Vehicle collision early warning method and device and vehicle

Abstract

The invention discloses a vehicle collision early warning method and device and a vehicle, and is applied to the technical field of vehicle control, and the method comprises the steps: obtaining driver physiological data, vehicle data and driving road data of a target vehicle; obtaining a driver emotion coefficient according to the driver physiological data and the driving road data; according to the whole vehicle data, the driving speed and the steering angle of the target vehicle in the future time period are obtained to serve as target driving parameters of the target vehicle; according to the driving road data, the average vehicle speed variation and the average angle variation of the target vehicle in the future time period are obtained to serve as the target driving variation of the target vehicle; and performing collision early warning processing on the target vehicle according to the driver emotion coefficient of the target vehicle, the target driving parameter and the target driving variable quantity. The accuracy of vehicle collision early warning can be effectively improved, the driving safety of the vehicle is improved, and the vehicle collision risk is reduced.

Description

Technical Field

[0001] The present application relates to the field of vehicle control technology, and in particular to a vehicle collision warning method, device and vehicle. Background Art

[0002] Vehicle collision is a common type of accident in road traffic, and it is a crucial part of vehicle driving assistance technology. In related technologies, the driver's physiological signals are collected and the driver's emotions are identified through physiological signals, and then the vehicle collision warning is realized based on the identified emotional information. However, the collision warning method of related technologies is relatively single, and its collision warning accuracy needs to be improved. Summary of the invention

[0003] The embodiments of the present application provide a vehicle collision warning method, device and vehicle for improving the accuracy of vehicle collision warning.

[0004] On the one hand, an embodiment of the present application provides a vehicle collision warning method, comprising the following steps: Obtain the driver's physiological data, vehicle data and driving road data of the target vehicle; Obtaining a driver emotion coefficient according to the driver physiological data and the driving road data; According to the whole vehicle data, the driving speed and steering angle of the target vehicle in a future time period are obtained as target driving parameters of the target vehicle; According to the driving road data, an average speed change and an average angle change of the target vehicle in a future time period are obtained as a target driving change of the target vehicle; According to the driver emotion coefficient, target driving parameters and target driving variation of the target vehicle, collision warning processing is performed on the target vehicle.

[0005] On the other hand, an embodiment of the present application provides a vehicle collision warning device, including: An acquisition module, used to acquire the driver's physiological data, vehicle data and driving road data of the target vehicle; A first processing module, used for obtaining a driver emotion coefficient according to the driver physiological data and the driving road data; A second processing module is used to obtain the driving speed and steering angle of the target vehicle in a future time period as the target driving parameters of the target vehicle according to the vehicle data; A third processing module is used to obtain, according to the driving road data, an average speed change and an average angle change of the target vehicle in a future time period as a target driving change of the target vehicle; The fourth processing module is used to perform collision warning processing on the target vehicle according to the driver emotion coefficient, target driving parameters and target driving change amount of the target vehicle.

[0006] In another aspect, an embodiment of the present application provides a vehicle, comprising: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the above-mentioned vehicle collision warning method.

[0007] The beneficial effects of the present application are: providing a vehicle collision warning method, device and vehicle, first, obtaining the driver's physiological data, whole vehicle data and driving road data of the target vehicle; then, obtaining the driver's emotional coefficient based on the driver's physiological data and driving road data, and obtaining the target vehicle's driving speed and steering angle in the future time period as the target driving parameters of the target vehicle based on the whole vehicle data, and obtaining the target vehicle's average speed change and average angle change in the future time period as the target driving change of the target vehicle based on the driving road data; finally, performing collision warning processing on the target vehicle based on the driver's emotional coefficient, target driving parameters and target driving change of the target vehicle. The present application realizes collision warning processing on the target vehicle while fully considering the driving conditions of the target vehicle in the future time period and the influence of the driver's emotions and road factors on the driving conditions of the target vehicle, which can effectively improve the accuracy of vehicle collision warning, improve the driving safety of the vehicle, and reduce the risk of vehicle collision.

[0008] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or understood by practicing the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 is a flow chart of a vehicle collision warning method provided by an embodiment of the present application; Figure 2 is a structural diagram of a vehicle collision warning device provided in an embodiment of the present application; Figure 3 This is an example diagram of a vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION

[0010] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0011] The present application is further described below in conjunction with the accompanying drawings and specific embodiments. The described embodiments should not be regarded as limiting the present application, and all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0012] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0013] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0014] In view of the defects existing in the related art, the embodiments of the present application provide a vehicle collision warning method, device and medium, aiming to improve the accuracy of vehicle collision warning.

[0015] First, the implementation steps of the vehicle collision warning method provided by the present application will be described in detail below with reference to the accompanying drawings.

[0016] It should be noted that in each implementation of the present application, when it comes to the need to perform relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of these data will comply with the relevant laws, regulations, and standards of the relevant countries and regions. In addition, when each implementation of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of each implementation of the present application will be obtained.

[0017] The vehicle collision warning method provided in the present application can be applied to a terminal, a server, or software running in a terminal or a server. The terminal can be a tablet computer, a laptop computer, a desktop computer, etc., but is not limited to this. The server can be an independent physical server, or a server cluster or distributed system built by several 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 communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms. In addition, the server can also be a node server in a blockchain network, but is not limited to this. Among them, blockchain is a new application model of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm.

[0018] Reference Figure 1 , Figure 1 : is a flow chart of a vehicle collision warning method provided by the present application, and the vehicle collision warning method may include the following steps S101-S105: S101, acquiring driver physiological data, vehicle data, and driving road data of a target vehicle; S102, obtaining a driver emotion coefficient according to the driver's physiological data and the driving road data; S103, obtaining the driving speed and steering angle of the target vehicle in the future time period according to the vehicle data as target driving parameters of the target vehicle; S104, obtaining an average speed change and an average angle change of the target vehicle in a future time period according to the driving road data as a target driving change of the target vehicle; S105, performing collision warning processing on the target vehicle according to the driver emotion coefficient, target driving parameters and target driving variation of the target vehicle.

[0019] In an embodiment of the present application, first, the driver's physiological data, whole vehicle data and driving road data of the target vehicle are obtained; then, the driver's emotional coefficient is obtained based on the driver's physiological data and the driving road data, and the driving speed and steering angle of the target vehicle in a future time period are obtained based on the whole vehicle data as the target driving parameters of the target vehicle, and the average speed change and average angle change of the target vehicle in the future time period are obtained based on the driving road data as the target driving change of the target vehicle; finally, collision warning processing is performed on the target vehicle based on the driver's emotional coefficient, target driving parameters and target driving change of the target vehicle.

[0020] It can be seen that the embodiment of the present application determines the driver's emotion coefficient through the driver's physiological data and the driving road data, and the driver's emotion coefficient can reflect the impact of the driver's emotions on the driving condition of the target vehicle in the future time period. The driving speed and steering angle of the target vehicle in the future time period are determined through the whole vehicle data as the target driving parameters of the target vehicle. The target driving parameters can reflect the driving condition of the target vehicle in the future time period. The average speed change and the average angle change of the target vehicle in the future time period are determined through the driving road data as the target driving change of the target vehicle. The target driving change can reflect the impact of road factors on the driving condition of the target vehicle in the future time period. Then, while fully considering the driving condition of the target vehicle in the future time period and the impact of the driver's emotions and road factors on the driving condition of the target vehicle, collision warning processing is implemented for the target vehicle. In this way, the accuracy of vehicle collision warning can be effectively improved, the driving safety of the vehicle can be improved, and the risk of vehicle collision can be reduced.

[0021] In the above step S101, the driver's physiological data, vehicle data and driving road data of the target vehicle are obtained. The driver's physiological data can characterize the physiological condition of the person driving the target vehicle, the vehicle data can characterize the condition of the target vehicle while driving, and the driving road data can characterize the driving road condition of the target vehicle.

[0022] The above-mentioned driver physiological data, the above-mentioned vehicle data and the above-mentioned driving road data can all be set according to actual conditions, and the embodiments of the present application do not make specific limitations on this.

[0023] For example, the above-mentioned driver physiological data may include the driver's eye images, pulse signals, emotion types, electromyography signals and physiological signals based on remote photoplethysmography, etc. The above-mentioned vehicle data may include driving speed, steering angle, slip rate and wheel brake pressure, etc. The above-mentioned driving road data may include the traffic congestion type, traffic congestion coefficient, road surface type, etc. of the driving road, but is not limited to this.

[0024] In the above step S102, the driver's emotion coefficient is determined based on the driver's physiological data and the driving road data, so as to implement collision warning processing for the target vehicle.

[0025] The above driver emotion coefficient is used to reflect the impact of the driver's emotion on the driving condition of the target vehicle in the future time period.

[0026] The above-mentioned obtaining the driver emotion coefficient based on the driver's physiological data and the driving road data may include obtaining the driver emotion coefficient based on the driver's physiological data and the driving road data in combination with a machine learning method, but is not limited thereto.

[0027] In the above step S103, the driving speed and steering angle of the target vehicle in the future time period are determined based on the whole vehicle data, and the driving speed and steering angle of the target vehicle in the future time period are determined as the target driving parameters of the target vehicle, so as to realize collision warning processing for the target vehicle.

[0028] The above target driving parameters are used to reflect the driving conditions of the target vehicle in the future time period.

[0029] The above-mentioned future time period may include multiple future moments, and the length of the above-mentioned future time period may be set according to actual conditions, which is not specifically limited in this implementation.

[0030] The target driving parameters may include the driving speed and steering angle of the target vehicle in a future time period.

[0031] The driving speed of the target vehicle in the future time period may include the driving speed of the target vehicle at multiple future moments.

[0032] The steering angle of the target vehicle in the future time period may include steering angles of the target vehicle at multiple future moments.

[0033] The above-mentioned steering angle may be a wheel steering angle, and the wheel steering angle may be a front wheel steering angle or a rear wheel steering angle; or, the above-mentioned steering angle may be a whole vehicle steering angle, which is not specifically limited in the present embodiment.

[0034] The above-mentioned obtaining the driving speed and steering angle of the target vehicle in the future time period based on the whole vehicle data may include obtaining the driving speed of the target vehicle in the future time period based on the whole vehicle data in combination with a machine learning method, and obtaining the steering angle of the target vehicle in the future time period based on the whole vehicle data in combination with a machine learning method, but is not limited to this.

[0035] In the above step S104, the average speed change and average angle change of the target vehicle in the future time period are determined based on the driving road data, and the average speed change and average angle change of the target vehicle in the future time period are determined as the target driving change of the target vehicle, so as to realize collision warning processing for the target vehicle.

[0036] The target driving change is used to reflect the impact of road factors on the driving condition of the target vehicle in the future time period.

[0037] The target driving variation may include an average vehicle speed variation and an average vehicle angle variation of the target vehicle in a future time period.

[0038] The above-mentioned average speed change of the target vehicle in the future time period can be understood as the average change of the target vehicle's driving speed in the future time period, which can reflect the dynamic change of the target vehicle's driving speed in the future time period due to the influence of road factors.

[0039] The above-mentioned average angle change of the target vehicle in the future time period can be understood as the average change of the steering angle of the target vehicle in the future time period, which can reflect the dynamic change of the steering angle of the target vehicle in the future time period due to the influence of road factors.

[0040] The above-mentioned method of obtaining the average speed change and the average angle change of the target vehicle in the future time period based on the driving road data may include obtaining the average speed change of the target vehicle in the future time period based on the driving road data in combination with a machine learning method, and obtaining the average angle change of the target vehicle in the future time period based on the driving road data in combination with a machine learning method, but is not limited to this.

[0041] The above step S102, the above step S103 and the above step S104 may be performed in parallel, for example, the above step S102, the above step S103 and the above step S104 are performed at the same time.

[0042] Alternatively, the above step S102, the above step S103 and the above step S104 may be performed in series, for example, the above step S102 is performed first, then the above step S103 is performed, and finally the above step S104 is performed, but it is not limited thereto.

[0043] In the above step S105, after obtaining the driver emotion coefficient, target driving parameters and target driving change of the target vehicle, collision warning processing is performed on the target vehicle based on the driver emotion coefficient, target driving parameters and target driving change of the target vehicle. In this way, collision warning processing is performed on the target vehicle while fully considering the driving conditions of the target vehicle in the future time period and the influence of the driver's emotions and road factors on the driving conditions of the target vehicle, which can effectively improve the accuracy of vehicle collision warning and enhance the driving safety of the vehicle.

[0044] The above-mentioned collision warning processing for the target vehicle based on the driver emotion coefficient, target driving parameters and target driving change of the target vehicle can include obtaining the collision risk coefficient of the target vehicle based on the driver emotion coefficient, target driving parameters and target driving change of the target vehicle in combination with a machine learning method. The collision coefficient can reflect the risk coefficient of a collision accident of the target vehicle in a future time period; if the collision risk coefficient is higher than a preset risk threshold, a collision warning signal is output, but is not limited to this.

[0045] The above-mentioned machine learning method and the above-mentioned risk threshold can be set according to actual conditions, and the embodiments of the present application do not make specific limitations on this.

[0046] For example, the above-mentioned machine learning method may be a support vector machine; or, the above-mentioned machine learning method may be a random forest or logistic regression, but is not limited thereto.

[0047] The above steps will be further described below.

[0048] In some embodiments, the driver's physiological data may include the driver's eyeball image, pupil image, pulse signal, historical emotional history data, and historical driving habit data, and the driving road data may include the traffic congestion coefficient and road roughness coefficient of the road on which the target vehicle is traveling; In the above step S102, the driver's emotion coefficient is obtained according to the driver's physiological data and the driving road data, which may include the following steps S1021-S1024: S1021, performing fusion processing and feature extraction on the eyeball image and the pupil image to obtain iris features; S1022, extracting features from the pulse signal to obtain pulse features; S1023, obtaining an emotion level identifier based on the historical emotion history data and the historical driving habit data; S1024, obtaining a driver emotion coefficient according to the iris feature, the pulse feature, the emotion level indicator, the traffic congestion coefficient and the road roughness coefficient.

[0049] In this embodiment, the driver's emotional loss of control is one of the important reasons for vehicle collision. According to prior knowledge, in addition to the driver's own factors, the road factor is one of the causes of the driver's emotional loss of control. For example, when the vehicle is driving on a bumpy road for a long time or the road ahead is blocked, the driver's emotions tend to be irritable, which increases the risk of collision accidents. When performing driver emotion recognition, related technologies often only consider the driver's own factors and lack consideration of other key factors. The accuracy of driver emotion recognition needs to be improved.

[0050] To this end, this embodiment first performs fusion processing and feature extraction on the eyeball image and the pupil image in order to extract the iris features, and performs feature extraction on the pulse signal in order to extract the pulse features in the pulse signal, and determines the emotion level identification based on the historical emotional medical history data and the historical driving habit data, which can characterize the driver's tendency of emotional changes, and then obtains the driver's emotion coefficient based on the iris features, pulse features and emotion level identification, combined with the traffic congestion coefficient and the road roughness coefficient.

[0051] It can be seen that iris features are extracted from eyeball images and pupil images, and pulse features are extracted from pulse signals. Multimodal physiological features such as iris features and pulse features are closely related to the driver's emotional changes. The corresponding emotional level identification is determined by historical emotional medical history data and historical driving habit data. The emotional level identification can characterize the driver's emotional change tendency, and then the driver's emotions can be recognized while fully considering key factors such as the driving road factors and the driver's multimodal physiological characteristics and emotional change tendencies, thereby effectively improving the accuracy of driver emotion recognition.

[0052] The above-mentioned driver physiological data may include the driver's eyeball image, pupil image, pulse signal, historical emotional medical history data and historical driving habit data, but is not limited thereto.

[0053] The eyeball image and the pupil image may be acquired by acquiring the driver's eyes through at least one preset image acquisition module at a preset time to obtain the driver's eyeball image and pupil image, but is not limited thereto.

[0054] The above-mentioned preset time and the number of the above-mentioned image acquisition modules can be set according to actual conditions, and this embodiment does not make any specific limitation to this.

[0055] The above-mentioned fusing the eyeball image and the pupil image and extracting features to obtain iris features may include fusing the eyeball image and the pupil image to obtain a fused eye image, and then extracting features from the fused eye image to obtain iris features, but is not limited to this.

[0056] The pulse signal may be obtained by collecting the pulse signal of the driver's finger through at least one pulse sensor disposed on the steering wheel at a preset time to obtain the driver's pulse signal, but is not limited thereto.

[0057] The number of the above-mentioned pulse sensors can be set according to actual conditions, and this embodiment does not specifically limit this.

[0058] The above-mentioned feature extraction of the pulse signal to obtain the pulse feature may include extracting the feature of the pulse signal through a feature extraction model to obtain the pulse feature, but is not limited thereto.

[0059] The above feature extraction model can be set according to actual conditions, and this embodiment does not make any specific limitation to this.

[0060] For example, the feature extraction model may be a convolutional neural network, but is not limited thereto.

[0061] The method for obtaining the above-mentioned historical emotional medical history data and the method for obtaining the above-mentioned historical driving habit data can be to obtain the driver's historical emotional medical history data and historical driving habit data through a preset database. The preset database can be a cloud database that pre-stores the driver's historical emotional medical history data and historical driving habit data, but is not limited to this.

[0062] The above-mentioned historical emotional illness history data is used to characterize the severity of the emotional illness history suffered by the driver in the historical period of time.

[0063] The above-mentioned historical emotional illness history data may include the driver's illness risk coefficient during the historical time period. The illness risk coefficient is used to characterize the driver's illness level when the driver suffers from at least one emotional illness. The illness risk coefficient is positively correlated with the illness level, that is, the larger the illness risk coefficient, the more serious the emotional illness level of the driver; the smaller the illness risk coefficient, the milder the emotional illness level of the driver, but it is not limited to this.

[0064] The above historical driving habit data is used to characterize the driving habits of the driver in a historical period of time.

[0065] The above-mentioned historical driving habit data may include the average acceleration and average deceleration of the target vehicle in the historical time period, the average acceleration may reflect the driver's acceleration habits while driving, and the average deceleration may reflect the driver's braking habits while driving, but is not limited to this.

[0066] The above historical time period can be set according to actual conditions, and this implementation mode does not impose any specific limitation on this.

[0067] The above-mentioned emotion level identification is mainly used to characterize the driver's tendency of emotion change.

[0068] The above-mentioned obtaining of the emotion level identification based on the historical emotion history data and the historical driving habit data may include searching for the emotion level identification corresponding to the historical emotion history data and the historical driving habit data from the emotion level mapping data, wherein the emotion level mapping data may include multiple preset comprehensive variables and the emotion level identification corresponding to each preset comprehensive variable, the preset comprehensive variables include preset emotion history data and preset driving habit data, but are not limited to this.

[0069] The data format of the above emotion level identifier can be set according to actual conditions, and this embodiment does not specifically limit this.

[0070] The emotion level mapping data may be table data or chart data, but is not limited thereto.

[0071] The above step S1021, the above step S1022 and the above step S1023 may be performed in parallel, that is, the above step S1021, the above step S1022 and the above step S1023 are performed at the same time.

[0072] Alternatively, the above step S1021, the above step S1022 and the above step S1023 may be performed in series, for example, the above step S1021 is performed first, then the above step S1022 is performed, and finally the above step S1023 is performed, but it is not limited thereto.

[0073] The above-mentioned driving road data may include a traffic congestion coefficient and a road surface roughness coefficient of the road on which the target vehicle is driving, but is not limited thereto.

[0074] The road on which the target vehicle travels may be determined by positioning the target vehicle, but is not limited thereto.

[0075] The above-mentioned traffic congestion coefficient is used to characterize the degree of traffic congestion ahead on the driving road. The traffic congestion coefficient is positively correlated with the degree of traffic congestion, that is, the higher the traffic congestion coefficient, the more serious the traffic congestion; the lower the traffic congestion coefficient, the less serious the traffic congestion.

[0076] The above-mentioned traffic congestion coefficient can be obtained by first positioning the target vehicle, obtaining the road section on which the target vehicle is traveling as the current driving section, which may include multiple road sections, and then obtaining the estimated travel time of the current driving section. Thereafter, the traffic congestion coefficient value corresponding to the estimated travel time is obtained from the congestion mapping data as the traffic congestion coefficient of the driving road, wherein the congestion mapping data may include multiple preset travel times and the traffic congestion coefficient value corresponding to each preset travel time, but is not limited to this.

[0077] The road roughness coefficient is used to characterize the road roughness of the driving road. The road roughness coefficient is positively correlated with the road roughness, that is, the higher the road roughness coefficient, the rougher the road surface of the driving road; the lower the road roughness coefficient, the smoother the road surface of the driving road.

[0078] The above-mentioned road roughness coefficient can be obtained by obtaining the real-time wheel slip rate of the target vehicle, and then searching the roughness mapping data to obtain the road roughness coefficient value corresponding to the real-time wheel slip rate as the road roughness coefficient of the driving road, wherein the roughness mapping data may include multiple preset wheel slip rates and the road roughness coefficient value corresponding to each preset wheel slip rate, but is not limited to this.

[0079] The above-mentioned method of obtaining the driver emotion coefficient based on iris features, pulse features, emotion level indicators, traffic congestion coefficient and road roughness coefficient may include fusing the iris features, pulse features, emotion level indicators, traffic congestion coefficient and road roughness coefficient into a feature vector, inputting the feature vector into a pre-trained neural network model, and obtaining the driver emotion coefficient through the pre-trained neural network model.

[0080] The above-mentioned neural network model can be a neural network model pre-trained by multiple preset feature vector samples and the driver emotion coefficient corresponding to each preset feature vector sample, wherein the preset feature vector sample is obtained by fusing a preset iris feature, a preset pulse feature, a preset emotion level indicator, a preset traffic congestion coefficient and a preset road roughness coefficient.

[0081] Alternatively, the above-mentioned obtaining of the driver emotion coefficient based on iris features, pulse features, emotion level identification, traffic congestion coefficient and road roughness coefficient may include obtaining the driver emotion coefficient based on iris features, pulse features, emotion level identification, traffic congestion coefficient and road roughness coefficient in combination with a machine learning method, but is not limited to this.

[0082] In some implementations, in the above step S1021, the eyeball image and the pupil image are fused and feature extracted to obtain the iris feature, which may include the following steps A01-A04: A01, projecting the pupil image onto the eyeball image to obtain a projected image; A02, performing block processing on the projected image to obtain a plurality of pixel blocks; A03, extracting features from each pixel block to obtain initial iris features of each pixel block; A04, obtaining iris features according to the initial iris features of each pixel block.

[0083] In this embodiment, first, the pupil image is projected onto the eyeball image to obtain a projected image to achieve image fusion; then, the projected image is subjected to block processing to divide the projected image into a plurality of pixel blocks; then, feature extraction is performed on each pixel block to obtain the initial iris feature of each pixel block; finally, the iris feature is obtained based on the initial iris feature of each pixel block. It can be seen that the projected image is divided into a plurality of pixel blocks by block processing to convert the image data into a more compact data expression form, and the initial iris features in each pixel block are extracted. These initial iris features are relatively stable and not easily affected by the outside world. They can represent the key features in each pixel block, such as color, texture, shape, etc., and then the initial iris features in each pixel block are used to obtain the final iris features, so that the iris features in the projected image can be captured more accurately and comprehensively, and the robustness and extraction accuracy of the iris features can be improved.

[0084] The sizes of the above pixel blocks are all the same.

[0085] The size of each of the above pixel blocks can be set according to actual conditions, and this embodiment does not impose any specific limitation on this.

[0086] The above-mentioned feature extraction of each pixel block to obtain the initial iris feature of each pixel block may include extracting the feature of each pixel block by a preset iris feature extraction algorithm to obtain the initial iris feature of each pixel block, but is not limited thereto.

[0087] The above iris feature extraction algorithm can be set according to actual conditions, and this embodiment does not make any specific limitation to this.

[0088] For example, the iris feature extraction algorithm may be a Daugman algorithm; or, the iris feature extraction algorithm may be a histogram feature extraction algorithm, but is not limited thereto.

[0089] The above-mentioned obtaining the iris feature according to the initial iris feature of each pixel block may include fusing the initial iris feature of each pixel block to obtain the iris feature, but is not limited thereto.

[0090] In some implementations, in the above step A03, extracting features from each pixel block to obtain initial iris features of each pixel block may include the following steps A031-A034: A031, extracting features from the pixel block through the local binary pattern to obtain the value of each pixel in the pixel block; A032, comparing the value of each pixel point in the pixel block with a preset pixel threshold; A033, if there is at least one pixel point value in the pixel block that is greater than the pixel threshold, determining a preset first value as the initial iris feature of the pixel block; A034, if all pixel values ​​in the pixel block are less than or equal to the pixel threshold, a preset second value is determined as the initial iris feature of the pixel block.

[0091] In this implementation, for each pixel block, first, feature extraction is performed on the pixel block through local binary patterns (Local Binary Patterns, LBP) to obtain the value of each pixel point in the pixel block, so that the texture information of the local area in the pixel block can be accurately captured and the accuracy of feature extraction is improved. Then, the value of each pixel point in the pixel block is compared with a preset pixel threshold, that is, it is determined whether there is at least one pixel point value in the pixel block that is greater than the pixel threshold. If so, the preset first value is determined as the initial iris feature of the pixel block, otherwise, the preset second value is determined as the initial iris feature of the pixel block, so as to achieve binarization processing of each pixel block, so that the iris feature can be determined by the initial iris feature of each pixel block in the subsequent steps.

[0092] The above pixel values ​​refer to the numerical values ​​of each pixel.

[0093] The above pixel values ​​can be 0 or 1.

[0094] The above pixel threshold can be set according to actual conditions, and this embodiment does not specifically limit this.

[0095] For example, the pixel threshold may be 1; or, the pixel threshold may be 0, but is not limited thereto.

[0096] The first value and the second value can be set according to actual conditions, and this embodiment does not specifically limit this.

[0097] For example, the first value may be 1, and the second value may be 0, but the present invention is not limited thereto.

[0098] In one example, for each pixel block, feature extraction is performed on the pixel block through a local binary pattern to obtain the value of each pixel in the pixel block, where the pixel value is 1 or 0, and then a determination is made as to whether there is at least one pixel value greater than 0 in the pixel block. If so, the initial iris feature of the pixel block is determined to be 1, otherwise the initial iris feature of the pixel block is determined to be 0.

[0099] In some implementations, in the above step A04, obtaining the iris feature according to the initial iris feature of each pixel block may include the following steps A041-A045: A041, using the abscissa position information of each pixel block in the image coordinate system as the abscissa of the first change curve, and using the initial iris feature of each pixel block as the ordinate of the first change curve, to construct the first change curve; wherein the origin of the image coordinate system is the lower left corner of the projected image, the positive semi-axis of the abscissa of the image coordinate system extends to the right, and the positive semi-axis of the ordinate of the image coordinate system extends upward; A042, constructing a second change curve by using the ordinate position information of each pixel block in the image coordinate system as the abscissa of the second change curve and using the initial iris feature of each pixel block as the ordinate of the second change curve; A043, obtaining a ratio of the mean of the first change curve to the standard deviation of the first change curve as a lateral iris feature value; A044, obtaining a ratio of the mean of the second change curve to the standard deviation of the second change curve as a longitudinal iris feature value; A045, obtain the average of the horizontal iris feature value and the vertical iris feature value as the iris feature.

[0100] In this embodiment, in order to realize the feature fusion of the initial iris features of each pixel block, firstly, the horizontal coordinate position information of each pixel block in the image coordinate system is used as the horizontal coordinate of the first change curve, and the initial iris features of each pixel block are used as the vertical coordinate of the first change curve to construct a first change curve, and the first change curve can map the change of the iris features of the projected image in the horizontal direction; and the vertical coordinate position information of each pixel block in the image coordinate system is used as the horizontal coordinate of the second change curve, and the initial iris features of each pixel block are used as the vertical coordinate of the second change curve to construct a second change curve, and the second change curve can map the change of the iris features of the projected image in the vertical direction. ; Then, the ratio of the mean of the first change curve to the standard deviation of the first change curve is obtained as the horizontal iris feature value, which can reflect the relative size of the iris feature dispersion in the horizontal direction of the projected image, and the ratio of the mean of the second change curve to the standard deviation of the second change curve is obtained as the longitudinal iris feature value, which can reflect the relative size of the iris feature dispersion in the vertical direction of the projected image; finally, the mean of the horizontal iris feature value and the longitudinal iris feature value is obtained as the iris feature, which can reflect the relative size of the iris feature dispersion in each direction of the projected image, thereby improving the feature extraction accuracy of the iris feature.

[0101] The above-mentioned image coordinate system refers to a coordinate system with the lower left corner of the projected image as the origin, the positive semi-axis of the horizontal axis extending to the right, and the positive semi-axis of the vertical axis extending upward.

[0102] The first change curve is a curve that uses the abscissa position information of each pixel block in the image coordinate system as the abscissa of the first change curve and uses the initial iris feature of each pixel block as the ordinate of the first change curve.

[0103] The first variation curve is used to characterize the variation of the iris features of the projected image in the horizontal direction.

[0104] The second change curve is a curve that uses the ordinate position information of each pixel block in the image coordinate system as the abscissa of the second change curve and uses the initial iris feature of each pixel block as the ordinate of the second change curve.

[0105] The second variation curve is used to characterize the variation of the iris features of the projection image in the vertical direction.

[0106] The above step A041 and the above step A042 may be performed in parallel, that is, the above step A041 and the above step A042 are performed at the same time.

[0107] Alternatively, the above step A041 and the above step A042 may be performed serially, for example, the above step A041 is performed first, and then the above step A042 is performed; or, the above step A042 is performed first, and then the above step A041 is performed.

[0108] The above-mentioned lateral iris feature value is used to characterize the relative size of the iris feature dispersion of the projected image in the horizontal direction.

[0109] The longitudinal iris feature value is used to characterize the relative size of the iris feature dispersion of the projected image in the vertical direction.

[0110] The above step A043 and the above step A044 may be performed in parallel, that is, the above step A043 and the above step A044 are performed at the same time.

[0111] Alternatively, the above-mentioned step A043 and the above-mentioned step A044 may be performed in series, for example, the above-mentioned step A043 is performed first, and then the above-mentioned step A044 is performed; or, the above-mentioned step A044 is performed first, and then the above-mentioned step A043 is performed.

[0112] In some implementations, in the above step S1023, obtaining the emotion level identifier according to the historical emotion history data and the historical driving habit data may include the following steps B01-B04: B01, based on historical emotional medical history data and historical driving habit data, combined with machine learning methods, obtain the driver's emotional change gradient; B02, determine whether the emotion change gradient is greater than a preset gradient threshold; if so, proceed to step B03; if not, proceed to step B04; B03, determining the first level mark as the emotion level mark; B04, determine the second level identifier as the emotion level identifier.

[0113] In this embodiment, in order to determine the driver's tendency of emotional changes, first, the driver's emotional change gradient is obtained based on historical emotional history data and historical driving habit data combined with machine learning methods; then, it is determined whether the emotional change gradient is greater than the preset gradient threshold; if the emotional change gradient is greater than the preset gradient threshold, it means that the driver's emotional changes tend to be extreme, and the first level mark is determined as the emotional level mark; if the emotional change gradient is less than or equal to the preset gradient threshold, it means that the driver's emotional changes tend to be smooth, and the second level mark is determined as the emotional level mark. It can be seen that by fully considering the driver's emotional illness and driving habits to determine the corresponding emotional level mark, it is beneficial to capture the driver's emotional change tendency, thereby improving the accuracy of emotion recognition.

[0114] It should be noted that before driving, the driver needs to actively upload the historical emotional medical history data to the cloud server. In actual application, if the cloud server does not store the driver's historical emotional medical history data, the driver's historical emotional medical history data is deemed to be empty.

[0115] The gradient threshold, the expression form of the first level identifier and the expression form of the second level identifier can be set according to actual conditions, and this embodiment does not specifically limit this.

[0116] For example, the first level identifier may be 1, and the second level identifier may be 0, but the present invention is not limited thereto.

[0117] In some embodiments, the whole vehicle data may include average wheel driving pressure, driver requested braking force, steering wheel angle, rear wheel angle, front wheel angle, driving speed, driving pressure corresponding to the automatic driving function of the target vehicle, and driving pressure corresponding to the electric control braking function of the target vehicle; In the above step S103, based on the vehicle data, the driving speed and steering angle of the target vehicle in the future time period are obtained as the target driving parameters of the target vehicle, which may include the following steps S1031-S1032: S1031, obtaining a driving speed of the target vehicle in a future time period according to the average wheel driving pressure, the driver's requested braking force, the driving speed, the driving pressure corresponding to the automatic driving function of the target vehicle, and the driving pressure corresponding to the electric control braking function of the target vehicle; S1032, obtaining a steering angle of the target vehicle in the future time period according to the steering wheel angle, the rear wheel angle, the front wheel angle and the driving speed of the target vehicle in the future time period.

[0118] In this embodiment, during actual driving, the driving pressure and real-time speed of the vehicle play a key role in affecting the speed of the vehicle at a future moment, and the real-time speed and wheel turning angle of the vehicle play a key role in affecting the turning angle of the vehicle at a future moment.

[0119] In this regard, in the aforementioned steps, the average wheel driving pressure, the driver's requested braking force, the steering wheel angle, the rear wheel angle, the front wheel angle, the driving speed, the driving pressure corresponding to the automatic driving function of the target vehicle, and the driving pressure corresponding to the electronic control braking function of the target vehicle are obtained. Various types of driving pressures can fully reflect the acceleration or braking conditions of the target vehicle, the driver's requested braking force can fully reflect the driver's braking intention, the real-time driving speed can fully reflect the power condition of the target vehicle, the steering wheel angle can fully reflect the driver's steering intention, and various wheel angles can fully reflect the steering condition of the target vehicle.

[0120] After obtaining the whole vehicle data, first, determine the target vehicle's driving speed in the future time period based on the average wheel driving pressure, the driver's requested braking force, the driving speed, the driving pressure corresponding to the target vehicle's automatic driving function, and the driving pressure corresponding to the target vehicle's electronic control braking function. In this way, the target vehicle's speed is predicted while fully considering the target vehicle's real-time acceleration, real-time braking, and real-time power conditions as well as the driver's real-time braking intention, thereby improving the accuracy of the vehicle's speed prediction. Then, determine the target vehicle's steering angle in the future time period based on the steering wheel angle, rear wheel angle, front wheel angle, and the target vehicle's driving speed in the future time period. In this way, the target vehicle's steering angle is predicted while fully considering the target vehicle's real-time steering condition and future speed as well as the driver's steering intention, thereby improving the accuracy of the vehicle's steering angle prediction.

[0121] The above-mentioned vehicle data may include average wheel driving pressure, driver requested braking force, steering wheel angle, rear wheel angle, front wheel angle, driving speed, driving pressure corresponding to the automatic driving function of the target vehicle and driving pressure corresponding to the electronic control braking function of the target vehicle, but is not limited to this.

[0122] The driving pressure corresponding to the automatic driving function of the target vehicle, the driving pressure corresponding to the electric control braking function of the target vehicle and the average wheel driving pressure are all used to characterize the acceleration or braking condition of the target vehicle.

[0123] The driver's requested braking force is used to represent the driver's braking intention.

[0124] The above steering wheel angle is used to represent the driver's steering intention.

[0125] The rear wheel turning angle and the front wheel turning angle are used to characterize the steering condition of the target vehicle.

[0126] The above-mentioned method of obtaining the driving speed of the target vehicle in a future time period based on the average wheel driving pressure, the driver's requested braking force, the driving speed, the driving pressure corresponding to the automatic driving function of the target vehicle, and the driving pressure corresponding to the electric control braking function of the target vehicle may include taking the average wheel driving pressure, the driver's requested braking force, the driving speed, the driving pressure corresponding to the automatic driving function of the target vehicle, and the driving pressure corresponding to the electric control braking function of the target vehicle as inputs of a pre-trained first prediction model, and predicting the driving speed of the target vehicle in the future time period through the first prediction model.

[0127] The above-mentioned first prediction model can be a long short-term memory neural network model trained by multiple preset first samples and the driving speed value corresponding to each preset first sample, wherein the first sample can include the driving pressure corresponding to the automatic driving function of the target vehicle, the driving pressure corresponding to the electric control braking function of the target vehicle, the average wheel driving pressure, the driver's requested braking force and the driving speed and other sample values.

[0128] Alternatively, the above-mentioned obtaining the driving speed of the target vehicle in the future time period based on the average wheel driving pressure, the driver's requested braking force, the driving speed, the driving pressure corresponding to the automatic driving function of the target vehicle, and the driving pressure corresponding to the electric control braking function of the target vehicle may include obtaining the driving speed of the target vehicle in the future time period based on the average wheel driving pressure, the driver's requested braking force, the driving speed, the driving pressure corresponding to the automatic driving function of the target vehicle, and the driving pressure corresponding to the electric control braking function of the target vehicle in combination with a machine learning method.

[0129] The above-mentioned obtaining the steering angle of the target vehicle in the future time period based on the steering wheel angle, rear wheel angle, front wheel angle and the driving speed of the target vehicle in the future time period may include inputting the steering wheel angle, rear wheel angle, front wheel angle and the driving speed of the target vehicle in the future time period into a pre-trained second prediction model, and predicting the steering angle of the target vehicle in the future time period by the second prediction model.

[0130] The above-mentioned second prediction model can be a long short-term memory neural network model trained by multiple preset second samples and the steering angle value corresponding to each preset second sample, wherein the second sample can include sample values ​​such as steering wheel angle, rear wheel angle, front wheel angle and driving speed.

[0131] Alternatively, the above-mentioned obtaining the steering angle of the target vehicle in the future time period based on the steering wheel angle, rear wheel angle, front wheel angle and the driving speed of the target vehicle in the future time period may include obtaining the steering angle of the target vehicle in the future time period based on the steering wheel angle, rear wheel angle, front wheel angle and the driving speed of the target vehicle in the future time period in combination with a machine learning method.

[0132] In some embodiments, in the above step S104, according to the driving road data, obtaining the average speed change and the average angle change of the target vehicle in the future time period as the target driving change of the target vehicle may include the following steps S1041-S1042: S1041, obtaining an average speed change of the target vehicle in a future time period according to the traffic congestion coefficient and the road roughness coefficient; S1042, obtaining an average angle change of the target vehicle in a future time period according to the traffic congestion coefficient and the road roughness coefficient.

[0133] In this embodiment, the traffic congestion and road roughness of the road have a certain impact on the speed change and steering change of the vehicle at the future moment. In this regard, the average speed change of the target vehicle in the future time period is determined according to the traffic congestion coefficient and road roughness coefficient of the road, and the average angle change of the target vehicle in the future time period is determined according to the traffic congestion coefficient and road roughness coefficient of the road. In this way, the speed change and average angle change of the target vehicle are predicted while fully considering the traffic congestion and road roughness of the road on which the vehicle is traveling, and the prediction accuracy of the speed change and average angle change of the vehicle is effectively improved.

[0134] The above-mentioned method of obtaining the average speed change of the target vehicle in the future time period based on the traffic congestion coefficient and the road roughness coefficient may include inputting the traffic congestion coefficient and the road roughness coefficient into a pre-trained third prediction model, and predicting the average speed change of the target vehicle in the future time period through the third prediction model.

[0135] The above-mentioned third prediction model can be a long short-term memory neural network model trained by multiple preset third samples and the average vehicle speed change corresponding to each preset third sample, wherein the third sample can include sample values ​​such as traffic congestion coefficient and road roughness coefficient.

[0136] Alternatively, the above-mentioned obtaining the average speed change of the target vehicle in the future time period based on the traffic congestion coefficient and the road roughness coefficient may include obtaining the average speed change of the target vehicle in the future time period based on the traffic congestion coefficient and the road roughness coefficient in combination with a machine learning method.

[0137] The above-mentioned method of obtaining the average angular change of the target vehicle in the future time period based on the traffic congestion coefficient and the road roughness coefficient may include inputting the traffic congestion coefficient and the road roughness coefficient into a pre-trained fourth prediction model, and predicting the average angular change of the target vehicle in the future time period through the fourth prediction model.

[0138] The fourth prediction model may be a long short-term memory neural network model trained by a plurality of preset third samples and an average angle change corresponding to each preset fourth sample.

[0139] Alternatively, the above-mentioned obtaining the average angular change of the target vehicle in the future time period based on the traffic congestion coefficient and the road roughness coefficient may include obtaining the average angular change of the target vehicle in the future time period based on the traffic congestion coefficient and the road roughness coefficient in combination with a machine learning method.

[0140] The above step S1041 and the above step S1042 may be performed in parallel, that is, the above step S1041 and the above step S1042 are performed at the same time.

[0141] Alternatively, the above step S1041 and the above step S1042 may be performed in series, for example, the above step S1041 is performed first, and then the above step S1042 is performed; or, the above step S1042 is performed first, and then the above step S1041 is performed.

[0142] In some embodiments, in the above step S105, performing collision warning processing on the target vehicle according to the driver emotion coefficient, target driving parameters and target driving change amount of the target vehicle may include the following steps S1051-S1053: S1051, obtaining a target driving trajectory of the target vehicle according to the driver emotion coefficient, the target driving parameter and the target driving change amount of the target vehicle; S1052, obtaining a target driving trajectory of at least one surrounding vehicle, where the surrounding vehicles are within a preset range of the target vehicle; S1053: If the target driving trajectory of the target vehicle coincides with the target driving trajectory of any surrounding vehicle, a collision warning process is performed on the target vehicle.

[0143] In this embodiment, first, the target driving trajectory of the target vehicle is obtained according to the driver emotion coefficient, the target driving parameter and the target driving variation of the target vehicle; then, the target driving trajectory of at least one surrounding vehicle is obtained, and the surrounding vehicles are located within the preset range of the target vehicle; then, it is determined whether the target driving trajectory of the target vehicle coincides with the target driving trajectory of any surrounding vehicle. If so, the target vehicle is subjected to collision warning processing, otherwise, it returns to the above step S101 to realize cyclic detection. It can be seen that the target driving trajectory of the target vehicle is determined under the condition that the driving condition of the target vehicle in the future time period and the influence of the driver's emotion and road factors on the driving condition of the target vehicle are fully considered, so as to improve the accuracy of the target vehicle's driving trajectory, and then the target driving trajectory of the target vehicle and the target driving trajectory of the surrounding vehicles are used to realize the collision warning processing of the target vehicle, so as to fully consider the interactive influence between the target vehicle and the other vehicles on the road, effectively improve the accuracy of vehicle collision warning, improve the driving safety of the vehicle, and reduce vehicle collision accidents.

[0144] The target driving trajectory of the target vehicle is obtained based on the driver emotion coefficient, target driving parameters and target driving change of the target vehicle, which may include obtaining the driver emotion coefficient, target driving parameters and target driving change of the target vehicle as inputs of a pre-trained fifth prediction model, and predicting the target driving trajectory of the target vehicle through the fifth prediction model, but is not limited to this.

[0145] The fifth prediction model mentioned above can be set according to actual conditions, and this embodiment does not make any specific limitation to this.

[0146] For example, the fifth prediction model mentioned above can be a long short-term memory neural network model, but is not limited to this.

[0147] The above-mentioned surrounding vehicles refer to vehicles located within a preset range of the target vehicle.

[0148] The above preset range can be set according to actual conditions, and this embodiment does not specifically limit this.

[0149] The target driving trajectory of the surrounding vehicles is realized in the same manner as the target driving trajectory of the target vehicle, and will not be described in detail in this embodiment.

[0150] The target driving trajectory of the target vehicle and the target driving trajectory of the surrounding vehicles may be data stored in a cloud server, but are not limited thereto.

[0151] The above-mentioned obtaining the target driving trajectory of at least one surrounding vehicle may include obtaining the target driving trajectory of at least one surrounding vehicle through a cloud server, but is not limited to this.

[0152] The above-mentioned collision warning processing for the target vehicle may include outputting a collision warning signal in the form of a prompt sound or an instrument display to remind the driver that the vehicle may collide in the future, but is not limited to this.

[0153] In some embodiments, in the above step S1051, obtaining the target driving trajectory of the target vehicle according to the driver emotion coefficient, the target driving parameter and the target driving change of the target vehicle may include the following steps C01-C05: C01, determining a first driving speed range of the target vehicle according to the driving speed and average speed change of the target vehicle in a future time period; C02, determining a first steering angle range of the target vehicle according to the steering angle and the average angle change of the target vehicle in a future time period; C03, correcting the first driving speed range according to the driver's emotion coefficient to obtain a second driving speed range of the target vehicle; C04, correcting the first steering angle range according to the driver emotion coefficient to obtain a second steering angle range of the target vehicle; C05: Obtain a target driving trajectory of the target vehicle according to the second driving speed range and the second steering angle range in combination with a pre-trained trajectory prediction model.

[0154] In the present embodiment, firstly, a first driving speed range of the target vehicle is determined based on the driving speed and the average speed change of the target vehicle in a future time period, and a first steering angle range of the target vehicle is determined based on the steering angle and the average angle change of the target vehicle in a future time period; then, the first driving speed range is corrected according to the driver emotion coefficient to obtain a second driving speed range of the target vehicle, and the first steering angle range is corrected according to the driver emotion coefficient to obtain a second steering angle range of the target vehicle, thereby improving the accuracy of the speed range and the steering angle range of the target vehicle; finally, the second driving speed range and the second steering angle range are input into a pre-trained trajectory prediction model, and the target driving trajectory of the target vehicle is predicted by the trajectory prediction model, thereby improving the accuracy of the driving trajectory of the target vehicle.

[0155] The first driving speed range is used to characterize changes in the driving speed of the target vehicle in a future time period.

[0156] The above-mentioned determining the first driving speed range of the target vehicle based on the driving speed and the average speed change of the target vehicle in the future time period may include determining the first driving speed range of the target vehicle based on the driving speed and the average speed change of the target vehicle in the future time period in combination with a machine learning method, but is not limited to this.

[0157] The first steering angle range is used to characterize changes in the steering angle of the target vehicle in a future time period.

[0158] The above-mentioned determination of the first steering angle range of the target vehicle based on the steering angle and the average angle change of the target vehicle in the future time period may include determining the first steering angle range of the target vehicle based on the steering angle and the average angle change of the target vehicle in the future time period in combination with a machine learning method, but is not limited to this.

[0159] The above step C01 and the above step C02 may be performed in parallel, that is, the above step C01 and the above step C02 are performed at the same time.

[0160] Alternatively, the above step C01 and the above step C02 may be performed in series, for example, the above step C01 is performed first, and then the above step C02 is performed; or, the above step C02 is performed first, and then the above step C01 is performed.

[0161] The second driving speed range is used to represent the corrected first driving speed range.

[0162] The above-mentioned correction processing of the first driving speed range according to the driver emotion coefficient to obtain the second driving speed range of the target vehicle may include obtaining the second driving speed range of the target vehicle according to the driver emotion coefficient and the first driving speed range in combination with a machine learning method, but is not limited to this.

[0163] The second steering angle range is used to represent the corrected first steering angle range.

[0164] The above-mentioned correction processing of the first steering angle range according to the driver emotion coefficient to obtain the second steering angle range of the target vehicle may include obtaining the second steering angle range of the target vehicle according to the driver emotion coefficient and the first steering angle range in combination with a machine learning method, but is not limited to this.

[0165] The above step C03 and the above step C04 may be performed in parallel, that is, the above step C03 and the above step C04 are performed at the same time.

[0166] Alternatively, the above step C03 and the above step C04 may be performed in series, for example, the above step C03 is performed first, and then the above step C04 is performed; or, the above step C04 is performed first, and then the above step C03 is performed.

[0167] The above trajectory prediction model can be set according to actual conditions, and this embodiment does not make any specific limitation to this.

[0168] For example, the trajectory prediction model may be a long short-term memory neural network model, but is not limited thereto.

[0169] In some embodiments, in the above step C01, determining the first driving speed range of the target vehicle according to the driving speed and the average speed change of the target vehicle in the future time period may include the following steps C011-C013: C011, obtaining the maximum value of the target vehicle's driving speed and the sum of the average speed change in the future time period as the upper limit of the first driving speed range; C012, obtaining the minimum value of the target vehicle's driving speed and the sum of the average speed change in the future time period as the lower limit value of the first driving speed range; C013: Determine the first driving speed range by using the upper limit value and the lower limit value of the first driving speed range.

[0170] In this embodiment, in order to determine the first driving speed range of the target vehicle, first, the maximum and minimum values ​​of the driving speed of the target vehicle in the future time period are obtained; then, the sum of the maximum value and the average speed change is obtained as the upper limit value of the first driving speed range, and the sum of the minimum value and the average speed change is obtained as the lower limit value of the first driving speed range; finally, the first driving speed range is determined by the upper limit value and the lower limit value of the first driving speed range. In this way, the first driving speed range of the target vehicle is determined by the extreme value and the average speed change of the driving speed of the target vehicle in the future time period, while fully considering the influence of road factors on the driving conditions of the target vehicle in the future time period, which can effectively improve the accuracy of the driving speed range of the target vehicle.

[0171] In some embodiments, in the above step C02, determining the first steering angle range of the target vehicle according to the steering angle and the average angle change of the target vehicle in the future time period may include the following steps C021-C023: C021, obtaining the maximum value and the sum of the average angle change of the steering angle of the target vehicle in the future time period as the upper limit value of the first steering angle range; C022, obtaining the minimum value of the steering angle of the target vehicle in the future time period and the sum of the average angle change as the lower limit value of the first steering angle range; C023, determining the first steering angle range according to the upper limit value and the lower limit value of the first steering angle range.

[0172] In this embodiment, in order to determine the first steering angle range of the target vehicle, first, the maximum and minimum values ​​of the steering angle of the target vehicle in the future time period are obtained; then, the sum of the maximum value and the average angle change is obtained as the upper limit value of the first steering angle range, and the sum of the minimum value and the average angle change is obtained as the lower limit value of the first steering angle range; finally, the first steering angle range is determined by the upper limit value and the lower limit value of the first steering angle range. In this way, the first steering angle range of the target vehicle is determined by the extreme value and the average angle change of the steering angle of the target vehicle in the future time period, while fully considering the influence of road factors on the driving condition of the target vehicle in the future time period, which can effectively improve the accuracy of the steering angle range of the target vehicle.

[0173] In some implementations, in the above step C03, the first driving speed range is corrected according to the driver emotion coefficient to obtain the second driving speed range of the target vehicle, which may include the following steps C031-C032: C031, selecting a correction coefficient corresponding to the driver emotion coefficient from the first correction coefficient data as the vehicle speed correction coefficient; the first correction coefficient data includes a plurality of preset driver emotion coefficients and a correction coefficient corresponding to each preset driver emotion coefficient; C032, obtaining the product of the vehicle speed correction coefficient and the first driving speed range as the second driving speed range.

[0174] In the present embodiment, first, a correction coefficient corresponding to the driver's emotion coefficient is selected from the first correction coefficient data as the vehicle speed correction coefficient, and the first correction coefficient data mainly includes a plurality of preset driver emotion coefficients and a correction coefficient corresponding to each preset driver emotion coefficient; then, the product of the vehicle speed correction coefficient and the first driving speed range is obtained as the second driving speed range. It can be seen that, while fully considering the influence of the driver's emotional factors on the driving condition of the target vehicle, the speed correction coefficient for correcting the driving speed range is determined by the driver's emotion coefficient, and then the product of the vehicle speed correction coefficient and the first driving speed range is obtained as the second driving speed range, thereby realizing the correction of the driving speed range, which can effectively improve the accuracy of the driving speed range of the target vehicle.

[0175] The first correction coefficient data may include a plurality of preset driver emotion coefficients and a correction coefficient corresponding to each preset driver emotion coefficient.

[0176] The first correction coefficient data may be table data or chart data, but is not limited thereto.

[0177] In some embodiments, in the above step C04, the first steering angle range is corrected according to the driver emotion coefficient to obtain the second steering angle range of the target vehicle, which may include the following steps C041-C042: C041, selecting a correction coefficient corresponding to the driver emotion coefficient from the second correction coefficient data as the turning angle correction coefficient; the second correction coefficient data includes a plurality of preset driver emotion coefficients and a correction coefficient corresponding to each preset driver emotion coefficient; C042, obtaining the product of the steering angle correction coefficient and the first steering angle range as the second steering angle range.

[0178] In the present embodiment, first, a correction coefficient corresponding to the driver's emotion coefficient is selected from the second correction coefficient data as the steering angle correction coefficient, and the second correction coefficient data mainly includes a plurality of preset driver emotion coefficients and a correction coefficient corresponding to each preset driver emotion coefficient; then, the product of the steering angle correction coefficient and the first steering angle range is obtained as the second steering angle range. It can be seen that, while fully considering the influence of the driver's emotional factors on the driving condition of the target vehicle, the steering angle correction coefficient for correcting the steering angle range is determined by the driver's emotion coefficient, and then the product of the steering angle correction coefficient and the first steering angle range is obtained as the second steering angle range, thereby realizing the correction of the steering angle range. This can effectively improve the accuracy of the steering angle range of the target vehicle.

[0179] The second correction coefficient data may include a plurality of preset driver emotion coefficients and a correction coefficient corresponding to each preset driver emotion coefficient.

[0180] The second correction coefficient data may be table data or chart data, but is not limited thereto.

[0181] To facilitate the understanding of the vehicle collision warning method of the present application, the actual application scenario of the vehicle collision warning method of the present application is used as an example. The specific process of performing collision warning on the target vehicle in this example includes the following steps S201-S208.

[0182] S201, obtaining the driver's eyeball image, pupil image, pulse signal, historical emotional medical history data and historical driving habit data as the driver's physiological data of the target vehicle, obtaining the traffic congestion coefficient and road roughness coefficient of the road on which the target vehicle is traveling as the target vehicle's driving road data, and obtaining the average wheel driving pressure, driver-requested braking force, steering wheel angle, rear wheel angle, front wheel angle, driving speed, driving pressure corresponding to the target vehicle's automatic driving function and driving pressure corresponding to the target vehicle's electronic control braking function as the target vehicle's whole vehicle data.

[0183] S202, firstly, fuse and extract features of the eyeball image and pupil image to obtain iris features, then extract features of the pulse signal through a convolutional neural network model to obtain pulse features, then obtain an emotion level identifier based on historical emotional medical history data and historical driving habit data, and finally obtain a driver emotion coefficient based on iris features, pulse features, emotion level identifiers, traffic congestion coefficient and road roughness coefficient in combination with machine learning methods.

[0184] For the extraction of iris features, first, the pupil image is projected onto the eyeball image to obtain a projection image; then, the projection image is divided into blocks to obtain a plurality of pixel blocks; thereafter, for each pixel block, the feature of the pixel block is extracted through a local binary pattern to obtain the value of each pixel point in the pixel block, the pixel point value is 1 or 0, and then it is determined whether there is at least one pixel point value greater than 0 in the pixel block, if so, the initial iris feature of the pixel block is determined to be 1, otherwise the initial iris feature of the pixel block is determined to be 0; finally, the ratio of the mean of the first change curve to the standard deviation of the first change curve is obtained as the lateral iris feature. The method comprises the following steps: obtaining a ratio of the mean of the second change curve to the standard deviation of the second change curve as the longitudinal iris feature value, and calculating the mean of the transverse iris feature value and the longitudinal iris feature value as the iris feature, wherein the first change curve refers to a curve having the horizontal coordinate position information of each pixel block in the image coordinate system as the horizontal coordinate of the first change curve, and the initial iris feature of each pixel block as the vertical coordinate of the first change curve; and the second change curve refers to a curve having the vertical coordinate position information of each pixel block in the image coordinate system as the horizontal coordinate of the second change curve, and the initial iris feature of each pixel block as the vertical coordinate of the second change curve.

[0185] To determine the emotion level identification, first, the driver's emotion change gradient is obtained based on historical emotion history data and historical driving habit data combined with machine learning methods; then, it is determined whether the emotion change gradient is greater than the preset gradient threshold; if the emotion change gradient is greater than the preset gradient threshold, it means that the driver's emotion changes tend to be extreme, and the emotion level identification is determined to be 1; if the emotion change gradient is less than or equal to the preset gradient threshold, it means that the driver's emotion changes tend to be gentle, and the emotion level identification is determined to be 0.

[0186] S203, based on the average wheel driving pressure, the driver's requested braking force, the driving speed, the driving pressure corresponding to the automatic driving function of the target vehicle and the driving pressure corresponding to the electric control braking function of the target vehicle, combined with the machine learning method, the driving speed of the target vehicle in the future time period is obtained, and then based on the steering wheel angle, the rear wheel angle, the front wheel angle and the driving speed of the target vehicle in the future time period, combined with the machine learning method, the steering angle of the target vehicle in the future time period is obtained.

[0187] S204, based on the traffic congestion coefficient and the road roughness coefficient, combined with the machine learning method, obtain the average speed change of the target vehicle in the future time period. At the same time, based on the traffic congestion coefficient and the road roughness coefficient, combined with the machine learning method, obtain the average angle change of the target vehicle in the future time period.

[0188] The above step S202, the above step S203 and the above step S204 may be performed simultaneously or in series.

[0189] S205, obtaining the maximum value of the target vehicle's driving speed in the future time period and the sum of the average speed change as the upper limit of the first driving speed range, obtaining the minimum value of the target vehicle's driving speed in the future time period and the sum of the average speed change as the lower limit of the first driving speed range, and then obtaining the first driving speed range of the target vehicle, and then selecting a correction coefficient corresponding to the driver's emotion coefficient from the first correction coefficient data as the speed correction coefficient, and obtaining the product of the speed correction coefficient and the first driving speed range as the second driving speed range of the target vehicle, wherein the first correction coefficient data includes a plurality of preset driver emotion coefficients and a correction coefficient corresponding to each preset driver emotion coefficient; At the same time, the maximum value and the sum of the average angle change of the steering angle of the target vehicle in the future time period are obtained as the upper limit value of the first steering angle range, and the minimum value and the sum of the average angle change of the steering angle of the target vehicle in the future time period are obtained as the lower limit value of the first steering angle range, so as to obtain the first steering angle range of the target vehicle, and then select the correction coefficient corresponding to the driver emotion coefficient from the second correction coefficient data as the steering angle correction coefficient, and obtain the product of the steering angle correction coefficient and the first steering angle range as the second steering angle range of the target vehicle, wherein the second correction coefficient data includes multiple preset driver emotion coefficients and the correction coefficient corresponding to each preset driver emotion coefficient.

[0190] S206: Obtain a target driving trajectory of the target vehicle according to the second driving speed range and the second steering angle range in combination with a pre-trained trajectory prediction model.

[0191] S207, obtaining the target driving trajectory of surrounding vehicles from the cloud server, and the surrounding vehicles are located within a preset range of the target vehicle.

[0192] S208, determine whether the target driving trajectory of the target vehicle coincides with the target driving trajectory of any surrounding vehicle; if so, output a collision warning signal in the form of a prompt sound or instrument display to remind the driver that the vehicle may collide in the future; otherwise, return to step S201 to implement loop detection.

[0193] In addition, refer to Figure 2 , the embodiment of the present application also provides a vehicle collision warning device, which may include: The acquisition module 301 is used to acquire the driver's physiological data, vehicle data and driving road data of the target vehicle; A first processing module 302 is used to obtain a driver emotion coefficient according to the driver's physiological data and the driving road data; The second processing module 303 is used to obtain the driving speed and steering angle of the target vehicle in the future time period as the target driving parameters of the target vehicle according to the vehicle data; The third processing module 304 is used to obtain the average speed change and the average angle change of the target vehicle in the future time period according to the driving road data as the target driving change of the target vehicle; The fourth processing module 305 is used to perform collision warning processing on the target vehicle according to the driver emotion coefficient, target driving parameters and target driving change amount of the target vehicle.

[0194] The contents of the above method embodiments are all applicable to the present device embodiments. The functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0195] Finally, refer to Figure 3 , the embodiment of the present application further provides a vehicle, which may include: at least one processor 401; At least one memory 402, used to store at least one program; When at least one program is executed by at least one processor 401, at least one processor 401 implements the above-mentioned vehicle collision warning method.

[0196] The above-mentioned vehicles can be private cars, such as sedans, sport utility vehicles (SUV), multi-purpose vehicles (MPV) or pickup trucks, etc., or they can be commercial vehicles, such as vans, buses, small trucks or large trailers, etc. They can also be gasoline vehicles or new energy vehicles such as hybrid vehicles and pure electric vehicles.

[0197] The above-mentioned memory 402, as a non-transient network system, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory 402 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory 402 may optionally include a memory 402 remotely arranged relative to the processor 401, and these remote memories 402 may be connected to the processor 401 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0198] The above-mentioned memory 402 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device or a random access memory (RAM). The memory 402 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 402, and the processor 401 is called to execute the method of the embodiment of this application.

[0199] The processor 401 may be implemented by a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solution provided in the embodiments of the present application.

[0200] In some embodiments, the vehicle may further include: Input / output interface, used to realize information input and output; Communication interface, used to realize communication interaction between this device and other devices. Communication can be realized through wired methods (such as USB, network cable, etc.) or wireless methods (such as mobile network, WIFI, Bluetooth, etc.); A bus that transmits information between various components of the device (e.g., processor 401, memory 402, input / output interfaces, and communication interfaces); The processor 401 , the memory 402 , the input / output interface and the communication interface can be connected to each other in communication within the device via a bus.

[0201] Similarly, the contents of the above method embodiments are all applicable to the present vehicle embodiment. The functions specifically implemented by the present vehicle embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0202] In some optional embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the application is provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operation and logic flow presented herein. Optional embodiments are expected, wherein the order of various operations is changed and the sub-operation described as a part of a larger operation is performed independently.

[0203] In addition, although the present application is described in the context of functional modules, it should be understood that, unless otherwise specified, one or more of the functions and / or features can be integrated into a single physical device and / or software module, or one or more functions and / or features can be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present application. More specifically, in view of the properties, functions, and internal relationships of the various functional modules in the device disclosed herein, the actual implementation of the module will be understood within the conventional techniques of the engineer. Therefore, those skilled in the art can implement the present application set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present application, which is determined by the full scope of the attached claims and their equivalents.

[0204] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several programs to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0205] The logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable programs for implementing logical functions, and may be embodied in any computer-readable medium for use by a program execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch and execute a program from a program execution system, device or apparatus), or in conjunction with such program execution system, device or apparatus. For purposes of this specification, a "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by a program execution system, device or apparatus, or in conjunction with such program execution system, device or apparatus.

[0206] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0207] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable program execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0208] In the above description of this specification, the description with reference to the terms "one embodiment / example", "another embodiment / example" or "certain embodiments / examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0209] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present application, and that the scope of the present application is defined by the claims and their equivalents.

[0210] The above is a specific description of the preferred implementation of the present application, but the present application is not limited to the described embodiments. Technical personnel familiar with the field may make various equivalent modifications or substitutions without violating the spirit of the present application. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present application.

Claims

1. A vehicle collision warning method, It is characterized in that The following steps are involved: Obtain the driver's physiological data, vehicle data and driving road data of the target vehicle; Obtaining a driver emotion coefficient according to the driver physiological data and the driving road data; According to the whole vehicle data, the driving speed and steering angle of the target vehicle in a future time period are obtained as target driving parameters of the target vehicle; According to the driving road data, an average speed change and an average angle change of the target vehicle in a future time period are obtained as a target driving change of the target vehicle; According to the driver emotion coefficient, target driving parameters and target driving variation of the target vehicle, collision warning processing is performed on the target vehicle.

2. The vehicle collision warning method according to claim 1, It is characterized in that The driver's physiological data includes the driver's eyeball image, pupil image, pulse signal, historical emotional history data and historical driving habit data, and the driving road data includes the traffic congestion coefficient and road roughness coefficient of the road on which the target vehicle is traveling; The step of obtaining the driver's emotion coefficient according to the driver's physiological data and the driving road data includes: Performing fusion processing and feature extraction on the eyeball image and the pupil image to obtain iris features; Extracting features from the pulse signal to obtain pulse features; Obtaining an emotion level indicator according to the historical emotion medical history data and the historical driving habit data; The driver emotion coefficient is obtained according to the iris feature, the pulse feature, the emotion level identifier, the traffic congestion coefficient and the road surface roughness coefficient.

3. The vehicle collision warning method according to claim 2, It is characterized in that The step of fusing the eyeball image and the pupil image and extracting features to obtain iris features includes: Projecting the pupil image onto the eyeball image to obtain a projected image; Performing block processing on the projection image to obtain a plurality of pixel blocks; Extracting features from each pixel block to obtain initial iris features of each pixel block; The iris feature is obtained according to the initial iris feature of each pixel block.

4. The vehicle collision warning method according to claim 3, It is characterized in that The step of extracting features from each pixel block to obtain initial iris features of each pixel block includes: Extracting features of the pixel block by using a local binary pattern to obtain a value of each pixel in the pixel block; Comparing the value of each pixel in the pixel block with a preset pixel threshold; If there is at least one pixel point in the pixel block whose value is greater than the pixel threshold, determining a preset first value as the initial iris feature of the pixel block; If all pixel values ​​in the pixel block are less than or equal to the pixel threshold, a preset second value is determined as the initial iris feature of the pixel block.

5. The vehicle collision warning method according to claim 3, It is characterized in that The obtaining the iris feature according to the initial iris feature of each pixel block comprises: The first change curve is constructed by taking the horizontal coordinate position information of each pixel block in the image coordinate system as the horizontal coordinate of the first change curve, and taking the initial iris feature of each pixel block as the vertical coordinate of the first change curve; wherein the origin of the image coordinate system is the lower left corner of the projection image, the positive semi-axis of the horizontal axis of the image coordinate system extends to the right, and the positive semi-axis of the vertical axis of the image coordinate system extends upward; Constructing the second change curve by taking the ordinate position information of each pixel block in the image coordinate system as the abscissa of the second change curve and taking the initial iris feature of each pixel block as the ordinate of the second change curve; Acquire a ratio of a mean value of the first change curve to a standard deviation of the first change curve as a lateral iris feature value; acquiring a ratio of a mean value of the second change curve to a standard deviation of the second change curve as a longitudinal iris feature value; An average value of the horizontal iris feature value and the vertical iris feature value is obtained as the iris feature.

6. The vehicle collision warning method according to claim 1, It is characterized in that The whole vehicle data includes average wheel driving pressure, driver requested braking force, steering wheel angle, rear wheel angle, front wheel angle, driving speed, driving pressure corresponding to the automatic driving function of the target vehicle and driving pressure corresponding to the electric control braking function of the target vehicle; The step of obtaining the driving speed and steering angle of the target vehicle in a future time period according to the vehicle data includes: Obtaining a driving speed of the target vehicle in a future time period according to the average wheel driving pressure, the driver requested braking force, the driving speed, the driving pressure corresponding to the automatic driving function of the target vehicle, and the driving pressure corresponding to the electronic control braking function of the target vehicle; The steering angle of the target vehicle in the future time period is obtained according to the steering wheel angle, the rear wheel angle, the front wheel angle and the driving speed of the target vehicle in the future time period.

7. The vehicle collision warning method according to claim 1, It is characterized in that The method of performing collision warning processing on the target vehicle according to the driver emotion coefficient, target driving parameter and target driving variation of the target vehicle comprises: Obtaining a target driving trajectory of the target vehicle according to the driver emotion coefficient, the target driving parameter and the target driving change of the target vehicle; Acquire a target driving trajectory of at least one surrounding vehicle, wherein the surrounding vehicle is located within a preset range of the target vehicle; If the target driving trajectory of the target vehicle coincides with the target driving trajectory of any of the surrounding vehicles, a collision warning process is performed on the target vehicle.

8. The vehicle collision warning method according to claim 7, It is characterized in that The step of obtaining a target driving trajectory of the target vehicle according to the driver emotion coefficient, the target driving parameter and the target driving variation of the target vehicle comprises: Determining a first driving speed range of the target vehicle according to the driving speed and average speed change of the target vehicle in a future time period; Determining a first steering angle range of the target vehicle according to the steering angle and the average angle change of the target vehicle in a future time period; According to the driver emotion coefficient, the first driving speed range is corrected to obtain a second driving speed range of the target vehicle; According to the driver emotion coefficient, the first steering angle range is corrected to obtain a second steering angle range of the target vehicle; According to the second driving speed range and the second steering angle range, in combination with a pre-trained trajectory prediction model, a target driving trajectory of the target vehicle is obtained.

9. A vehicle collision warning device, It is characterized in that include: An acquisition module, used to acquire the driver's physiological data, vehicle data and driving road data of the target vehicle; A first processing module, used for obtaining a driver emotion coefficient according to the driver physiological data and the driving road data; A second processing module is used to obtain the driving speed and steering angle of the target vehicle in a future time period as the target driving parameters of the target vehicle according to the vehicle data; A third processing module is used to obtain, according to the driving road data, an average speed change and an average angle change of the target vehicle in a future time period as a target driving change of the target vehicle; The fourth processing module is used to perform collision warning processing on the target vehicle according to the driver emotion coefficient, target driving parameters and target driving change amount of the target vehicle.

10. A vehicle, It is characterized in that include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the vehicle collision warning method as described in any one of claims 1-8.

Images