Vehicle posture detection method, device, equipment and medium

Abstract

The application discloses a vehicle posture detection method, comprising: obtaining driving state information of a driver, working condition information of a vehicle and environment information within a predetermined time period; obtaining first posture transformation information of the vehicle according to the driving state information of the driver; obtaining second posture transformation information of the vehicle according to the working condition information of the vehicle; obtaining third posture transformation information of the vehicle according to the environment information; inputting the first posture transformation information, the second posture transformation information and the third posture transformation information into a posture transformation detection model to obtain posture transformation factors corresponding to the driving posture transformation output by the posture transformation detection model. The application judges transformation factors (whether it is caused by human or the vehicle itself) of posture transformation of the vehicle by collecting working condition information of internal components of the vehicle, driving state information of the driver and environment information in real time, thereby improving the accuracy of the judgment and the safety of driving.

Description

Technical Field

[0001] This invention belongs to the field of automotive testing technology, specifically relating to a vehicle attitude detection method, device, equipment, and medium. Background Technology

[0002] In recent years, there has been an increasing number of news reports about car malfunctions, sudden driver incidents, or interference with driving that have resulted in multiple injuries or fatalities. With the rapid increase in the number of private and commercial vehicles, it is undoubtedly essential to monitor the vehicle's driving status and the driving area during operation, enabling the system to issue warnings to the driver or apply emergency braking in case of abnormal conditions to ensure the safety of the driver and passengers.

[0003] Currently, there are many methods for monitoring abnormal driving behavior in vehicles, but most of them monitor a single element, and few systems comprehensively monitor both driver and vehicle states. This highlights the problems with existing abnormal driving behavior monitoring systems, such as their simplistic judgment methods and incomplete detection results. Summary of the Invention

[0004] In view of the shortcomings of the prior art described above, the present invention provides a vehicle attitude detection method, apparatus, device and medium to solve the above technical problems.

[0005] This invention provides a vehicle attitude detection method, the method comprising:

[0006] The vehicle's driving parameters and driving posture changes within a predetermined time period are obtained. The driving parameters include: driver's driving status information, vehicle operating condition information, and environmental information.

[0007] The first attitude change information of the vehicle is obtained based on the driver's driving state information;

[0008] The second attitude transformation information of the vehicle is obtained based on the vehicle's operating condition information;

[0009] The third attitude transformation information of the vehicle is obtained based on the environmental information;

[0010] The first attitude change information, the second attitude change information, and the third attitude change information are input into the attitude change detection model to obtain the attitude change factors corresponding to the driving attitude change output by the attitude change detection model; wherein, the attitude change factors represent the factors that cause the vehicle to produce attitude change; the attitude change detection model is trained by using the first historical attitude change information, the second historical attitude change information, and the third historical attitude change information as input and the attitude change factors as output.

[0011] In one embodiment of the present invention, obtaining the first posture transformation information of the vehicle based on the driver's driving state information includes:

[0012] The driving state information is input into the first posture recognition model to obtain the first posture transformation information output by the first posture recognition model; wherein, the first posture recognition model is trained with the driving state information as input and the first posture transformation information as output.

[0013] The second attitude transformation information of the vehicle is obtained based on the vehicle's operating condition information, including:

[0014] The vehicle's operating condition information is input into the second posture recognition model to obtain the second posture transformation information output by the second posture recognition model; wherein, the second posture recognition model is trained using the vehicle's operating condition information as input and the second posture transformation information as output.

[0015] The third attitude transformation information of the vehicle is obtained based on the environmental information, including:

[0016] The environmental information is input into the third pose recognition model to obtain the third pose transformation information output by the third pose recognition model; wherein, the second pose recognition model is trained with the environmental information as input and the third pose transformation information as output.

[0017] In one embodiment of the present invention, the step of obtaining the driver's driving status information includes:

[0018] Acquire an image of the cockpit containing the driver;

[0019] Target detection is performed on the cockpit image to obtain the driver target;

[0020] Feature extraction is performed on the driver target to obtain a human key point feature map;

[0021] The driver's driving status information is obtained by analyzing the key point feature map of the human body using a first posture recognition model.

[0022] In one embodiment of the present invention, the target detection of the cockpit image includes:

[0023] Multi-scale detection of cockpit images is performed using the feature extraction layer in the target detection model to obtain detection features at different scales;

[0024] The target prediction layer in the target detection model upsamples the detection features at different scales to obtain upsampled features, and then fuses the upsampled features and the corresponding detection features to obtain fused features; based on the fused features, a driver target is obtained.

[0025] In one embodiment of the present invention, the feature extraction layer includes a plurality of residual blocks connected in sequence, each residual block being formed by merging convolutional layers of different numbers in a cyclically set number.

[0026] In one embodiment of the present invention, the residual block includes convolutional layers including depthwise convolutional layers and pointwise convolutional layers;

[0027] The deep convolutional layer is used to extract features from each channel of the cockpit image;

[0028] The pointwise convolutional layer is used for feature fusion of features extracted by the deep convolutional layer.

[0029] In one embodiment of the present invention, the target prediction layer is embedded with an SENet layer.

[0030] In one embodiment of the present invention, the vehicle's operating condition information includes at least one of the following: tire information, brake information, and suspension information.

[0031] In one embodiment of the present invention, the environmental information includes: vehicle driving road information and weather information; the road information includes at least one of the following: lane, road environment, traffic density information, engine information; the weather information includes at least one of the following: temperature, weather.

[0032] The present invention provides a vehicle attitude detection device, the device comprising:

[0033] The data acquisition module is used to acquire the vehicle's driving parameters and driving posture changes within a predetermined time period. The driving parameters include: driver's driving status information, vehicle operating condition information, and environmental information.

[0034] The first posture transformation recognition module is used to obtain the first posture transformation information of the vehicle based on the driver's driving state information;

[0035] The second attitude change recognition module is used to obtain the second attitude change information of the vehicle based on the vehicle's operating condition information.

[0036] The third attitude transformation recognition module is used to obtain the third attitude transformation information of the vehicle.

[0037] The attitude change factor prediction module is used to input the first attitude change information, the second attitude change information, and the third attitude change information into the attitude change detection model to obtain the attitude change factors corresponding to the driving attitude change output by the attitude change detection model; wherein, the attitude change factors represent the factors that cause the vehicle to produce attitude changes; the attitude change detection model is trained using the first historical attitude change information, the second historical attitude change information, and the third historical attitude change information as input and the attitude change factors as output.

[0038] The present invention provides an electronic device, the electronic device comprising:

[0039] One or more processors;

[0040] A storage device for storing one or more programs that, when executed by one or more processors, cause the electronic device to implement the steps of the vehicle attitude detection method described above.

[0041] The present invention provides a computer-readable storage medium storing a computer program thereon, which, when executed by a computer processor, causes the computer to perform the steps of the above-described vehicle attitude detection method.

[0042] The beneficial effects of this invention: A vehicle posture detection method of this invention includes: acquiring vehicle driving parameters and posture changes within a predetermined time period, wherein the driving parameters include: driver's driving state information, vehicle operating condition information, and environmental information; obtaining first posture change information of the vehicle based on the driver's driving state information; obtaining second posture change information of the vehicle based on the vehicle operating condition information; obtaining third posture change information of the vehicle based on the environmental information; inputting the first posture change information, the second posture change information, and the third posture change information into a posture change detection model to obtain posture change factors corresponding to the vehicle posture change output by the posture change detection model; wherein, the posture change factors represent the factors that cause the vehicle to produce posture changes; the posture change detection model is trained using first historical posture change information, second historical posture change information, and third historical posture change information as input and posture change factors as output. This invention improves the accuracy of judgment and driving safety by real-time collection of operating condition information of internal vehicle components, driver's driving state information, and environmental information to determine the change factors (human error or vehicle-related issues) that cause vehicle posture changes.

[0043] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0044] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings:

[0045] Figure 1 This is a schematic diagram illustrating the implementation environment of a vehicle attitude detection method according to an exemplary embodiment of this application;

[0046] Figure 2 This is a flowchart illustrating a vehicle attitude detection method in an exemplary embodiment of this application;

[0047] Figure 3 A flowchart illustrating the steps for obtaining driving status information, as shown in an exemplary embodiment of this application;

[0048] Figure 4 A flowchart illustrating target detection is shown as an exemplary embodiment of this application;

[0049] Figure 5 This is a block diagram illustrating a vehicle attitude detection device in an exemplary embodiment of this application;

[0050] Figure 6 This is a block diagram illustrating a vehicle controller as shown in an exemplary embodiment of this application;

[0051] Figure 7 A schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application is shown. Detailed Implementation

[0052] The embodiments of the present invention will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention and not for limiting the scope of protection of the present invention.

[0053] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0054] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the invention. However, it will be apparent to those skilled in the art that embodiments of the invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the invention.

[0055] Figure 1 This is a schematic diagram illustrating an exemplary vehicle attitude detection method implementation environment according to this application. The method is used to monitor the vehicle's driving state and the state of the driving area during vehicle operation, enabling the driver to be alerted or to take emergency braking action when the vehicle is in an abnormal state to ensure the safety of the driver and passengers. Please refer to... Figure 1 The implementation environment includes a terminal device 101 and a server 102, which communicate with each other via a wired or wireless network. The terminal device acquires vehicle driving parameters and driving posture changes within a predetermined time period. The driving parameters include: driver's driving state information, vehicle operating condition information, and environmental information. Based on the driver's driving state information, the terminal device obtains first posture change information of the vehicle; based on the vehicle's operating condition information, it obtains second posture change information of the vehicle; based on the environmental information, it obtains third posture change information of the vehicle. The first posture change information, the second posture change information, and the third posture change information are input into a posture change detection model to obtain posture change factors corresponding to the driving posture changes output by the posture change detection model. The posture change factors represent the factors that cause the vehicle to undergo posture changes. The posture change detection model is trained using first historical posture change information, second historical posture change information, and third historical posture change information as input and posture change factors as output. This invention improves the accuracy of judgment and driving safety by collecting real-time operating information of internal vehicle components, driver's driving status information, and environmental information to determine the factors causing changes in vehicle posture (human error or vehicle-related issues).

[0056] It should be understood that Figure 1 The number of terminal devices 101 and servers 102 shown is merely illustrative. Any number of terminal devices 101 and servers 102 can be used depending on actual needs.

[0057] The terminal device 101 corresponds to the client, which can be any electronic device with a user input interface, including but not limited to smartphones, tablets, laptops, computers, in-vehicle computers, etc. The user input interface includes but is not limited to touch screens, keyboards, physical buttons, audio pickup devices, etc.

[0058] Among them, server 102 corresponds to the server side, which can be a server that provides various services. It can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. This section does not impose any restrictions on this.

[0059] Terminal device 101 can communicate with server 102 via wireless networks such as 3G (third-generation mobile information technology), 4G (fourth-generation mobile information technology), and 5G (fifth-generation mobile information technology), and this is not restricted here.

[0060] The embodiments of this application respectively propose a vehicle attitude detection method, a vehicle attitude detection device, an electronic device, and a computer-readable storage medium, which will be described in detail below.

[0061] Please see Figure 2 , Figure 2 This is a flowchart illustrating a vehicle attitude detection method as an exemplary embodiment of this application. This method can be applied to... Figure 1 The implementation environment is shown, and the method is specifically executed by the terminal device 101 in that implementation environment. It should be understood that the method can also be applied to other exemplary implementation environments and specifically executed by devices in other implementation environments. This embodiment does not limit the implementation environment to which the method is applicable.

[0062] Please see Figure 2 , Figure 2 This is a flowchart illustrating an exemplary vehicle attitude detection method of this application. The vehicle attitude detection method includes at least steps S210 to S270, which are described in detail below:

[0063] Step S210: Obtain the vehicle's driving parameters and driving posture changes within a predetermined time period. The driving parameters include: driver's driving status information, vehicle operating condition information, and environmental information.

[0064] Step S220: Obtain the first attitude change information of the vehicle based on the driver's driving state information;

[0065] Step S230: Obtain the second attitude transformation information of the vehicle based on the vehicle's operating condition information;

[0066] Step S240: Obtain the third attitude transformation information of the vehicle based on the environmental information;

[0067] Step S250: Input the first attitude change information, the second attitude change information, and the third attitude change information into the attitude change detection model to obtain the attitude change factors corresponding to the driving attitude change output by the attitude change detection model; wherein, the attitude change factors represent the factors that cause the vehicle to produce attitude change; the attitude change detection model is trained using the first historical attitude change information, the second historical attitude change information, and the third historical attitude change information as input and the attitude change factors as output.

[0068] The following will provide a detailed explanation of each of the above steps.

[0069] In step S210, the driving parameters and driving posture changes of the vehicle within a predetermined time period are obtained. The driving parameters include: driver's driving status information, vehicle operating condition information, and environmental information.

[0070] Driving posture change refers to the change in the vehicle's posture from the start time to the end time of a predetermined period, that is, the process of changing from a first posture to a second posture. Of course, other postures may also be included in the process of changing from the first posture to the second posture.

[0071] Driving status information refers to the driver's posture while driving the vehicle; different driving postures result in different vehicle driving postures. The vehicle's operating condition information includes at least one of the following: tire information, braking information, suspension information, and angular momentum. The environmental information includes: road information and weather information.

[0072] The road information includes at least one of the following: lanes, road environment, and traffic density information;

[0073] The road environment can include whether the road has potholes, the speed limit of the road, the gradient, the number of traffic lights, and the turning requirements of vehicles on the road.

[0074] The weather information includes at least one of the following: temperature and weather. Weather includes: sunny, rainy, cloudy, snowy, hail, etc. Temperature may include the temperature inside the vehicle's cabin and the ambient temperature outside the cabin.

[0075] In step S220, the first attitude change information of the vehicle is obtained based on the driver's driving state information;

[0076] Specifically, the first attitude change information of the vehicle is obtained based on the driver's driving state information, including:

[0077] The driving state information is input into the first posture recognition model to obtain the first posture transformation information output by the first posture recognition model; wherein, the first posture recognition model is trained by using the driving state information as input and the first posture transformation information as output.

[0078] It should be noted that the first pose model can be a neural network-based model.

[0079] Please see Figure 3 , Figure 3 This is a flowchart illustrating the steps for obtaining driving status information, as shown in an exemplary embodiment of this application. Figure 3 As shown, the steps for obtaining the driver's driving status information include:

[0080] Step S310: Obtain an image of the cockpit containing the driver;

[0081] The driver's cockpit image includes the driver, and the cockpit image can be captured by an image acquisition device in the vehicle.

[0082] Step S320: Target detection is performed on the cockpit image to obtain the driver target;

[0083] Since the cockpit image may include targets other than the driver, such as passengers in the front passenger seat, it is necessary to perform target detection on the cockpit image to obtain the driver target.

[0084] Step S330: Extract features from the driver target to obtain a human key point feature map;

[0085] Human body key point data may include the coordinate values ​​of some or all of the 18 human body key points. The coordinate values ​​of a key point can be understood as the coordinate positions of the human skeletal key points identified from the driving image. The human body key point data may include the 18 human skeletal key points: right ankle, left ankle, right knee, left knee, right waist, left waist, right shoulder, the midpoint between the left and right shoulders, left shoulder, right elbow, left elbow, right wrist, left wrist, right ear, left ear, right eye, left eye, and nose. In other embodiments of this application, the human body key point data may also include 14 human skeletal key points: head, neck, left shoulder, right shoulder, left elbow, right elbow, left wrist, right wrist, left hip, right hip, left knee, right knee, left ankle, and right ankle. It should be understood that the human body key point data may also correspond to other numbers of human skeletal key points, such as 28.

[0086] Step S340: Analyze the human body key point feature map using the first posture recognition model to obtain the driver's driving state information.

[0087] The first posture recognition model is pre-trained. When using the first posture recognition model to analyze the human body key point feature map, the human body key point features are input into the first posture recognition model to obtain the driver's driving state information.

[0088] In one exemplary embodiment, the human body key point data includes skeletal key point data. Driving state information can be obtained by inputting the human body key point data into a pre-trained first posture recognition model, or by processing the human body key point feature map using an image recognition algorithm. Determining the driver's driving state information based on the human body key point feature map is beneficial for recognizing the driver's posture, thereby determining whether the driver is in a driving state such as smoking or making a phone call.

[0089] Please see Figure 4 , Figure 4 A flowchart illustrating target detection is shown as an exemplary embodiment of this application, such as... Figure 4 As shown, the target detection of the cockpit image includes:

[0090] Step S410: Multi-scale detection of the cockpit image is performed through the feature extraction layer in the target detection model to obtain detection features at different scales;

[0091] Specifically, the feature extraction layer includes multiple residual blocks connected in sequence, each residual block being formed by fusing different numbers of convolutional layers in a cyclic setting.

[0092] More specifically, the residual block includes convolutional layers including deep convolutional layers and pointwise convolutional layers; the deep convolutional layers are used to extract features from each channel of the cockpit image; the pointwise convolutional layers are used to fuse the features extracted by the deep convolutional layers.

[0093] The residual block is a depthwise separable convolutional module. Depthwise separable convolution separates the channels and spatial regions, decomposing the residual module into depthwise convolution and pointwise convolution. First, depthwise convolution is used to perform 3*3 convolution on the three single channels of the feature map to collect the features of each channel. Then, pointwise convolution is used to perform 1*1 pointwise convolution on the feature map after depthwise convolution to collect the features of each point, thereby obtaining detection features at different scales.

[0094] Step S420: Upsample the detection features at different scales through the target prediction layer in the target detection model to obtain upsampled features, and fuse the upsampled features and the detection features corresponding to the upsampled features to obtain fused features; predict the driver target based on the fused features.

[0095] Specifically, the target prediction layer embeds an SENet layer.

[0096] In one embodiment, to train the object detection model, a dataset containing images of different types of objects needs to be selected from a public dataset. Based on the labels of the data, the K-means clustering algorithm is used to perform cluster analysis on the dataset to obtain the specific anchorbox values ​​of the objects in the images in the dataset, and then the object detection model is trained.

[0097] Specifically, the process involves: extracting M images of N different target types from a public dataset and labeling them using a labeling tool; then dividing the images into training and testing sets according to a set ratio; calculating anchorbox values ​​using the K-means clustering method on the training set; reading the labeled dataset, randomly selecting the width and height values ​​of one image as coordinate points and initial cluster centers, and then iteratively calculating the specific anchorbox values ​​using the K-means clustering method.

[0098] In one embodiment, generating independent target sequences for different targets requires transcoding based on the time of the first complete detection of the target and the corresponding anchorbox value to generate the target sequence number;

[0099] Specifically, the time when the target (which can be a vehicle or a driver) is first fully detected is recorded, and then combined with the corresponding anchorbox for transcoding, using hexadecimal, to generate a target sequence number.

[0100] When using an object detection model to detect objects, the pre-trained network model weight file is first loaded, and the dataset is input into the trained object detection model to obtain multi-scale feature maps. The logistic function is used to activate the network's predicted x, y, confidence, and class probabilities. After thresholding, the coordinates, confidence, and class probabilities of all predicted boxes are obtained. The results are then processed using non-maximum suppression to remove redundant detection boxes, generating the final object detection boxes and recognition results. Based on the recognition results, image information of the same target is packaged and categorized into Level I image packages according to the timeline, and these Level I image packages are labeled with generated vehicle serial numbers.

[0101] In this embodiment, since the determination is based on the driver's driving state over a period of time, it is necessary to acquire images of the driver over that period. Therefore, in order to determine the driver, a vehicle tracker can be constructed using Kalman filtering to achieve real-time vehicle tracking. This requires obtaining the position and size of the target (here, the driver) cropped from the Level I image packet, and then determining the driver's posture marked in the image.

[0102] In one embodiment, during the training of the object detection model, the data in the Level I image packet is deblurred. Then, the learned target features are compared with the corresponding data. If the comparison results are consistent, the corresponding data is placed into the Level II data packet. Next, the object detection network is trained using the data in the Level II data packet. The object detection network learns the target's state, labels the target, analyzes target features, determines the target's state, and performs label transcoding based on the state. The transcoding result is then labeled in the Level II data packet.

[0103] In step S230, the second attitude transformation information of the vehicle is obtained based on the vehicle's operating condition information;

[0104] The second attitude transformation information of the vehicle is obtained based on the vehicle's operating condition information, including:

[0105] The vehicle's operating condition information is input into the second attitude recognition model to obtain the second attitude transformation information output by the second attitude recognition model; wherein, the second attitude recognition model is trained using the vehicle's operating condition information as input and the second attitude transformation information as output.

[0106] It should be noted that the second attitude model can be a neural network-based model. The second attitude recognition model is pre-trained. When using the second attitude recognition model to analyze the working condition information, the working condition information is input into the first attitude recognition model to obtain the second attitude transformation information.

[0107] In step S240, the third attitude transformation information of the vehicle is obtained based on the environmental information;

[0108] The third attitude transformation information of the vehicle is obtained based on the environmental information, including:

[0109] The environmental information is input into the third pose recognition model to obtain the third pose transformation information output by the third pose recognition model; wherein, the second pose recognition model is trained with the environmental information as input and the third pose transformation information as output.

[0110] It should be noted that the third pose model can be a neural network-based model. The third pose recognition model is pre-trained. When using the third pose recognition model to analyze environmental information, the environmental information is input into the first pose recognition model to obtain the third pose transformation information.

[0111] In step S250, the first attitude change information, the second attitude change information, and the third attitude change information are input into the attitude change detection model to obtain the attitude change factors corresponding to the driving attitude change output by the attitude change detection model; wherein, the attitude change factors represent the factors that cause the vehicle to produce attitude change; the attitude change detection model is trained using the first historical attitude change information, the second historical attitude change information, and the third historical attitude change information as input and the attitude change factors as output.

[0112] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0113] Figure 5 This is a block diagram illustrating a vehicle attitude detection device according to an exemplary embodiment of this application. The device can be applied to… Figure 1 The implementation environment shown is specifically configured in a terminal device. This device can also be applied to other exemplary implementation environments and specifically configured in other devices. This embodiment does not limit the implementation environment to which the device is applicable.

[0114] like Figure 5 As shown, this application provides a vehicle attitude detection device, which includes:

[0115] The data acquisition module 510 is used to acquire the driving parameters and driving posture changes of the vehicle within a predetermined time period. The driving parameters include: driver's driving status information, vehicle operating condition information, and environmental information.

[0116] The first posture transformation recognition module 520 is used to obtain the first posture transformation information of the vehicle based on the driver's driving state information.

[0117] The second attitude change recognition module 530 is used to obtain the second attitude change information of the vehicle based on the vehicle's operating condition information.

[0118] The third attitude transformation recognition module 540 is used to obtain the third attitude transformation information of the vehicle.

[0119] The attitude change factor prediction module 550 is used to input the first attitude change information, the second attitude change information, and the third attitude change information into the attitude change detection model to obtain the attitude change factors corresponding to the driving attitude change output by the attitude change detection model; wherein, the attitude change factors represent the factors that cause the vehicle to produce attitude change; the attitude change detection model is trained using the first historical attitude change information, the second historical attitude change information, and the third historical attitude change information as input and the attitude change factors as output.

[0120] It should be noted that the vehicle attitude detection device and the vehicle attitude detection method provided in the above embodiments belong to the same concept. The specific operation methods of each module and unit have been described in detail in the method embodiments and will not be repeated here. In practical applications, the vehicle attitude detection device provided in the above embodiments can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. This is not a limitation here.

[0121] Please see Figure 6 , Figure 6 This is a block diagram illustrating a vehicle controller as an exemplary embodiment of this application. The vehicle controller includes a coordination controller module, an image acquisition module, a network module, a deep learning module, an angular momentum module, a power supply module, and multiple control units (ECUs).

[0122] Each control unit (ECU) includes an image processing module, an input module, an output module, a communication module, and a processor module. All ECUs share a coordination controller module, an image acquisition module, a network module, a deep learning module, an angular momentum module, and a power supply module. The coordination controller module coordinates the operation of multiple ECUs, the power supply module ensures power supply to other modules, and the network module connects the communication modules within the internal ECUs to external networks. The deep learning module has different preset models (based on neural networks, machine learning, etc.) integrated into the network module. During image transmission, the processor module performs information judgment on the image.

[0123] Specifically, the information judgment includes target detection, driver driving status judgment, vehicle operating condition information processing, and environmental information processing. Based on different judgment information, it is distributed to different control units (ECUs), and commands are sent to the vehicle through the processor module or displayed on the vehicle screen for the driver to perform specific operations.

[0124] In one embodiment, the input module comprises a digital input unit, an analog input unit, and a frequency input unit.

[0125] In one embodiment, the output module comprises a digital output unit, an analog output unit, a low-current low-level drive unit, and a high-current low-level drive unit.

[0126] In one embodiment, the control unit (ECU) has a unique ID as its identification information. When accessing the control unit (ECU), a frame data request command is sent to the control unit (ECU); frame data is received from the control unit (ECU) based on the frame data request command; a key is calculated based on the frame data and a preset key calculation algorithm to obtain a key; the control unit (ECU) is authenticated using the key, and the existence of a security vulnerability in the control unit (ECU) is determined based on the authentication result fed back by the control unit (ECU); if the authentication is successful, the control unit (ECU) has no security vulnerability; if the authentication fails, the control unit (ECU) has a security vulnerability.

[0127] Embodiments of this application also provide an electronic device, including: one or more processors; and a storage device for storing one or more programs, which, when executed by the one or more processors, cause the electronic device to implement the vehicle attitude detection method provided in the above embodiments.

[0128] Figure 7 A schematic diagram of a computer system suitable for implementing the embodiments of this application is shown. It should be noted that... Figure 7 The computer system of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0129] like Figure 7 As shown, the computer system includes a Central Processing Unit (CPU), which can perform various appropriate actions and processes based on programs stored in Read-Only Memory (ROM) or loaded from storage into Random Access Memory (RAM), such as executing the methods described in the above embodiments. The RAM also stores various programs and data required for system operation. The CPU, ROM, and RAM are interconnected via a bus. Input / output (I / O) interfaces are also connected to the bus.

[0130] The following components are connected to the I / O interface: input sections including keyboards, mice, etc.; output sections including cathode ray tubes (CRTs), liquid crystal displays (LCDs), and speakers; storage sections including hard drives; and communication sections including network interface cards such as LAN (Local Area Network) cards and modems. The communication sections perform communication processing via networks such as the Internet. Drives are also connected to the I / O interface as needed. Removable media, such as disks, optical discs, magneto-optical discs, semiconductor memories, etc., are installed on the drive as needed so that computer programs read from them can be installed into the storage section as required.

[0131] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including methods for performing processes. Figure 2 The computer program illustrating the method. In such embodiments, the computer program can be downloaded and installed from a network via a communication component, and / or installed from a removable medium. When the computer program is executed by a central processing unit (CPU), it performs the various functions defined in the system of this application.

[0132] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0133] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0134] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0135] Another aspect of this application provides a computer-readable storage medium storing a computer program thereon, which, when executed by a computer's processor, causes the computer to perform the vehicle attitude detection method as described above. This computer-readable storage medium may be included in the electronic device described in the above embodiments, or it may exist independently and not incorporated into the electronic device.

[0136] Another aspect of this application provides a computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the vehicle attitude detection method provided in the various embodiments described above.

[0137] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. A vehicle attitude detection method, characterized in that, The method includes: The vehicle's driving parameters and driving posture changes within a predetermined time period are obtained. The driving parameters include: driver's driving status information, vehicle operating condition information, and environmental information. The first attitude change information of the vehicle is obtained based on the driver's driving state information; The second attitude transformation information of the vehicle is obtained based on the vehicle's operating condition information; The third attitude transformation information of the vehicle is obtained based on the environmental information; The first attitude change information, the second attitude change information, and the third attitude change information are input into the attitude change detection model to obtain the attitude change factors corresponding to the driving attitude change output by the attitude change detection model; wherein, the attitude change factors represent the factors that cause the vehicle to produce attitude change; the attitude change detection model is trained by using the first historical attitude change information, the second historical attitude change information, and the third historical attitude change information as input and the attitude change factors as output.

2. The vehicle attitude detection method according to claim 1, characterized in that, The first attitude change information of the vehicle is obtained based on the driver's driving state information, including: The driving state information is input into the first posture recognition model to obtain the first posture transformation information output by the first posture recognition model; wherein, the first posture recognition model is trained with the driving state information as input and the first posture transformation information as output. The second attitude transformation information of the vehicle is obtained based on the vehicle's operating condition information, including: The vehicle's operating condition information is input into the second posture recognition model to obtain the second posture transformation information output by the second posture recognition model; wherein, the second posture recognition model is trained using the vehicle's operating condition information as input and the second posture transformation information as output. The third attitude transformation information of the vehicle is obtained based on the environmental information, including: The environmental information is input into the third pose recognition model to obtain the third pose transformation information output by the third pose recognition model; wherein, the second pose recognition model is trained with the environmental information as input and the third pose transformation information as output.

3. The vehicle attitude detection method according to claim 1, characterized in that, The steps for obtaining the driver's driving status information include: Acquire an image of the cockpit containing the driver; Target detection is performed on the cockpit image to obtain the driver target; Feature extraction is performed on the driver target to obtain a human key point feature map; The driver's driving status information is obtained by analyzing the key point feature map of the human body using a first posture recognition model.

4. The vehicle attitude detection method according to claim 3, characterized in that, The target detection of the cockpit image includes: Multi-scale detection of cockpit images is performed using the feature extraction layer in the target detection model to obtain detection features at different scales; The target prediction layer in the target detection model upsamples the detection features at different scales to obtain upsampled features, and then fuses the upsampled features and the corresponding detection features to obtain fused features; based on the fused features, a driver target is obtained.

5. The vehicle attitude detection method according to claim 4, characterized in that, The feature extraction layer includes multiple residual blocks connected in sequence. Each residual block is formed by merging convolutional layers of different numbers in a cyclic setting.

6. The vehicle attitude detection method according to claim 5, characterized in that, The residual block includes convolutional layers, including depthwise convolutional layers and pointwise convolutional layers; The deep convolutional layer is used to extract features from each channel of the cockpit image; The pointwise convolutional layer is used for feature fusion of features extracted by the deep convolutional layer.

7. The vehicle attitude detection method according to claim 4, characterized in that, The target prediction layer contains an embedded SENet layer.

8. The vehicle attitude detection method according to claim 1, characterized in that, The vehicle's operating information includes at least one of the following: tire information, brake information, suspension information, and engine information.

9. The vehicle attitude detection method according to claim 1, characterized in that, The environmental information includes: vehicle driving road information and weather information; the road information includes at least one of the following: lane, road environment, traffic density information; the weather information includes at least one of the following: temperature, weather.

10. A vehicle attitude detection device, characterized in that, The device includes: The data acquisition module is used to acquire the vehicle's driving parameters and driving posture changes within a predetermined time period. The driving parameters include: driver's driving status information, vehicle operating condition information, and environmental information. The first posture transformation recognition module is used to obtain the first posture transformation information of the vehicle based on the driver's driving state information; The second attitude change recognition module is used to obtain the second attitude change information of the vehicle based on the vehicle's operating condition information. The third attitude transformation recognition module is used to obtain the third attitude transformation information of the vehicle. The attitude change factor prediction module is used to input the first attitude change information, the second attitude change information, and the third attitude change information into the attitude change detection model to obtain the attitude change factors corresponding to the driving attitude change output by the attitude change detection model; wherein, the attitude change factors represent the factors that cause the vehicle to produce attitude changes; the attitude change detection model is trained using the first historical attitude change information, the second historical attitude change information, and the third historical attitude change information as input and the attitude change factors as output.

11. An electronic device, characterized in that, The electronic device includes: One or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, cause the electronic device to implement the steps of the vehicle attitude detection method as described in any one of claims 1 to 8.

12. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by the computer's processor, causes the computer to perform the steps of the vehicle attitude detection method according to any one of claims 1 to 8.

Images