Vehicle driving behavior prediction method, device, equipment, medium, product and vehicle
The vehicle driving behavior prediction model analyzes the image of the target vehicle, predicts its driving behavior and avoids dangers in advance, solving the problem of failure to predict the behavior in the prior art, and improving the safety of the autonomous driving system.
Patent Information
- Application Number
- CN202310745502.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-06-21
- Publication Date
- 2024-12-24
AI Technical Summary
In the prior art, vehicle driving behavior prediction mainly focuses on current behavior, and failing to effectively predict the driving behavior that will occur, making it difficult to avoid potential dangers in advance.
By obtaining continuous images of the target vehicle at different speeds, input them into the corresponding vehicle driving behavior prediction model, calculate the probability of each driving behavior, and determine the maximum probability behavior as the predicted behavior, including playing prompt information or Send control instructions to the autonomous driving system to avoid danger.
Accurate prediction of the vehicle's driving behavior is achieved, dangerous behaviors are avoided in advance, and the safety of the autonomous driving system is improved.
Smart Images
Figure CN119176142A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the field of autonomous driving technology, and in particular, relates to a vehicle driving behavior prediction method, device, equipment, medium, product and vehicle. Background Art
[0002] Vehicle driving behavior refers to the behavior that occurs during the vehicle driving process, such as emergency braking, turning on fog lights, turning on wipers, vehicle acceleration, etc.
[0003] The related technologies only focus on the current driving behavior of the vehicle, but not on the driving behavior that the vehicle is about to take. However, the driving behavior that the vehicle is about to take is also particularly important for autonomous driving. For example, controlling the vehicle not to take dangerous driving behaviors that are about to take place, so as to avoid dangerous driving behaviors in advance. Therefore, how to predict the driving behavior that the vehicle is about to take place is a technical problem that needs to be solved urgently. Summary of the invention
[0004] The embodiments of the present application provide a vehicle driving behavior prediction method, device, equipment, medium, product and vehicle, which can predict the vehicle's upcoming driving behavior.
[0005] In a first aspect, an embodiment of the present application provides a vehicle driving behavior prediction method, comprising:
[0006] Acquire multiple images continuously collected of the target vehicle at a first speed;
[0007] Inputting the first speed and the plurality of images into a first vehicle driving behavior prediction model corresponding to the first speed to obtain the probability that the target vehicle will perform each driving behavior;
[0008] The driving behavior corresponding to the maximum probability is determined as the target driving behavior that the target vehicle will take.
[0009] In a second aspect, an embodiment of the present application provides a vehicle driving behavior prediction device, comprising:
[0010] A first acquisition module is used to acquire a plurality of images continuously collected from the target vehicle at a first speed;
[0011] A probability determination module, used for inputting the first speed and the plurality of images into a first vehicle driving behavior prediction model corresponding to the first speed, to obtain the probability that the target vehicle will perform each driving behavior;
[0012] The prediction module is used to determine the driving behavior corresponding to the maximum probability as the target driving behavior that will occur for the target vehicle.
[0013] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor and a memory storing computer program instructions; when the processor reads and executes the computer program instructions, the vehicle driving behavior prediction method provided in the first aspect of the embodiment of the present application is implemented.
[0014] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the vehicle driving behavior prediction method provided in the first aspect of the embodiment of the present application is implemented.
[0015] In a fifth aspect, an embodiment of the present application provides a computer program product. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the vehicle driving behavior prediction method provided in the first aspect of the embodiment of the present application.
[0016] In a fifth aspect, an embodiment of the present application provides a vehicle, comprising at least one of the following items:
[0017] The vehicle driving behavior prediction device provided by the second aspect of the embodiment of the present application;
[0018] The electronic device provided by the third aspect of the embodiment of the present application;
[0019] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium.
[0020] In the embodiment of the present application, multiple images continuously collected at the first speed of the target vehicle are obtained; the first speed and the multiple images are input into the first vehicle driving behavior prediction model corresponding to the first speed to obtain the probability of each driving behavior that the target vehicle will have; the driving behavior corresponding to the maximum probability is determined as the target driving behavior that the target vehicle will have. In this way, the driving behavior that the vehicle will have can be predicted. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.
[0022] Figure 1 It is a flow chart of a vehicle driving behavior prediction method provided in an embodiment of the present application;
[0023] Figure 2 : is a schematic diagram of the system structure of a vehicle driving behavior prediction model for training provided in an embodiment of the present application;
[0024] Figure 3is a schematic diagram of the structure of a vehicle driving behavior prediction device provided in an embodiment of the present application;
[0025] Figure 4 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0026] In order to more clearly understand the above-mentioned purposes, features and advantages of the present application, the scheme of the present application will be further described below. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.
[0027] In the following description, many specific details are set forth to facilitate a full understanding of the present application, but the present application may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only part of the embodiments of the present application, rather than all of the embodiments.
[0028] The following, in conjunction with the accompanying drawings, describes in detail the vehicle driving behavior prediction method, device, equipment, medium, product and vehicle provided in the embodiments of the present application through specific embodiments and their application scenarios.
[0029] Figure 1 FIG. 1 is a flow chart of a vehicle driving behavior prediction method provided in an embodiment of the present application. Figure 1 As shown, the vehicle driving behavior prediction method may include:
[0030] Step 101: Acquire multiple images continuously captured of the target vehicle at a first speed;
[0031] Step 102: inputting the first speed and the plurality of images into a first vehicle driving behavior prediction model corresponding to the first speed, and obtaining the probability that the target vehicle will perform each driving behavior;
[0032] Step 103: Determine the driving behavior corresponding to the maximum probability as the target driving behavior to be performed by the target vehicle.
[0033] The specific implementation of each of the above steps will be described in detail below.
[0034] In the embodiment of the present application, multiple images continuously collected at the first speed of the target vehicle are obtained; the first speed and the multiple images are input into the first vehicle driving behavior prediction model corresponding to the first speed to obtain the probability of each driving behavior that the target vehicle will have; the driving behavior corresponding to the maximum probability is determined as the target driving behavior that the target vehicle will have. In this way, the driving behavior that the vehicle will have can be predicted.
[0035] In some possible implementations of the embodiment of the present application, in step 101, an independent camera or a driving recorder installed on the target vehicle may be used to collect images of the target vehicle during driving. The first speed is the current speed of the target vehicle.
[0036] In some possible implementations of the embodiments of the present application, in step 102, the vehicle driving behavior prediction model is used to calculate the probability of each driving behavior that the vehicle will have. Different vehicle driving behavior prediction models correspond to different speeds to predict each driving behavior that the vehicle will have at different speeds.
[0037] In some possible implementations of the embodiments of the present application, when there are multiple vehicle driving behavior prediction models corresponding to multiple speeds, before step 102, the vehicle driving behavior prediction method provided by the embodiments of the present application may further include:
[0038] A first vehicle driving behavior prediction model corresponding to a first speed is determined from a plurality of vehicle driving behavior prediction models, wherein the plurality of vehicle driving behavior prediction models correspond to a plurality of speeds, respectively.
[0039] After the first speed and the multiple images continuously collected at the first speed are input into the first vehicle driving behavior prediction model corresponding to the first speed, the first vehicle driving behavior prediction model corresponding to the first speed outputs the probability that the vehicle corresponding to the first speed will have each driving behavior. The greater the probability of a certain driving behavior output by the vehicle driving behavior prediction model, the more likely the driving behavior is to occur.
[0040] In some possible implementations of the embodiments of the present application, the vehicle driving behavior prediction method provided by the embodiments of the present application may also include: when the driving behavior that the target vehicle is about to perform is a dangerous driving behavior, playing a prompt message, wherein the prompt message is used to prompt the target user that the target vehicle is about to perform a target driving behavior or that the target vehicle is about to perform a dangerous driving behavior.
[0041] In some possible implementations of the embodiments of the present application, the dangerous driving behaviors in the embodiments of the present application include but are not limited to: emergency braking, vehicle collision, etc.
[0042] When the target driving behavior that the target vehicle is about to perform is a dangerous driving behavior, the driver can be prompted by voice broadcast through the vehicle audio to enable the driver to avoid the dangerous driving behavior in advance, for example, slow down the vehicle in advance to avoid emergency braking.
[0043] In the embodiment of the present application, by playing prompt information to remind the user that the vehicle is about to perform target driving behavior or dangerous driving behavior, the driver can avoid dangerous driving behavior in advance and ensure personal safety.
[0044] In some possible implementations of the embodiments of the present application, the vehicle driving behavior prediction method provided in the embodiments of the present application may also include: when the target driving behavior to be performed by the target vehicle is a dangerous driving behavior, sending first information to the vehicle automatic driving system, wherein the first information is used to instruct the vehicle automatic driving system to control the target vehicle not to perform a dangerous driving behavior.
[0045] Exemplarily, the first message sent to the vehicle's automatic driving system is "emergency braking is about to occur, please evade it in advance."
[0046] The embodiments of the present application do not limit the method used by the vehicle automatic driving system to control the target vehicle to prevent it from engaging in dangerous driving behavior. Any available method can be applied to the embodiments of the present application.
[0047] In an embodiment of the present application, by sending first information to the vehicle automatic driving system to instruct the vehicle automatic driving system to control the vehicle so as not to perform dangerous driving behavior, the vehicle automatic driving system can control the vehicle so as not to perform dangerous driving behavior and ensure personal safety.
[0048] In some possible implementations of the embodiments of the present application, the first vehicle driving behavior prediction model in the embodiments of the present application can be trained based on multiple historical images continuously collected before the vehicle occurs each driving behavior at the first speed.
[0049] The first vehicle driving behavior prediction model may be obtained by training the target vehicle or by training the server.
[0050] In some possible implementations of the embodiments of the present application, when the vehicle driving behavior prediction model is obtained by training the server, before step 101, the vehicle driving behavior prediction method provided by the embodiments of the present application may also include: when the target vehicle engages in dangerous driving behavior, sending a plurality of historical images continuously collected before the target vehicle engages in the dangerous driving behavior and the historical speed of the target vehicle when the dangerous driving behavior engages to the server, so that the server trains the vehicle driving behavior prediction models corresponding to different speeds; and receiving multiple vehicle driving behavior prediction models sent by the server.
[0051] Each vehicle can use an independent camera or driving recorder installed on the vehicle to collect images of the vehicle during driving, and then save the images at fixed time intervals, for example, save the images of the most recent 5 minutes.
[0052] When dangerous driving behavior occurs, the saved image is sent to the server, wherein the dangerous driving behavior in the embodiment of the present application includes but is not limited to: acceleration less than a preset acceleration threshold, emergency braking, collision behavior, etc.
[0053] The server stores the received images according to the speed ladder and the time ladder. For example, the images corresponding to the speed of 60KM / H are divided into one group, and the images corresponding to the speed of 80KM / H are divided into one group, and each group of images is stored. For each group of images, it can also be grouped according to time, for example, images of 10 seconds are grouped, and so on.
[0054] After receiving an image sent by a certain vehicle, the server can train the vehicle driving behavior prediction model, and can also regularly train the vehicle driving behavior prediction model corresponding to the speed using the image corresponding to the speed for different speeds. Then, multiple vehicle driving behavior prediction models corresponding to multiple speeds are sent to each vehicle, so that the vehicle can perform vehicle driving behavior prediction.
[0055] The embodiments of the present application do not limit the specific process of training the vehicle driving behavior prediction model. The training of the vehicle driving behavior prediction model can refer to the training process of the neural network model in the related art.
[0056] In some possible implementations of the embodiments of the present application, the neural network in the embodiments of the present application may be a convolutional neural network (CNN). Among them, the convolutional neural network is a type of feedforward neural network (FNN) that includes convolution calculations and has a deep structure, and is one of the representative algorithms of deep learning.
[0057] The convolutional neural network includes an input layer, a hidden layer and an output layer. The hidden layer includes a convolutional layer, a pooling layer and a fully connected layer. The convolutional layer of the convolutional layer extracts features from the input data. In combination with the vehicle driving behavior prediction method provided in the embodiment of the present application, the convolutional layer extracts features from the input image.
[0058] In some possible implementations of the embodiments of the present application, the convolution model of the convolution layer in the embodiments of the present application is as shown in formula (1).
[0059]
[0060] In formula (1), b is the deviation, Z L and Z l+1 represents the convolution input and output of the l+1th layer, L l+1 Z l+1 Z(i,j) corresponds to the pixels of the feature map, K is the number of channels of the feature map, f, s0 and p are the convolution layer parameters, corresponding to the convolution kernel size, convolution step size and number of padding layers respectively.
[0061] In some possible implementations of the embodiments of the present application, the pooling model of the pooling layer in the embodiments of the present application is as shown in formula (2).
[0062]
[0063] In formula (2), (i, j) represents a pixel, f is the convolution kernel size, s0 is the convolution step size, and p is a pre-specified parameter.
[0064] It can be understood that the pooling model shown in formula (2) is L p Pooling.
[0065] In some possible implementations of this embodiment, after a vehicle driving behavior prediction model corresponding to a certain speed is obtained through training, a first parameter value of a parameter of the vehicle driving behavior prediction model can also be obtained; based on the first parameter value, the parameter value of the parameter is adjusted to obtain a second parameter value of the parameter; based on the second parameter value, the vehicle driving behavior prediction model corresponding to the speed is retrained; if the accuracy of the retrained vehicle driving behavior prediction model corresponding to the speed is greater than or equal to the accuracy of the vehicle driving behavior prediction model corresponding to the speed before retraining, the retrained vehicle driving behavior prediction model corresponding to the speed is used as the final vehicle driving behavior prediction model corresponding to the speed; if the accuracy of the retrained vehicle driving behavior prediction model corresponding to the speed is less than the accuracy of the vehicle driving behavior prediction model corresponding to the speed before retraining, the vehicle driving behavior prediction model corresponding to the speed before retraining is used as the final vehicle driving behavior prediction model corresponding to the speed.
[0066] Exemplarily, it is assumed that corresponding vehicle driving behavior prediction models of 40km / h, 60km / h, and 80km / h are obtained through training.
[0067] For the vehicle driving behavior prediction model at 40km / h, the parameter value of the model parameter is obtained, the parameter value of the model parameter is adjusted based on the parameter value, and the neural network is retrained based on the adjusted parameter value using the image corresponding to 40km / h to obtain the vehicle driving behavior prediction model corresponding to the parameter adjustment. If the accuracy of the vehicle driving behavior prediction model corresponding to the parameter adjustment is greater than or equal to the accuracy of the vehicle driving behavior prediction model corresponding to the parameter adjustment before the parameter adjustment, the vehicle driving behavior prediction model corresponding to the parameter adjustment is used as the final vehicle driving behavior prediction model corresponding to 40km / h; if the accuracy of the vehicle driving behavior prediction model corresponding to the parameter adjustment is less than the accuracy of the vehicle driving behavior prediction model corresponding to the parameter adjustment before the parameter adjustment, the vehicle driving behavior prediction model corresponding to the parameter adjustment before the parameter adjustment is used as the final vehicle driving behavior prediction model corresponding to 40km / h.
[0068] Similarly, a vehicle driving behavior prediction model corresponding to 60 km / h and a vehicle driving behavior prediction model corresponding to 80 km / h can be obtained.
[0069] In some possible implementations of the embodiments of the present application, when the parameter value of a parameter is adjusted based on a first parameter value to obtain a second parameter value of the parameter, an adjustment value for the parameter adjustment can be determined based on the first parameter value, and the parameter adjustment can be performed based on the adjustment value.
[0070] In some possible implementations of the embodiments of the present application, when determining the adjustment value for parameter adjustment based on the first parameter value, the minimum value with the same precision as the first parameter value may be determined as the adjustment value for parameter adjustment.
[0071] Exemplarily, assuming that the parameter value of a certain parameter is 1.245, and the parameter precision is three decimal places, that is, one thousandth, then the parameter adjustment value is determined to be 0.001.
[0072] Figure 2 1 is a schematic diagram of the system structure of the vehicle driving behavior prediction model training provided in the embodiment of the present application. The system for training the vehicle driving behavior prediction model includes a server and N vehicles, wherein the N vehicles are vehicles 1 to N respectively.
[0073] Vehicles 1 to N collect images during driving and store the collected images locally.
[0074] When a vehicle engages in dangerous driving behavior, its locally stored images are sent to the server.
[0075] After receiving an image sent by any vehicle, the server may start training the vehicle driving behavior prediction model, or, when the vehicle driving behavior prediction model retraining cycle is reached, start training the vehicle driving behavior prediction model.
[0076] After training the multiple vehicle driving behavior prediction models, the server sends the multiple vehicle driving behavior prediction models to vehicles 1 to N.
[0077] Vehicles 1 to N collect images during driving and predict the driving behavior to be occurred based on receiving multiple vehicle driving behavior prediction models.
[0078] Corresponding to the above method embodiment, the present application embodiment also provides a vehicle driving behavior prediction device. Figure 3 As shown, Figure 3 300 is a schematic diagram of the structure of a vehicle driving behavior prediction device provided in an embodiment of the present application. The vehicle driving behavior prediction device 300 may include:
[0079] A first acquisition module 301 is used to acquire a plurality of images continuously collected from the target vehicle at a first speed;
[0080] The probability determination module 302 is used to input the first speed and the multiple images into a first vehicle driving behavior prediction model corresponding to the first speed to obtain the probability that the target vehicle will perform each driving behavior;
[0081] The prediction module 303 is used to determine the driving behavior corresponding to the maximum probability as the target driving behavior that the target vehicle will take.
[0082] In the embodiment of the present application, multiple images continuously collected at the first speed of the target vehicle are obtained; the first speed and the multiple images are input into the first vehicle driving behavior prediction model corresponding to the first speed to obtain the probability of each driving behavior that the target vehicle will have; the driving behavior corresponding to the maximum probability is determined as the target driving behavior that the target vehicle will have. In this way, the driving behavior that the vehicle will have can be predicted.
[0083] In some possible implementations of the embodiments of the present application, the vehicle driving behavior prediction device 300 provided in the embodiments of the present application may further include:
[0084] A playback module is used to play a prompt message when the target vehicle is about to perform a dangerous driving behavior, wherein the prompt message is used to prompt a target user that the target vehicle is about to perform a target driving behavior or that the target vehicle is about to perform a dangerous driving behavior; or,
[0085] The first sending module is used to send first information to the vehicle automatic driving system, wherein the first information is used to instruct the vehicle automatic driving system to control the target vehicle to avoid dangerous driving behavior.
[0086] In the embodiment of the present application, by playing a prompt message for reminding the user that the vehicle is about to perform a target driving behavior or a dangerous driving behavior, the driver can avoid the dangerous driving behavior in advance and ensure personal safety. By sending information to the vehicle automatic driving system for instructing the vehicle automatic driving system to control the vehicle not to perform a dangerous driving behavior, the vehicle automatic driving system can control the vehicle not to perform a dangerous driving behavior and ensure personal safety.
[0087] In some possible implementations of the embodiments of the present application, the first vehicle driving behavior prediction model is trained based on a plurality of historical images continuously collected before each driving behavior of the vehicle occurs at the first speed.
[0088] In some possible implementations of the embodiments of the present application, the vehicle driving behavior prediction device 300 provided in the embodiments of the present application may further include:
[0089] The determination module is used to determine a first vehicle driving behavior prediction model corresponding to a first speed from a plurality of vehicle driving behavior prediction models, wherein the plurality of vehicle driving behavior prediction models correspond to a plurality of speeds respectively.
[0090] In some possible implementations of the embodiments of the present application, the vehicle driving behavior prediction device 300 provided in the embodiments of the present application may further include:
[0091] The second sending module is used to send a plurality of historical images continuously collected before the target vehicle has the dangerous driving behavior and the historical speed of the target vehicle when the dangerous driving behavior occurs to the server when the target vehicle has the dangerous driving behavior, so that the server can train the vehicle driving behavior prediction model corresponding to different speeds;
[0092] The receiving module is used to receive multiple vehicle driving behavior prediction models sent by the server.
[0093] Figure 4 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application.
[0094] The electronic device may include a processor 401 and a memory 402 storing computer program instructions.
[0095] Specifically, the processor 401 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.
[0096] Memory 402 may include a large capacity memory for data or instructions. By way of example and not limitation, memory 402 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, memory 402 may include a removable or non-removable (or fixed) medium. In appropriate cases, memory 402 may be inside or outside of an electronic device. In some specific embodiments, memory 402 is a non-volatile solid-state memory.
[0097] In some specific embodiments, the memory may include a read-only memory (ROM), a random access memory (RAM), a disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Therefore, generally, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the vehicle driving behavior prediction method according to the present application.
[0098] The processor 401 implements the vehicle driving behavior prediction method provided in the embodiment of the present application by reading and executing the computer program instructions stored in the memory 402.
[0099] In some examples, the electronic device may further include a communication interface 403 and a bus 410. Figure 4 As shown, the processor 401, the memory 402, and the communication interface 403 are connected via a bus 410 and communicate with each other.
[0100] The communication interface 403 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.
[0101] The bus 410 includes hardware, software or both, coupling the components of the electronic device to each other. For example, but not limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro channel architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus or other suitable buses or a combination of two or more of these. Where appropriate, the bus 410 may include one or more buses. Although embodiments of the present application describe and illustrate a particular bus, the present application contemplates any suitable bus or interconnect.
[0102] The electronic device can execute the vehicle driving behavior prediction method provided in the embodiment of the present application, thereby achieving the corresponding technical effects of the vehicle driving behavior prediction method provided in the embodiment of the present application.
[0103] In addition, in combination with the vehicle driving behavior prediction method in the above embodiment, the embodiment of the present application also provides a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; when the computer program instructions are executed by the processor, the vehicle driving behavior prediction method provided in the embodiment of the present application is implemented. Examples of computer-readable storage media include non-transitory computer-readable media, such as ROM, RAM, magnetic disk or optical disk, etc.
[0104] An embodiment of the present application also provides a computer program product. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the vehicle driving behavior prediction method provided in the embodiment of the present application and can achieve the same technical effect. To avoid repetition, it will not be repeated here.
[0105] The present application also provides a vehicle, which includes at least one of the following items:
[0106] The vehicle driving behavior prediction device provided in the embodiment of the present application;
[0107] The electronic device provided by the embodiment of the present application;
[0108] The computer-readable storage medium provided by the embodiments of the present application.
[0109] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprises" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.
Claims
1. A vehicle driving behavior prediction method, characterized in that: The method comprises: Acquire multiple images continuously collected of the target vehicle at a first speed; Inputting the first speed and the plurality of images into a first vehicle driving behavior prediction model corresponding to the first speed to obtain a probability that the target vehicle will perform each driving behavior; The driving behavior corresponding to the maximum probability is determined as the target driving behavior that will occur for the target vehicle.
2. The method according to claim 1, characterized in that In the case where the target driving behavior is a dangerous driving behavior, the method further includes: Playing prompt information, wherein the prompt information is used to prompt the target user that the target vehicle is about to perform the target driving behavior or the target vehicle is about to perform a dangerous driving behavior; or, Sending first information to the vehicle automatic driving system, wherein the first information is used to instruct the vehicle automatic driving system to control the target vehicle not to perform the target driving behavior.
3. The method according to claim 1, characterized in that The first vehicle driving behavior prediction model is trained based on a plurality of historical images continuously collected before each driving behavior of the vehicle occurs at the first speed.
4. The method according to claim 1, characterized in that Before inputting the first speed and the plurality of images into a first vehicle driving behavior prediction model corresponding to the first speed to obtain the probability that the target vehicle will perform each driving behavior, the method further includes: The first vehicle driving behavior prediction model corresponding to the first speed is determined from a plurality of vehicle driving behavior prediction models, wherein the plurality of vehicle driving behavior prediction models correspond to a plurality of speeds, respectively.
5. The method according to claim 4, characterized in that Before acquiring a plurality of images continuously captured from the target vehicle at the first speed, the method further includes: When the target vehicle has a dangerous driving behavior, a plurality of historical images continuously collected before the target vehicle has the dangerous driving behavior and the historical speed of the target vehicle when the dangerous driving behavior has occurred are sent to a server, so that the server can train a vehicle driving behavior prediction model corresponding to different speeds; Receive the multiple vehicle driving behavior prediction models sent by the server.
6. A vehicle driving behavior prediction device, characterized in that: The device comprises: A first acquisition module is used to acquire a plurality of images continuously collected from the target vehicle at a first speed; a probability determination module, configured to input the first speed and the plurality of images into a first vehicle driving behavior prediction model corresponding to the first speed, and obtain a probability that the target vehicle will perform each driving behavior; The prediction module is used to determine the driving behavior corresponding to the maximum probability as the target driving behavior that will occur for the target vehicle.
7. An electronic device, characterized in that: The electronic device comprises: a processor and a memory storing computer program instructions; The processor reads and executes the computer program instructions to implement the vehicle driving behavior prediction method as described in any one of claims 1-5.
8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the vehicle driving behavior prediction method according to any one of claims 1 to 5 is implemented.
9. A computer program product, characterized in that When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the vehicle driving behavior prediction method as described in any one of claims 1-5.
10. A vehicle, characterized in that: The vehicle includes at least one of the following: The vehicle driving behavior prediction device according to claim 6; The electronic device according to claim 7; The computer readable storage medium of claim 8.