time required for each vehicle to be tested behind the vehicle to reach the vehicle's position, and the second travel time required for the vehicle to pass through the signal light intersection.

[0062] In at least one embodiment of the present application, the traffic data includes first traffic data and second traffic data. The first traffic data may include the first travel speed, first acceleration, first vehicle length of the vehicle to be tested, and the vehicle distance between the vehicle to be tested and the vehicle. The second traffic data may include the distance between the vehicle and the signal light intersection, the second travel speed, second acceleration, and second vehicle length of the vehicle. Among them, based on the first traffic data, the first travel time can be determined, and based on the second traffic data, the second travel time can be determined. The method for determining the first travel time has been described in detail in step S21 above and will not be elaborated here.

[0063] In some embodiments, taking the determination of the second travel time based on the second traffic data as an example, based on the distance between the vehicle and the signal light intersection, the second travel speed, and the second acceleration, using formula 2, the second travel time required for the vehicle to pass through the signal light intersection can be determined.

[0064] Formula 2: S 本 =V 0本 t 本 +1 / 2a 本 t 本 2 .

[0065] Among them, S 本 represents the distance between the vehicle and the signal light intersection, V 0本 represents the second travel speed, a 本 represents the second acceleration, and t 本 represents the second travel time.

[0066] S32. Based on the first travel time and the second travel time, determine the target travel time.

[0067] In at least one embodiment of the present application, the sum value of the first travel time and the second travel time can be used as the target travel time, or the first travel time and the second travel time can be weighted and summed to obtain the target travel time, and the present application does not limit this here.

[0068] S33. Determine the third target vehicle as the vehicle to be tested whose target travel time is greater than the remaining green light time.

[0069] In at least one embodiment of the present application, the traffic light information includes the remaining green light time, and a vehicle to be tested whose target driving time is greater than the remaining green light time is determined as a third target vehicle.

[0070] In the collision warning method provided by the embodiment of the present application, in the green light scenario, by combining the first driving time, the second driving time, and the remaining green light time, a target vehicle that may collide with the rear of the vehicle is predicted, which can realize the collision prediction of the rear of the vehicle in the green light scenario, avoid collisions at the rear of the vehicle, and improve the driving safety of the vehicle; moreover, the present application quantifies the motion trends of the vehicle and the vehicle to be tested based on the time dimension information, and can accurately detect the possibility of a collision occurring at the rear of the vehicle in the green light scenario, improving the effect of collision warning.

[0071] In at least one embodiment of the present application, after predicting a target vehicle that collides with the vehicle from the vehicles to be tested, the warning level of the target vehicle can be determined, and a collision warning prompt can be output. Exemplarily, the method for determining the collision preset prompt: determining the warning level corresponding to the target vehicle according to a preset update period; outputting the collision warning prompt corresponding to the determined warning level according to the corresponding relationship between the pre-set warning level and the collision warning prompt; and determining the number of times the same target vehicle is determined as the preset level within multiple update periods; determining the collision warning prompt according to the number of times.

[0072] In some embodiments, the warning level of the target vehicle is determined according to different scenarios. Among them, the warning level is used to indicate the probability of a collision. The greater the probability of a collision, the higher the warning level; the lower the probability of a collision, the lower the warning level. For example, the warning level can include a first level and a second level, and the probability of a collision corresponding to the first level is less than the probability of a collision corresponding to the second level. In some embodiments, when the vehicle is in the red light scenario, the warning level corresponding to the first target vehicle whose first driving speed is greater than or equal to the speed threshold is determined as the first level; the warning level corresponding to the second target vehicle whose first driving time is less than or equal to the remaining red light time is determined as the second level. When the vehicle is in the green light scenario, the warning level corresponding to the third target vehicle whose target driving time is greater than the remaining green light time is determined as the second level.

[0073] In some embodiments, for the corresponding relationship between the pre-set warning level and the collision warning prompt, by querying this corresponding relationship, the collision warning prompt corresponding to the determined warning level can be output. For example, when the warning level of a target vehicle is the first level, the collision warning prompt can include "There is a vehicle with a fast speed behind"; when the warning level of a target vehicle is the second level, the collision warning prompt can include "A collision may occur with the vehicle behind".

[0074] In some embodiments, the update period is a preset time period for updating traffic data. When a vehicle recognizes traffic light information, the traffic data of the vehicle is determined according to the update period. For example, the update period can be 200 milliseconds, 300 milliseconds, 400 milliseconds, etc. In the embodiments of the present application, taking the update period of 200 milliseconds as an example, when a vehicle recognizes traffic light information, the traffic data of the vehicle within 200 milliseconds is obtained, and based on the traffic data and the traffic light information, the target vehicle behind the vehicle and the warning level are determined. Then, the traffic data of the vehicle within the next 200 milliseconds is obtained, and based on the updated traffic data and the traffic light information, the target vehicle behind the vehicle and the warning level are determined. This is executed for multiple update periods until the vehicle leaves the signal intersection.

[0075] In some embodiments, the preset level can be the second level. The number of times a same target vehicle is determined to be at the preset level can be monitored within multiple update periods, and the number of times is compared with the number threshold. If the number of times is greater than or equal to the number threshold, a prompt of "rear vehicle collision danger" is output; if the number of times is less than the number threshold, a prompt of "rear vehicle may collide" is output. Among them, the number threshold can be set according to actual needs. For example, the number threshold can be 2 times, 3 times, 4 times, etc. In the embodiments of the present application, the number threshold of 3 times is taken as an example for illustration. For example, within 1 second, the number of times a same target vehicle is marked as the second level is 3 times, then the collision warning prompt can include "rear vehicle collision danger". The collision warning prompt can be output in ways such as text, graphics or sound, which is not limited here.

[0076] In the embodiments of the present application, by setting the correspondence between the warning level and the collision warning prompt, the collision warning prompt corresponding to the determined warning level can be output quickly and accurately; and in the present application, corresponding warning levels are set for target vehicles with different collision probabilities. Through hierarchical setting, the effect of collision warning can be improved; in addition, in the present application, by counting the number of times a same target vehicle is determined to be at the preset level within multiple update periods, the probability of the target vehicle colliding can be determined, and a collision warning prompt is output in a timely manner for the situation with a relatively high probability of collision, reminding the user in a timely manner and improving the effect of collision warning.

[0077] Please refer to Figure 7 , Figure 7 which is a schematic structural diagram of a collision warning device provided by the embodiments of the present application. In some embodiments, the collision warning device 20 may include multiple functional modules composed of computer program segments. The computer programs of each program segment in the collision warning device 20 can be stored in the memory of the vehicle 10 and executed by at least one processor to execute (see in detail Figure 2 the description) the function of collision warning.

[0078] In this embodiment, the collision warning device 20 can be divided into multiple functional modules according to the functions it performs. The functional modules may include: an information acquisition module 201, a time determination module 202, and a collision prediction module 203. The module referred to in this application means a series of computer program segments that can be executed by at least one processor and can complete fixed functions, and are stored in the memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

[0079] The information acquisition module 201 can be used to acquire the traffic light information of the signal light intersection and the traffic data of the vehicle.

[0080] The time determination module 202 can be used to determine the target driving time according to the traffic data. The target driving time includes the first driving time required for a vehicle to be measured behind the vehicle to reach the vehicle position of the vehicle, and the second driving time required for the vehicle to pass through the signal light intersection.

[0081] The collision prediction module 203 can be used to predict a target vehicle that will collide with the vehicle from the vehicles to be measured based on the traffic light information, the first driving time, and the second driving time.

[0082] In some embodiments, the collision prediction module 203 can also be used to determine that the vehicle is in a red light scenario when the traffic light information indicates that the traffic light in front of the vehicle is red, analyze the traffic data, and obtain the first driving speed of each vehicle to be measured behind the vehicle; determine the vehicle to be measured with the first driving speed greater than or equal to the speed threshold as the first target vehicle.

[0083] In some embodiments, the time determination module 202 can also be used to analyze the traffic data to obtain the first driving time required for each vehicle to be measured behind the vehicle to reach the vehicle position of the vehicle when the traffic light information indicates that the traffic light in front of the vehicle is red.

[0084] In some embodiments, the time determination module 202 can also be used to determine the vehicle distance between each vehicle to be measured and the vehicle according to the traffic data, and determine the first driving speed and the first acceleration of each vehicle to be measured; based on the vehicle distance, the first driving speed, and the first acceleration, determine the first driving time corresponding to each vehicle to be measured.

[0085] In some embodiments, the collision prediction module 203 can also be used to determine the vehicle to be measured with the first driving time less than or equal to the remaining red light time as the second target vehicle if the traffic light information indicates that the traffic light in front of the vehicle is red.

[0086] In some embodiments, the time determination module 202 may further be configured to, if the traffic signal information indicates that the signal light in front of the vehicle is green, determine that the vehicle is in a green light scenario, analyze the traffic data, and obtain a first travel time required for each vehicle to be measured behind the vehicle to reach the vehicle position of the vehicle, and a second travel time required for the vehicle to pass through the signal light intersection.

[0087] In some embodiments, the collision prediction module 203 may further be configured to, if the traffic signal information indicates that the signal light in front of the vehicle is green, determine a target travel time based on the first travel time and the second travel time; and determine a third target vehicle as a vehicle to be measured for which the target travel time is greater than the remaining green light time.

[0088] In some embodiments, the collision prediction module 203 may further be configured to determine a warning level corresponding to the target vehicle according to a preset update period; output a collision warning prompt corresponding to the determined warning level according to a corresponding relationship between a pre-set warning level and a collision warning prompt; and determine the number of times a same target vehicle is determined to be a preset level within a plurality of update periods; and determine the collision warning prompt according to the number of times.

[0089] It can be understood that the collision warning device 20 and the collision warning method in the above embodiments belong to the same inventive concept. The specific implementation manners of the modules of the collision warning device 20 correspond to the steps of the collision warning method in the above embodiments, and are not elaborated herein in this application.

[0090] The above-described module division is a logical function division, and there may be other division manners in actual implementation. In addition, in each embodiment of the present application, the functional modules may be integrated in the same processing unit, or each module may exist physically alone, or two or more modules may be integrated in the same unit. The above-integrated modules may be implemented in the form of hardware, or in the form of a combination of hardware and software functional modules.

[0091] Next Figure 1Regarding the description of the vehicle, the communication module 103 may include a wired communication module and / or a wireless communication module. The wired communication module may provide one or more of the solutions for wired communication such as universal serial bus (USB), Controller Area Network (CAN), etc. The wireless communication module may provide one or more of the solutions for wireless communication such as wireless fidelity (Wi-Fi), Bluetooth (BT), mobile communication network, frequency modulation (FM), near field communication (NFC), infrared (IR), etc.

[0092] In some embodiments, the memory 104 may include one or more random access memories (RAM) and one or more non-volatile memories (NVM). The random access memory can be directly read and written by the processor 105, and can be used to store the executable programs (such as machine instructions) of other running programs, and can also be used to store user and application data, etc. The random access memory may include static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), etc.

[0093] In some embodiments, the non-volatile memory can also store executable programs and store user and application data, etc., and can be pre-loaded into the random access memory for the processor 105 to directly read and write. The non-volatile memory may include disk storage devices, flash memory.

[0094] In some embodiments, the processor 105 may include one or more processing units. For example, the processor 105 may include an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), and / or a neural-network processing unit (NPU), etc. Among them, different processing units may be independent devices or integrated in one or more processors.

[0095] It can be understood that the structure illustrated in the embodiments of the present application does not constitute a specific limitation on the vehicle 10. In other embodiments of the present application, the vehicle 10 may include more or fewer components than those illustrated, or combine certain components, or split certain components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0096] The embodiments of the present application also provide a computer-readable storage medium, on which a computer program is stored. The computer program includes program instructions, and the method implemented when the program instructions are executed may refer to the methods in the above various embodiments of the present application.

[0097] Among them, the computer-readable storage medium may be the internal memory of the vehicle described in the above embodiments, such as the hard disk or memory of the vehicle. The computer-readable storage medium may also be an external storage device of the vehicle, such as a plug-in hard disk equipped on the vehicle, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc.

[0098] In some embodiments, the computer-readable storage medium may include a program storage area and a data storage area. Among them, the program storage area may store an operating system, application programs required for at least one function, etc.; the data storage area may store data created according to the use of the vehicle.

[0099] The computer-readable storage medium mainly includes a program storage area and a data storage area. Among them, the program storage area may store an operating system, application programs required for at least one function, etc.; the data storage area may store data created according to the use of the vehicle 10.

[0100] The integrated units implemented in the form of software functional modules as described above can be stored in a computer-readable storage medium. The above software functional modules are stored in a storage medium and include several instructions for causing a vehicle or a processor to execute parts of the methods according to the embodiments of the present application.

[0101] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of modules is only a logical function division, and there may be other division methods in actual implementation.

[0102] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units. They can be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0103] In addition, in each embodiment of the present application, the functional modules can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0104] For those skilled in the art, it is obvious that the present application is not limited to the details of the above exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or basic characteristics of the present application. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present application is defined by the appended claims rather than the above description. Therefore, it is intended to cover all changes within the meaning and scope of the equivalent elements of the claims in the present application. Any reference signs in the claims should not be regarded as limiting the claimed claims. In addition, it is obvious that the word "comprising" does not exclude other units, and the singular does not exclude the plural. The multiple units or devices described in the specification can also be implemented by one unit or device through software or hardware. The words such as first and second are used to represent names and do not represent any specific order.

[0105] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and not to limit them. Although the present application has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present application can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. A collision warning method, applied to a vehicle, characterized in that, The method includes: Obtaining the traffic light information of the signal light intersection and the traffic data of the vehicle; Based on the traffic data, determining a target travel time, where the target travel time includes a first travel time required for a to-be-detected vehicle located behind the vehicle to reach the vehicle position of the vehicle, and a second travel time required for the vehicle to pass through the signal light intersection; Based on the traffic light information, the first travel time, and the second travel time, predicting a target vehicle that collides with the vehicle from the to-be-detected vehicles.

2. The collision warning method according to claim 1, wherein After obtaining the traffic light information of the signal light intersection and the traffic data of the vehicle, the method further includes: If the traffic light information indicates that the traffic light in front of the vehicle is red, determining that the vehicle is in a red light scenario, parsing the traffic data, and obtaining a first travel speed of each to-be-detected vehicle located behind the vehicle; Determining a first target vehicle as the to-be-detected vehicle whose first travel speed is greater than or equal to a speed threshold.

3. The collision warning method according to claim 1, characterized in that, The determining the target travel time based on the traffic data includes: If the traffic light information indicates that the traffic light in front of the vehicle is red, then parsing the traffic data and obtaining a first travel time required for each to-be-detected vehicle located behind the vehicle to reach the vehicle position of the vehicle.

4. The collision warning method according to claim 3, wherein The parsing the traffic data and obtaining a first travel time required for each to-be-detected vehicle located behind the vehicle to reach the vehicle position of the vehicle includes: Based on the traffic data, determining the vehicle distance between each to-be-detected vehicle and the vehicle, and determining the first travel speed and the first acceleration of each to-be-detected vehicle; Based on the vehicle distance, the first travel speed, and the first acceleration, determining the first travel time corresponding to each to-be-detected vehicle.

5. The collision warning method according to claim 1, characterized in that, The traffic light information includes the remaining red light time. The predicting a target vehicle that collides with the vehicle from the to-be-detected vehicles based on the traffic light information, the first travel time, and the second travel time includes: If the traffic light information indicates that the traffic light in front of the vehicle is red, then determining a second target vehicle as the to-be-detected vehicle whose first travel time is less than or equal to the remaining red light time.

6. The collision warning method according to claim 1, wherein, The determining the target travel time based on the traffic data further includes: If the traffic light information indicates that the traffic light in front of the vehicle is green, determining that the vehicle is in a green light scenario, parsing the traffic data, and obtaining a first travel time required for each to-be-detected vehicle located behind the vehicle to reach the vehicle position of the vehicle, and a second travel time required for the vehicle to pass through the signal light intersection.

7. The collision warning method according to claim 1, characterized in that The traffic light information includes the remaining green light time. The predicting a target vehicle that collides with the vehicle from the to-be-detected vehicles based on the traffic light information, the first travel time, and the second travel time includes: If the traffic light information indicates that the traffic light in front of the vehicle is green, then based on the first travel time and the second travel time, determining the target travel time; Determining a third target vehicle as the to-be-detected vehicle whose target travel time is greater than the remaining green light time.

8. The collision warning method according to claim 1, wherein The method further includes: Determining a warning level corresponding to the target vehicle according to a preset update period; outputting a collision warning prompt corresponding to the determined warning level according to a corresponding relationship between a preset warning level and a collision warning prompt; and Determining the number of times the same target vehicle is determined to be a preset level within multiple update periods; determining the collision warning prompt according to the number of times.

9. A vehicle, characterized in that, The vehicle includes a processor and a memory, and the processor is configured to implement the collision warning method according to any one of claims 1 to 8 when executing a computer program stored in the memory.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor of a computer device, the collision warning method according to any one of claims 1 to 8 is implemented.

Images