Vehicle driving condition recognition method and system, vehicle and storage medium

Abstract

The application discloses a vehicle driving condition recognition method and system, a vehicle and a storage medium, wherein the vehicle driving condition recognition method comprises the following steps: acquiring vehicle driving data; segmenting a driving process of the vehicle according to the vehicle driving data to obtain a plurality of driving segments; determining a plurality of gray images corresponding to the plurality of driving segments according to the vehicle driving data corresponding to the plurality of driving segments, wherein the gray images are used to represent driving condition characteristics of the corresponding driving segments; and determining a driving condition recognition result according to the gray images and a preset condition image library. The application solves the technical problem that the existing driving condition recognition method does not cover comprehensive condition scenes.

Description

Technical Field

[0001] This invention relates to the field of intelligent driving technology, and more specifically, to a method, system, vehicle, and storage medium for identifying vehicle driving conditions. Background Technology

[0002] Vehicle driving conditions typically include acceleration, deceleration, cruising, turning, lane changing, U-turns, and coupled driving conditions. Dividing the driving process into segments based on these driving conditions facilitates analysis of user behavior, driving habits, and driving style recognition, or allows for the construction of new driving processes based on segments of driving behavior. However, existing methods for identifying vehicle driving behavior conditions based solely on the vehicle's own information, without utilizing information from other vehicles in the traffic flow, require comparing and judging multiple signals. This involves numerous scenarios, making exhaustive enumeration difficult and resulting in insufficient coverage of driving conditions. Summary of the Invention

[0003] This invention provides a vehicle driving condition identification method, system, vehicle, and storage medium to at least solve the technical problem that existing driving condition identification methods do not cover a comprehensive range of driving conditions.

[0004] According to a first aspect of the present invention, a vehicle driving condition recognition method is provided. The vehicle driving condition recognition method includes: acquiring vehicle driving data; segmenting the vehicle driving process according to the vehicle driving data to obtain multiple driving segments; determining grayscale images corresponding to the multiple driving segments according to the vehicle driving data corresponding to the multiple driving segments, wherein the grayscale images are used to characterize the driving condition features of the corresponding driving segments; and determining the driving condition recognition result according to the grayscale images and a preset driving condition image library.

[0005] Optionally, the driving segment includes a lateral driving segment and a longitudinal driving segment; based on the vehicle driving data, the vehicle's driving process is segmented to obtain multiple driving segments, including: determining the lateral short-time average energy within a first preset time interval based on the yaw rate in the vehicle driving data, and determining the longitudinal short-time average energy within a second preset time interval based on the longitudinal acceleration in the vehicle driving data, wherein the lateral short-time average energy is used to characterize the change of the yaw rate within the first preset time interval, and the longitudinal short-time average energy is used to characterize the change of the longitudinal acceleration within the second preset time interval; multiple lateral driving segments are determined based on the lateral short-time average energy, and multiple longitudinal driving segments are determined based on the longitudinal short-time average energy.

[0006] Optionally, determining the grayscale image corresponding to multiple driving segments based on vehicle driving data corresponding to multiple driving segments includes: resampling the vehicle driving data corresponding to multiple driving segments to obtain multiple data sequences; normalizing the multiple data sequences to obtain a data grayscale value sequence; determining a grayscale matrix based on the multiple data grayscale value sequences; and determining the grayscale image based on the grayscale matrix using a preset conversion algorithm.

[0007] Optionally, the preset working condition image library includes multiple preset working condition images. Constructing preset working condition images includes: constructing simulation scenarios for various driving conditions; for each driving condition, performing working condition simulation in the simulation scenario to obtain simulation data; and determining the preset working condition image template based on the simulation data.

[0008] Optionally, multiple driving conditions include any one or a combination of the following: acceleration, deceleration, cruise, lane keeping, lane changing, turning, U-turn, roundabout, and ramp.

[0009] Optionally, determining the driving condition recognition result based on the grayscale image and a preset working condition image library includes: using a preset image matching algorithm to match the grayscale image with the working condition images in the preset working condition image library to obtain a matching result; and determining the driving condition recognition result based on the matching result.

[0010] Optionally, determining the driving condition recognition result based on the grayscale image and the preset driving condition image library includes: using a preset driving condition recognition model to recognize the grayscale image to obtain the driving condition recognition result, wherein the preset driving condition recognition model is trained based on the preset driving condition image library.

[0011] According to a second aspect of the present invention, a vehicle driving condition recognition system is also provided, comprising: an acquisition module for acquiring vehicle driving data; a segmentation module for segmenting the vehicle driving process according to the vehicle driving data to obtain multiple driving segments; a first determination module for determining grayscale images corresponding to the multiple driving segments according to the vehicle driving data corresponding to the multiple driving segments, wherein the grayscale images are used to characterize the driving condition features of the corresponding driving segments; and a second determination module for determining the driving condition recognition result according to the grayscale images and a preset driving condition image library.

[0012] Optionally, the driving segment includes a lateral driving segment and a longitudinal driving segment; the segmentation module is further configured to: determine the lateral short-time average energy within a first preset time interval based on the yaw rate in the vehicle driving data, and determine the longitudinal short-time average energy within a second preset time interval based on the longitudinal acceleration in the vehicle driving data, wherein the lateral short-time average energy is used to characterize the change of the yaw rate within the first preset time interval, and the longitudinal short-time average energy is used to characterize the change of the longitudinal acceleration within the second preset time interval; determine multiple lateral driving segments based on the lateral short-time average energy, and determine multiple longitudinal driving segments based on the longitudinal short-time average energy.

[0013] Optionally, the first determining module is further configured to: resample vehicle driving data corresponding to multiple driving segments to obtain multiple data sequences; normalize the multiple data sequences to obtain a data grayscale value sequence; determine a grayscale matrix based on the multiple data grayscale value sequences; and determine a grayscale image based on the grayscale matrix using a preset conversion algorithm.

[0014] Optionally, the preset working condition image library includes multiple preset working condition images, and the vehicle driving condition recognition system also includes a construction module, which is used to: construct simulation scenarios of multiple driving conditions; for each driving condition, perform working condition simulation in the simulation scenario to obtain simulation data; and determine the preset working condition image template based on the simulation data.

[0015] Optionally, the various driving conditions constructed by the building module include any one or more combinations of the following: acceleration condition, deceleration condition, cruise condition, lane keeping condition, lane changing condition, turning condition, U-turn condition, roundabout condition, and ramp condition.

[0016] Optionally, the second determining module is further configured to: use a preset image matching algorithm to match the grayscale image with the working condition images in the preset working condition image library to obtain the matching result; and determine the driving working condition recognition result based on the matching result.

[0017] Optionally, the second determining module is further configured to: use a preset driving condition recognition model to recognize the grayscale image and obtain the driving condition recognition result, wherein the preset driving condition recognition model is trained based on a preset driving condition image library.

[0018] According to a third aspect of the present invention, a vehicle is also provided, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the vehicle driving condition identification method described in any of the embodiments of the first aspect.

[0019] According to a fourth aspect of the present invention, a non-volatile storage medium is also provided, wherein a computer program is stored in the non-volatile storage medium, and the computer program is configured to execute the vehicle driving condition identification method described in any embodiment of the first aspect when running on a computer or processor.

[0020] In this embodiment of the invention, the vehicle's driving process is segmented based on vehicle driving data to obtain multiple driving segments. Based on the vehicle driving data corresponding to these segments, grayscale images corresponding to each segment are determined. These grayscale images represent the driving condition characteristics of the corresponding driving segment. The driving condition recognition result is determined based on the grayscale images and a preset driving condition image library. First, grayscale images corresponding to the driving segments are constructed. Then, the driving condition recognition result is determined based on the grayscale images and the preset driving condition image library. This effectively represents multiple signals in a single driving segment in the grayscale images. The preset driving condition image library provides multiple driving condition images for driving condition recognition, thereby solving the technical problem of insufficient coverage of driving condition scenarios in existing driving condition recognition methods. Attached Figure Description

[0021] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0022] Figure 1 This is a flowchart of a vehicle driving condition identification method according to one embodiment of the present invention;

[0023] Figure 2 This is a schematic diagram of the first data change according to one embodiment of the present invention;

[0024] Figure 3 This is a schematic diagram of a second data change according to one embodiment of the present invention;

[0025] Figure 4 This is a schematic diagram of a first grayscale image according to one embodiment of the present invention;

[0026] Figure 5 This is a schematic diagram of a second grayscale image according to one embodiment of the present invention;

[0027] Figure 6 This is a structural block diagram of a vehicle driving condition recognition system according to one embodiment of the present invention. Detailed Implementation

[0028] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] According to an embodiment of the present invention, an embodiment of a vehicle driving condition identification method is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system containing at least a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0031] This method embodiment can also be executed in an electronic device, similar control device, or vehicle-mounted terminal that includes a memory and a processor. Taking a vehicle-mounted terminal as an example, the vehicle-mounted terminal may include one or more processors and a memory for storing data. Optionally, the vehicle-mounted terminal may also include a communication device for communication functions and a display device. Those skilled in the art will understand that the above structural description is merely illustrative and does not limit the structure of the vehicle-mounted terminal. For example, the vehicle-mounted terminal may include more or fewer components than those described above, or have a different configuration than those described above.

[0032] A processor may include one or more processing units. For example, a processor may include a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processing (DSP) chip, a microcontroller unit (MCU), a field-programmable gate array (FPGA), a neural network processing unit (NPU), a tensor processing unit (TPU), or an artificial intelligence (AI) processor. Different processing units may be independent components or integrated into one or more processors. In some instances, electronic devices may also include one or more processors.

[0033] The memory can be used to store computer programs, such as the computer program corresponding to the vehicle driving condition recognition method in this embodiment of the invention. The processor implements the aforementioned vehicle driving condition recognition method by running the computer program stored in the memory. The memory may include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to electronic devices via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0034] The communication device is used to receive or send data via a network. Specific examples of the network mentioned above may include a wireless network provided by the mobile terminal's communication provider. In one example, the communication device includes a network interface controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the communication device may be a radio frequency (RF) module, used for wireless communication with the Internet. In some embodiments of this solution, the communication device is used to connect to mobile devices such as mobile phones and tablets, enabling the mobile device to send commands to the vehicle-mounted terminal.

[0035] The display device can be a touchscreen liquid crystal display (LCD) or a touch display (also referred to as a "touchscreen" or "touch screen"). This LCD allows the user to interact with the user interface of the in-vehicle terminal. In some embodiments, the in-vehicle terminal has a graphical user interface (GUI), allowing the user to interact with the GUI through finger contact and / or gestures on a touch-sensitive surface. Executable instructions for performing these human-machine interaction functions are configured / stored in one or more processor-executable computer program products or readable storage media.

[0036] Figure 1 This is a flowchart of a vehicle driving condition recognition method according to one embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0037] Step S101: Obtain vehicle driving data.

[0038] Specifically, the vehicle generates driving data during operation, which can then be obtained through the vehicle bus.

[0039] Step S102: Based on the vehicle driving data, the vehicle driving process is segmented to obtain multiple driving segments.

[0040] Specifically, the entire driving process of a vehicle can be divided into multiple driving segments based on the vehicle's driving data. These segments are continuous throughout the entire driving process, but the driving conditions corresponding to two adjacent segments are different.

[0041] Optionally, in some embodiments of the present invention, when segmenting the vehicle's driving process, the vehicle can be segmented in real time, or multiple driving segments can be divided at once based on all driving data from the start to the shutdown of the vehicle.

[0042] Step S103: Determine the grayscale images corresponding to multiple driving segments based on the vehicle driving data corresponding to multiple driving segments.

[0043] Specifically, grayscale images are used to represent the driving condition characteristics of corresponding driving segments. Different driving segments have different driving condition characteristics, and therefore different grayscale images are determined.

[0044] Understandably, the various driving data corresponding to each driving segment are represented in the grayscale image.

[0045] Optionally, in some embodiments of the present invention, the grayscale image can also be determined in real time based on the vehicle driving data corresponding to each driving segment. That is, for each driving segment, the grayscale image corresponding to the driving segment is determined based on the driving data corresponding to the driving segment.

[0046] Step S104: Determine the driving condition recognition result based on the grayscale image and the preset working condition image library.

[0047] Specifically, after determining the grayscale image corresponding to each driving segment, the driving condition recognition result can be determined based on the grayscale image and the preset driving condition image library, with each grayscale image corresponding to a driving condition.

[0048] In this embodiment of the invention, the vehicle's driving process is segmented based on vehicle driving data to obtain multiple driving segments. Based on the vehicle driving data corresponding to these segments, grayscale images corresponding to each segment are determined. These grayscale images represent the driving condition characteristics of the corresponding driving segment. The driving condition recognition result is determined based on the grayscale images and a preset driving condition image library. First, grayscale images corresponding to the driving segments are constructed. Then, the driving condition recognition result is determined based on the grayscale images and the preset driving condition image library. This effectively represents multiple signals in a single driving segment in the grayscale images. The preset driving condition image library provides multiple driving condition images for driving condition recognition, thereby solving the technical problem of insufficient coverage of driving condition scenarios in existing driving condition recognition methods.

[0049] Optionally, the driving segment includes lateral driving segments and longitudinal driving segments. In step S102, segmenting the vehicle's driving process into multiple driving segments based on the vehicle driving data may include the following steps:

[0050] Step S1021: Based on the yaw rate in the vehicle driving data, determine the lateral short-time average energy within a first preset time interval, and based on the longitudinal acceleration in the vehicle driving data, determine the longitudinal short-time average energy within a second preset time interval. The lateral short-time average energy is used to characterize the change of the yaw rate within the first preset time interval, and the longitudinal short-time average energy is used to characterize the change of the longitudinal acceleration within the second preset time interval.

[0051] Specifically, the formula for determining the transverse short-time average energy within the first preset time interval is as follows:

[0052]

[0053] Where Eh is the transverse short-time average energy, in units of (° / s). 2ω is the yaw rate, which can be obtained by a sensor and is in ° / s. k is the average energy duration range, k = T1 / dt, where dt is the time interval for sampling the yaw rate, and T1 is the preset time for calculating the short-term average energy of the yaw rate, i.e., the first preset time interval.

[0054] Specifically, the formula for determining the longitudinal short-time average energy within the second preset time interval is as follows:

[0055]

[0056] Where Ez is the longitudinal short-time average energy, in units of (m / s) 2 ) 2 'a' represents longitudinal acceleration, which can be obtained from a sensor and is measured in m / s². 2 k is the average energy duration range, k = T2 / dt, dt is the time interval for sampling longitudinal acceleration, and T2 is the preset time for calculating the short-time average energy of yaw rate, i.e., the second preset time interval.

[0057] It should be noted that minor, unconscious steering maneuvers by the driver are characterized by their short duration or small peak yaw rate. By selecting appropriate calculation time ranges T1 and T2, the amplitudes of Eh and Ez can effectively distinguish minor, unconscious driving maneuvers from normal driving maneuvers. Furthermore, T1 and T2 can be preset based on experimental data and actual needs.

[0058] Optionally, in some embodiments of the present invention, T1 and T2 are 2 seconds.

[0059] Step S1022: Determine multiple lateral travel segments based on the lateral short-time average energy, and determine multiple longitudinal travel segments based on the longitudinal short-time average energy.

[0060] Specifically, when determining a lateral driving segment, the start time of a lateral driving segment is defined as when the short-term average lateral energy exceeds a first preset energy threshold. The short-term average lateral energy is then continuously monitored, and the end time of the current lateral driving segment is defined as when the short-term average lateral energy falls below a second preset energy threshold. A lateral driving segment is determined from the aforementioned start time to the end time.

[0061] It should be noted that the second preset energy threshold is less than the first preset energy threshold.

[0062] Specifically, when determining a longitudinal driving segment, the start time of a longitudinal driving segment is defined as when the longitudinal short-time average energy is greater than a third preset energy threshold. Then, the longitudinal short-time average energy is continuously assessed, and the end time of the current longitudinal driving segment is defined as when the longitudinal short-time average energy is less than a fourth preset energy threshold. The aforementioned start time to end time determines a longitudinal driving segment.

[0063] It should be noted that the fourth preset energy threshold is less than the third preset energy threshold.

[0064] It should be noted that the first preset energy threshold, the second preset energy threshold, the third preset energy threshold, and the fourth preset energy threshold are set according to actual needs.

[0065] Optionally, in some embodiments of the present invention, in addition to lateral travel segments and longitudinal travel segments, other travel segments, such as parking segments, are also included. Travel segments that do not belong to either lateral or longitudinal travel segments during vehicle movement are classified as other travel segments.

[0066] For example, refer to Figure 2 , Figure 2 The diagram illustrates the changes in vehicle speed, yaw rate energy (short-term average lateral energy), and longitudinal acceleration energy (short-term average longitudinal energy) over a given period. Specifically, in the time interval around 20 seconds, the vehicle speed continuously increases, with high longitudinal acceleration energy and low yaw rate energy; this period is classified as a longitudinal travel segment. In the time interval around 60 seconds, the vehicle speed remains stable, but yaw rate energy is high while longitudinal acceleration energy is low; this period is classified as a lateral travel segment. In the time intervals around 80 seconds and 100 seconds, the vehicle speed first decreases and then increases, with longitudinal acceleration energy lower than yaw rate energy; these two periods are classified as lateral travel segments. In the time interval from 140 to 160 seconds, the vehicle speed continuously decreases, with longitudinal acceleration energy higher than yaw rate energy; this period is classified as a longitudinal travel segment.

[0067] It should be noted that time periods not divided into lateral or longitudinal driving segments are classified as other driving segments, such as the time period corresponding to time node 120 seconds to 140 seconds.

[0068] Optionally, in step S103, determining the grayscale images corresponding to multiple driving segments based on the vehicle driving data corresponding to multiple driving segments may include the following steps:

[0069] Step S1031: Resample the vehicle driving data corresponding to multiple driving segments to obtain multiple data sequences.

[0070] Specifically, each data point in the vehicle driving data corresponding to each driving segment is resampled to obtain a data sequence for each data point, where the sampling interval is a preset sampling interval. Resampling the vehicle driving data corresponding to multiple driving segments yields multiple data sequences. A data sequence is represented as X. i =[x i1 ,x i2 ,...,x in ], where n is the number of data collection points included after resampling the vehicle driving data.

[0071] Optionally, the preset sampling interval is 0.25 seconds.

[0072] Step S1032: Normalize multiple data sequences to obtain a data grayscale value sequence.

[0073] Specifically, multiple data sequences are normalized using a normalization algorithm to transform them into a data grayscale value sequence, where each data sequence corresponds to a data grayscale value sequence.

[0074] For example, Among them, Y i Given a grayscale value sequence, min() and max() represent the minimum and maximum values ​​of the data sequence, respectively.

[0075] Step S1033: Determine the grayscale matrix based on multiple data grayscale value sequences.

[0076] Specifically, the grayscale matrix is ​​represented as follows:

[0077]

[0078] Where M represents the number of data types in the vehicle driving data.

[0079] Optionally, in some embodiments of the present invention, the types of data in the vehicle driving data include, but are not limited to: vehicle speed, yaw rate, longitudinal vehicle speed, lateral vehicle speed, longitudinal acceleration, accelerator pedal opening, braking pressure, steering wheel angle, yaw rate of change, and longitudinal acceleration rate of change.

[0080] For example, refer to Figure 3 , Figure 3 The diagram illustrates the variations in yaw angle, lateral acceleration Ay, yaw rate, and longitudinal acceleration curve Ax during a lateral driving segment. Specifically, in this segment, the longitudinal acceleration curve fluctuates by no more than 2, the yaw angle fluctuates by a maximum of 4, the yaw rate fluctuates by approximately 5, and the lateral acceleration Ay varies significantly when the yaw rate changes greatly.

[0081] Step S1034: Determine the grayscale image using a preset conversion algorithm based on the grayscale matrix.

[0082] For example, refer to Figure 4 , Figure 4 This is a grayscale image corresponding to a driving segment, which is obtained by converting the grayscale matrix using a preset conversion algorithm.

[0083] Optionally, the preset working condition image library includes multiple preset working condition images. Constructing preset working condition images includes: constructing simulation scenarios for various driving conditions; for each driving condition, performing working condition simulation in the simulation scenario to obtain simulation data; and determining the preset working condition image template based on the simulation data.

[0084] Specifically, by using vehicle dynamics simulation software, simulation scenarios for each driving condition are established, typical driving processes for each driving condition are obtained, and a preset image template representing the driving condition is generated based on the simulation data generated during the driving process.

[0085] For example, refer to Figure 5 , Figure 5 It is a preset working condition image template corresponding to a certain driving condition.

[0086] Optionally, multiple driving conditions include any one or a combination of the following: acceleration, deceleration, cruise, lane keeping, lane changing, turning, U-turn, roundabout, and ramp.

[0087] Optionally, determining the driving condition recognition result based on the grayscale image and a preset working condition image library includes: using a preset image matching algorithm to match the grayscale image with the working condition images in the preset working condition image library to obtain a matching result; and determining the driving condition recognition result based on the matching result.

[0088] For example, based on a preset image matching algorithm, a similarity match is performed between the grayscale image to be matched and the working condition images in a preset working condition image library. This invention does not limit the image matching algorithm. Histogram method, cosine similarity, difference hashing algorithm, SSIM (structural similarity measure), etc., can be used.

[0089] Taking the cosine similarity algorithm as an example, an image is represented as a vector. The cosine distance between the vectors is used to characterize the similarity between two images. If the absolute value of the similarity is greater than the preset similarity threshold, the match is successful and the matching result is obtained.

[0090] Understandably, based on the matching results, the working condition images in the preset working condition image library that have been successfully matched are determined, and the driving condition corresponding to the working condition image is further determined as the driving condition recognition result.

[0091] Optionally, the preset similarity threshold is 0.9.

[0092] Optionally, determining the driving condition recognition result based on the grayscale image and the preset driving condition image library includes: using a preset driving condition recognition model to recognize the grayscale image to obtain the driving condition recognition result, wherein the preset driving condition recognition model is trained based on the preset driving condition image library.

[0093] Specifically, preset driving condition images in the preset driving condition image library are used as training samples to train a preset driving condition recognition model. The preset driving condition recognition model can recognize the input grayscale image and output the driving condition recognition result.

[0094] For example, taking a convolutional neural network classification algorithm, we construct a convolutional layer, a fully connected layer, and a classifier. Specifically, the convolutional layer uses the sliding of the convolutional kernel to extract local features of the image, such as edge features in a certain direction. Multiple kernels are used for simultaneous convolution to generate a multi-dimensional local feature map. A fully connected layer follows the convolutional layer to integrate all the local information from the convolutional pooling to obtain global information, which is then input into the classifier. The classifier is a fully connected layer based on the SOFTMAX function (normalized exponential function), and its output is a two-dimensional probability feature vector, representing the probability that the image features belong to a certain driving condition.

[0095] It should be noted that the preset working condition recognition model can be optimized through supervised training during training.

[0096] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0097] This embodiment also provides a vehicle driving condition recognition system, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" refers to a combination of software and / or hardware capable of performing a predetermined function. Although the system described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0098] Figure 6This is a structural block diagram of a vehicle driving condition recognition system 200 according to one embodiment of the present invention, as shown below. Figure 6 As shown, a vehicle driving condition recognition system 200 is used as an example. The system includes: an acquisition module 201 for acquiring vehicle driving data; a segmentation module 202 for segmenting the vehicle's driving process into multiple driving segments based on the vehicle driving data; a first determination module 203 for determining grayscale images corresponding to multiple driving segments based on the vehicle driving data corresponding to the multiple driving segments, wherein the grayscale images are used to characterize the driving condition features of the corresponding driving segments; and a second determination module 204 for determining the driving condition recognition result based on the grayscale images and a preset driving condition image library.

[0099] Optionally, the driving segment includes a lateral driving segment and a longitudinal driving segment; the segmentation module 202 is further configured to: determine the lateral short-time average energy within a first preset time interval based on the yaw rate in the vehicle driving data, and determine the longitudinal short-time average energy within a second preset time interval based on the longitudinal acceleration in the vehicle driving data, wherein the lateral short-time average energy is used to characterize the change of the yaw rate within the first preset time interval, and the longitudinal short-time average energy is used to characterize the change of the longitudinal acceleration within the second preset time interval; determine multiple lateral driving segments based on the lateral short-time average energy, and determine multiple longitudinal driving segments based on the longitudinal short-time average energy.

[0100] Optionally, the first determining module 203 is further configured to: resample the vehicle driving data corresponding to multiple driving segments to obtain multiple data sequences; normalize the multiple data sequences to obtain a data grayscale value sequence; determine a grayscale matrix based on the multiple data grayscale value sequences; and determine a grayscale image based on the grayscale matrix using a preset conversion algorithm.

[0101] Optionally, the preset working condition image library includes multiple preset working condition images. The vehicle driving condition recognition system also includes a construction module (not shown in the figure). The construction module is connected to the second determining module 204. The construction module is used to: construct simulation scenarios of multiple driving conditions; perform working condition simulation in the simulation scenario for each driving condition to obtain simulation data; and determine the preset working condition image template based on the simulation data.

[0102] Optionally, the various driving conditions constructed by the building module include any one or more combinations of the following: acceleration condition, deceleration condition, cruise condition, lane keeping condition, lane changing condition, turning condition, U-turn condition, roundabout condition, and ramp condition.

[0103] Optionally, the second determining module 204 is further configured to: use a preset image matching algorithm to match the grayscale image with the working condition images in the preset working condition image library to obtain a matching result; and determine the driving working condition recognition result based on the matching result.

[0104] Optionally, the second determining module 204 is further configured to: use a preset driving condition recognition model to recognize the grayscale image and obtain the driving condition recognition result, wherein the preset driving condition recognition model is trained based on a preset driving condition image library.

[0105] Embodiments of the present invention also provide a vehicle, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to execute the vehicle driving condition identification method described in any of the above embodiments.

[0106] Optionally, in this embodiment, the processor in the vehicle can be configured to run a computer program to perform the following steps:

[0107] Step S101: Obtain vehicle driving data.

[0108] Step S102: Based on the vehicle driving data, the vehicle driving process is segmented to obtain multiple driving segments.

[0109] Step S103: Determine the grayscale images corresponding to multiple driving segments based on the vehicle driving data corresponding to multiple driving segments.

[0110] Step S104: Determine the driving condition recognition result based on the grayscale image and the preset working condition image library.

[0111] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0112] Embodiments of the present invention also provide a non-volatile storage medium storing a computer program, wherein the computer program is configured to execute the vehicle driving condition identification method described in any of the above embodiments when run on a computer or processor.

[0113] Optionally, in this embodiment, the computer program described above may be configured to store a computer program for performing the following steps:

[0114] Step S101: Obtain vehicle driving data.

[0115] Step S102: Based on the vehicle driving data, the vehicle driving process is segmented to obtain multiple driving segments.

[0116] Step S103: Determine the grayscale images corresponding to multiple driving segments based on the vehicle driving data corresponding to multiple driving segments.

[0117] Step S104: Determine the driving condition recognition result based on the grayscale image and the preset working condition image library.

[0118] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0119] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0120] In the embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of modules can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through interfaces, or indirect couplings or communication connections between modules, and may be electrical or other forms.

[0121] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0122] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0123] If the integrated module is implemented as a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0124] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for identifying vehicle driving conditions, characterized in that, include: Obtain vehicle driving data; Based on the vehicle driving data, the vehicle's driving process is segmented to obtain multiple driving segments; Based on the vehicle driving data corresponding to the multiple driving segments, a grayscale image corresponding to the multiple driving segments is determined, wherein the grayscale image is used to characterize the driving condition features of the corresponding driving segment; The driving condition recognition result is determined based on the grayscale image and the preset working condition image library.

2. The vehicle driving condition identification method according to claim 1, characterized in that, The multiple driving segments include lateral driving segments and longitudinal driving segments; the process of segmenting the vehicle's driving process into multiple driving segments based on the vehicle driving data includes: Based on the yaw rate in the vehicle driving data, the lateral short-time average energy within a first preset time interval is determined, and based on the longitudinal acceleration in the vehicle driving data, the longitudinal short-time average energy within a second preset time interval is determined. The lateral short-time average energy is used to characterize the change of the yaw rate within the first preset time interval, and the longitudinal short-time average energy is used to characterize the change of the longitudinal acceleration within the second preset time interval. Based on the lateral short-time average energy, a plurality of lateral travel segments are determined, and based on the longitudinal short-time average energy, a plurality of longitudinal travel segments are determined.

3. The vehicle driving condition identification method according to claim 1, characterized in that, The step of determining the grayscale image corresponding to the plurality of driving segments based on the vehicle driving data corresponding to the plurality of driving segments includes: The vehicle driving data corresponding to the multiple driving segments are resampled to obtain multiple data sequences; The multiple data sequences are normalized to obtain a data grayscale value sequence; Determine the grayscale matrix based on multiple sequences of grayscale values ​​of the data; The grayscale image is determined using a preset conversion algorithm based on the grayscale matrix.

4. The vehicle driving condition identification method according to claim 1, characterized in that, The preset working condition image library includes multiple preset working condition images, and constructing the preset working condition images includes: Construct simulation scenarios for various driving conditions; For each driving condition, simulation data is obtained by performing condition simulation in the simulation scenario; Based on the simulation data, a preset working condition image template is determined.

5. The vehicle driving condition identification method according to claim 4, characterized in that, The various driving conditions include any one or more combinations of the following: acceleration, deceleration, cruise, lane keeping, lane changing, turning, U-turn, roundabout, and ramp conditions.

6. The vehicle driving condition identification method according to claim 1, characterized in that, The step of determining the driving condition recognition result based on the grayscale image and a preset driving condition image library includes: A preset image matching algorithm is used to match the grayscale image with the working condition images in the preset working condition image library to obtain the matching result; Based on the matching results, the driving condition identification result is determined.

7. The vehicle driving condition identification method according to claim 1, characterized in that, The step of determining the driving condition recognition result based on the grayscale image and a preset driving condition image library includes: The grayscale image is identified using a preset driving condition recognition model to obtain the driving condition recognition result, wherein the preset driving condition recognition model is trained based on a preset driving condition image library.

8. A vehicle driving condition recognition system, characterized in that, include: The acquisition module is used to acquire vehicle driving data; The segmentation module is used to segment the vehicle's driving process into multiple driving segments based on the vehicle's driving data. The first determining module is used to determine a grayscale image corresponding to the plurality of driving segments based on the vehicle driving data corresponding to the plurality of driving segments, wherein the grayscale image is used to characterize the driving condition features of the corresponding driving segment; The second determining module is used to determine the driving condition recognition result based on the grayscale image and the preset working condition image library.

9. A vehicle comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the vehicle driving condition identification method as described in any one of claims 1 to 7.

10. A non-volatile storage medium, characterized in that, The non-volatile storage medium stores a computer program, wherein the computer program is configured to execute the vehicle driving condition identification method as described in any one of claims 1 to 7 when running on a computer or processor.

Images