CN110171361B - Automobile safety early warning method based on emotion and driving tendency of driver - Google Patents
Automobile safety early warning method based on emotion and driving tendency of driver Download PDFInfo
- Publication number
- CN110171361B CN110171361B CN201910521885.2A CN201910521885A CN110171361B CN 110171361 B CN110171361 B CN 110171361B CN 201910521885 A CN201910521885 A CN 201910521885A CN 110171361 B CN110171361 B CN 110171361B
- Authority
- CN
- China
- Prior art keywords
- driver
- vehicle
- emotion
- driving
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60Q—ARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
- B60Q9/00—Arrangement or adaptation of signal devices not provided for in one of main groups B60Q1/00 - B60Q7/00, e.g. haptic signalling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24133—Distances to prototypes
- G06F18/24137—Distances to cluster centroïds
- G06F18/2414—Smoothing the distance, e.g. radial basis function networks [RBFN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24147—Distances to closest patterns, e.g. nearest neighbour classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/59—Context or environment of the image inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
- G06V20/597—Recognising the driver's state or behaviour, e.g. attention or drowsiness
Abstract
The invention discloses an automobile driving safety early warning method considering the emotion and driving tendency of a driver, belongs to the field of image recognition and intelligent transportation, comprehensively considers two factors of the emotion and the driving tendency of the driver, and carries out early warning on automobile driving behaviors. An automobile driving safety early warning method considering the emotion and driving tendency of a driver comprises the following steps: the method comprises the following steps of collecting driving tendency data of a driver, collecting face data of the driver, recognizing emotion, judging anger emotion, judging early warning, collecting vehicle information data, judging a vehicle driving state threshold value and judging alarm. The automobile driving safety early warning method considering the emotion and the driving tendency of the driver can confirm the driving tendency of the driver according to the acquired data; the emotion change of a driver and the running state of a driven vehicle can be monitored in real time in the running process of the vehicle; the warning prompt appears when the driver is angry, and the warning prompt appears when the driving state of the vehicle exceeds the threshold value of the normal driving state. The driver's improper operation is reduced through the early warning and the alarm prompt, and the risk of accident occurrence is reduced.
Description
Technical Field
The invention relates to the field of image recognition and intelligent traffic, in particular to an automobile driving safety early warning method considering the emotion and driving tendency of a driver.
Background
In recent years, with the development of society, the progress of era and the vigorous development of automobile intelligence, the control system of the automobile is increasingly complex, and the contradiction between the driver and the automobile control system is increasingly prominent. Meanwhile, "road rage" and the driving tendency of the driver have a crucial influence on the driving safety. According to the relevant data, most traffic accidents can be attributed to abnormal driving emotions and overstimulated driving tendencies. How to timely identify the abnormal driving emotion and the overstimulated driving tendency is an important way for avoiding traffic accidents and ensuring the safe driving of vehicles.
The existing automobile safety early warning method rarely takes the driving emotion into consideration, but the driving emotion plays an important role in driving safety and cannot be ignored. Emotion recognition is an important means for analyzing driving emotion, and currently, the most effective emotion recognition is based on an image recognition algorithm of a convolutional neural network, and the facial expression of a driver is shot, so that the shot picture is recognized, and the emotion of the driver at the moment is judged. Therefore, when safety early warning is carried out on the automobile, the driving emotion of a driver needs to be considered.
Disclosure of Invention
The invention provides an automobile driving safety early warning method considering the emotion and driving tendency of a driver, aiming at overcoming the problems of angry emotion and overstimulation of the driver in the driving process, and reducing the risk of accidents by effectively preventing and alarming the driver and providing corresponding prompts for the driver.
The invention provides an automobile driving safety early warning method considering the emotion and driving tendency of a driver, which comprises the following steps of:
s1, evaluating the driving tendency of the driver: before the vehicle is started, a questionnaire survey is carried out on a vehicle driver, and the driving tendency of the driver is judged by comparing data in a database;
s2, aggressive authentication: judging whether the driver is aggressive or not according to the data collected in the step S1 and the judgment result, and if so, entering the step S3; if no, go to step S12;
s3, acquiring driver face data and recognizing emotion: in the driving process of the vehicle, the facial data of a driver are collected in real time, and the emotion of the driver is identified according to the collected data;
s4, authentication of angry emotion: judging whether the emotion of the driver is angry according to the data collected in the step S3 and the judgment result, and if yes, entering a step S5; if no, go to step S12;
s5, early warning of angry emotion: according to the authentication result of the step S4, when the driver is angry, music for relieving angry emotion is automatically played to relieve the angry emotion of the driver;
s6, re-certifying angry emotion: after the music playing in step S5 is completed, recognizing the emotion of the driver again, and determining whether the angry emotion of the driver has disappeared, if it is determined to be "no", proceeding to step S7; if yes, the flow proceeds to step S12;
s7, collecting vehicle running information: in the running process of the vehicle, real-time data acquisition is carried out on the running information of the vehicle;
s8, vehicle driving state primary alarm judgment: judging whether the vehicle exceeds a safe driving threshold value or not according to the vehicle driving data collected in the step S7, and if yes, entering the step S9; if no, go to step S12;
s9, primary alarm: performing a primary alarm to the driver according to the judgment result of the step S8;
s10, secondary alarm judgment of the vehicle running state: judging whether the vehicle is recovered to be within the safe driving threshold value or not according to the vehicle driving data collected in the step S7, and if not, entering the step S11; if yes, go to step S12;
s11, secondary alarm: according to the judgment result of the step S10, performing secondary alarm on the driver, and automatically performing operations such as deceleration and the like on the vehicle in the driving process under the condition of the secondary alarm;
and S12, normally operating the vehicle.
The invention relates to an automobile driving safety early warning method considering the emotion and driving tendency of a driver, which comprises the following steps of: the evaluation is carried out in the form of questionnaires, the questionnaires are displayed through a vehicle-mounted screen, a driver can do the questions of the questionnaires before the vehicle is started, and then the system compares scores of the questionnaires with score intervals of a database so as to obtain the driving tendency of the driver.
The invention relates to an automobile driving safety early warning method considering the emotion and driving tendency of a driver, which comprises the following steps of: the facial data collection and emotion recognition are algorithms based on a convolutional neural network, and the specific algorithms are as follows:
step 1: a data input layer which parses a picture into a multi-dimensional matrix represented by pixel values;
step 2: the convolutional layer is the core of the convolutional neural network, and acquires the characteristics of the picture through different convolutional kernels. The convolution kernel is equivalent to a filter, different filters extract different characteristics, the product sum of each pixel of the image and corresponding elements of the domain pixel and the filter matrix is calculated, and the convolution formula of the convolution layer is as follows:
wherein f (x) represents an activation function; l, W represents the length and width of the convolution kernel; omega n,m Is the weight corresponding to the position of the convolution kernel (n, m); u denotes the output of the previous layer. The activation function is to perform nonlinear operation on the output of the convolutional layer, and there are generally three activation functions, which are sigmoid, tanh and ReLU, respectively, and experiments show that: the ReLU is more quickly converged than functions such as sigmoid and tanh, and a large amount of time is saved for gradient descent training, so that the ReLU function is selected as an activation function. The mathematical expression of the ReLU function is as follows:
f(x)＝max(0,x)
and step 3: in the pooling layer, the feature dimensions of the input samples after passing through the convolutional layer are large, and if the feature values are directly used for classification, the results of large calculation amount, over-complexity and the like can be caused. Therefore, each convolutional layer is followed by a pooling layer for the purpose of dimension reduction. The invariant feature is obtained by performing function transformation on the non-overlapped part on the feature graph output by the previous layer;
and 4, step 4: the full connection layer is generally connected between the last down-sampling layer and the classifier, can sense global information, and integrates local features obtained by learning of the convolutional layer and the down-sampling layer so as to obtain global features; the mathematical expression of the full connection layer is as follows:
y＝g(Wh+b 1 )
wherein g (x) represents a classification function; w represents a connection weight; h represents a hidden output; b 1 Indicating the bias. The classification function selects a Softmax function, and the function expression of the Softmax function is as follows:
in the formula, f i The extracted features of the ith sample representing the last fully-connected layer output; p i Denotes f i A posterior probability of being correctly classified; n is the number of training samples, K is the number of classes; w j Column j representing a fully connected layer weight matrix; b j Is a bias term;
and 5: and the output layer generally adopts an RBF network, the center of each RBF is a mark of each category, the larger the network output is, the more dissimilar the representation is, and the minimum value output is the judgment result of the network.
The invention relates to an automobile driving safety early warning method considering the emotion and driving tendency of a driver, which mainly comprises the following steps:
angry emotion early warning device: when the driver is detected to be angry, the system automatically plays music for relieving the angry, so that the angry emotion of the driver is relieved, overstimulated driving behaviors of the driver due to emotions can be avoided to a certain extent, and potential safety hazards are eliminated;
a primary alarm device: when the driver has an over-excited driving behavior, and the vehicle speed exceeds a safe driving vehicle speed threshold value, the system provides a voice alarm prompt for the driver to prompt that the driver is in a dangerous driving state at present;
a secondary alarm device: and when the vehicle does not return to the safe driving speed threshold value within 30 seconds after the primary alarm is finished, the system performs secondary alarm, provides voice prompt for the driver and performs forced deceleration measures on the vehicle after 5 seconds.
The invention relates to an automobile driving safety early warning method considering the emotion and driving tendency of a driver, which comprises the following steps: a360-degree panoramic camera is mounted on a vehicle, and the transverse speed and the longitudinal speed of the vehicle are further calculated according to vehicle position information captured by the panoramic camera, wherein the calculation formula is as follows:
v 1 ＝v·cosθ
v 2 ＝v·sinθ
in the formula, v 1 Indicating the longitudinal speed, v, of the vehicle 2 Represents the lateral velocity of the vehicle, v represents the traveling velocity of the vehicle, and θ represents the angle between the traveling direction of the vehicle and the road direction.
Before the vehicle is normally started, the driving tendency of the driver can be evaluated and judged. The vehicle can be normally started after the driving tendency is judged. In the running process of the vehicle, whether dangerous driving exists in the driver can be judged through real-time driver face data acquisition, emotion recognition and real-time vehicle running information acquisition, and when the dangerous driving occurs, the driver is fed back through early warning or alarm signals, so that potential safety hazards in the running process of the vehicle are reduced.
Drawings
Fig. 1 is a flow chart of a driving safety warning method for an automobile in consideration of the emotion and driving tendency of a driver.
Fig. 2 is a flow diagram of a system for emotion recognition.
Detailed Description
The following description will explain embodiments of the present invention by referring to the detailed description.
The invention provides a flow chart of an automobile driving safety early warning method considering the emotion and driving tendency of a driver, which comprises the following steps as shown in figure 1:
s1, evaluating the driving tendency of the driver: before the vehicle is started, a questionnaire survey is carried out on a vehicle driver, and the driving tendency of the driver is judged by comparing data in a database;
s2, aggressive authentication: judging whether the driver is aggressive or not according to the data collected in the step S1 and the judgment result, and if so, entering the step S3; if no, go to step S12;
s3, acquiring driver face data and recognizing emotion: in the driving process of the vehicle, the facial data of a driver are collected in real time, and the emotion of the driver is identified according to the collected data;
s4, angry emotion authentication: judging whether the emotion of the driver is angry according to the data collected in the step S3 and the judgment result, and if yes, entering a step S5; if no, go to step S12;
s5, angry emotion early warning: according to the authentication result of the step S4, when the driver is angry, music for relieving angry emotion is automatically played to relieve the angry emotion of the driver;
s6, re-certification of anger emotion: after the music playing in step S5 is completed, recognizing the emotion of the driver again, and determining whether the angry emotion of the driver has disappeared, if it is determined to be "no", proceeding to step S7; if yes, go to step S12;
s7, collecting vehicle running information: in the running process of the vehicle, real-time data acquisition is carried out on the running information of the vehicle;
s8, vehicle driving state primary alarm judgment: judging whether the vehicle exceeds a safe driving threshold value or not according to the vehicle driving data collected in the step S7, and if yes, entering the step S9; if no, go to step S12;
s9, primary alarm: performing a primary alarm to the driver according to the judgment result of the step S8;
s10, secondary alarm judgment of the vehicle running state: judging whether the vehicle is recovered to be within the safe driving threshold value or not according to the vehicle driving data collected in the step S7, and if not, entering the step S11; if yes, go to step S12;
s11, secondary alarm: according to the judgment result of the step S10, performing secondary alarm on the driver, and automatically performing operations such as deceleration and the like on the vehicle in the driving process under the condition of the secondary alarm;
and S12, normally running the vehicle.
A system flow for emotion recognition, as shown in fig. 2, comprising the steps of:
step 1: a data input layer which parses a picture into a multi-dimensional matrix represented by pixel values;
step 2: the method comprises the following steps that (1) a convolutional layer is used as a core of a convolutional neural network, and the characteristics of a picture are obtained through different convolutional kernels; the convolution kernel is equivalent to a filter, and different filters extract different features;
and step 3: a pooling layer 1, one pooling layer is connected behind each convolution layer for the purpose of reducing dimension; the size of the output matrix of the original convolution layer is generally changed into half of the original size, so that the subsequent operation is facilitated;
and 4, step 4: performing convolution and pooling for multiple times, and performing deeper expression on the original sample;
and 5: the full connection layer is generally connected between the last downsampling layer and the classifier, can sense global information, and integrates local features obtained through learning of the convolutional layer and the downsampling layer so as to obtain global features;
and 6: softmax is used in the multi-classification process, which maps the outputs of a plurality of neurons into the (0,1) interval;
and 7: and the output layer generally adopts an RBF network, the center of each RBF is a mark of each category, the larger the network output is, the more dissimilar the representation is, and the minimum value output is the judgment result of the network.
Claims (3)
1. An automobile driving safety early warning method considering the emotion and driving tendency of a driver is characterized by comprising the following steps of:
s1, evaluating the driving tendency of the driver: before the vehicle is started, a questionnaire survey is carried out on a vehicle driver, and the driving tendency of the driver is judged by comparing data in a database;
s2, aggressive authentication: judging whether the driver is aggressive or not according to the data collected in the step S1 and the judgment result, and if so, entering the step S3; if no, go to step S12;
s3, acquiring driver face data and recognizing emotion: in the driving process of the vehicle, the facial data of a driver are collected in real time, and the emotion of the driver is identified according to the collected data;
s4, authentication of angry emotion: judging whether the emotion of the driver is angry according to the data collected in the step S3 and the judgment result, and if the emotion is judged to be angry, entering the step S5; if no, go to step S12;
s5, angry emotion early warning: according to the authentication result of the step S4, when the driver is angry, music for relieving angry emotion is automatically played to relieve the angry emotion of the driver;
s6, re-certification of anger emotion: after the music playing in the step S5 is completed, the emotion of the driver is recognized again, whether the anger emotion of the driver has disappeared is judged, and if the judgment is "no", the routine proceeds to a step S7; if yes, go to step S12;
s7, collecting vehicle running information: in the running process of the vehicle, real-time data acquisition is carried out on the running information of the vehicle;
s8, vehicle driving state primary alarm judgment: judging whether the vehicle exceeds a safe driving threshold value or not according to the vehicle driving data collected in the step S7, and if yes, entering the step S9; if no, go to step S12;
s9, primary alarm: performing primary alarm on the driver according to the judgment result of the step S8;
s10, secondary alarm judgment of the vehicle running state: judging whether the vehicle is recovered to be within the safe driving threshold value or not according to the vehicle driving data collected in the step S7, and if not, entering the step S11; if yes, go to step S12;
s11, secondary alarm: according to the judgment result of the step S10, performing secondary alarm on the driver, and automatically performing deceleration operation on the vehicle in the driving process under the condition of secondary alarm;
s12, the vehicle runs normally;
the driver face data collection and emotion recognition in step S3 is an algorithm based on a convolutional neural network, and the specific algorithm is as follows:
step 1: the data input layer is used for analyzing a facial picture of the driver, which is acquired by the camera in the vehicle, into a multi-dimensional matrix represented by pixel values;
step 2: and (2) the convolutional layer acquires the characteristics of the input picture data in the step (1) through different convolutional kernels, and calculates the product sum of the neighborhood pixels of each pixel point of the picture and the corresponding elements of the filter matrix, wherein the convolutional formula of the convolutional layer is as follows:
wherein f (x) represents an activation function; l, W represents the length and width of the convolution kernel; omega n,m Is the weight corresponding to the position of the convolution kernel (n, m); u represents the output of the previous layer; x and y are respectively input pixel characteristics; b is a constant; the ReLU function is taken as an activation function, and the mathematical expression of the ReLU function is as follows:
f(x)＝max(0,x)；
and step 3: the pooling layers are used for obtaining larger characteristic dimension after the input image data passes through the convolution layers, and the dimension reduction is carried out after each convolution layer by one pooling layer;
and 4, step 4: the full articulamentum is connected between last one deck downsampling layer and classifier, will integrate through the local feature that convolutional layer and downsampling layer study obtained, obtains global feature, and the mathematical expression of full articulamentum is:
y＝g(Wh+b 1 )；
wherein g (x) represents a classification function; w represents a connection weight; h represents a hidden output; b is a mixture of 1 Expressing the offset, the classification function selects a Softmax function, and the function expression of the Softmax function is as follows:
in the formula, e represents a natural base number; f. of i The extracted features of the ith sample representing the last fully-connected layer output; p i Denotes f i A posterior probability of being correctly classified; n is the number of training samples, K is the number of classes; w j T A transpose representing a jth column of the fully-connected layer weight matrix;
an offset corresponding to the input value of the sample of the ith; b j Is a bias term;
and 5: and the output layer adopts RBF networks, the center of each RBF network is a mark of each category, the larger the output of the RBF network is, the more dissimilar the output is, and the minimum output value is the judgment result of the RBF network.
2. The automobile driving safety warning method considering the emotion and driving tendency of a driver as set forth in claim 1, wherein: the driving tendency evaluation of the driver is carried out in the form of questionnaires, the questionnaires are displayed through a vehicle-mounted screen, and after the driver finishes the driving, the system can compare scores of the questionnaires with a database so as to obtain the driving tendency of the driver.
3. The automobile driving safety warning method considering the emotion and driving tendency of a driver as set forth in claim 1, wherein: the vehicle running information acquisition depends on a 360-degree panoramic camera arranged on a vehicle, and the transverse speed and the longitudinal speed of the vehicle are obtained through vehicle position information captured by the panoramic camera, and the calculation formula is as follows:
v 1 ＝v·cosθ；
v 2 ＝v·sinθ；
in the formula, v 1 Indicating the longitudinal speed, v, of the vehicle 2 Showing the cross of the vehicleThe velocity, v, and θ represent the traveling velocity of the vehicle and the angle between the traveling direction of the vehicle and the road direction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910521885.2A CN110171361B (en) | 2019-06-17 | 2019-06-17 | Automobile safety early warning method based on emotion and driving tendency of driver |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910521885.2A CN110171361B (en) | 2019-06-17 | 2019-06-17 | Automobile safety early warning method based on emotion and driving tendency of driver |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110171361A CN110171361A (en) | 2019-08-27 |
| CN110171361B true CN110171361B (en) | 2022-09-23 |
Family
ID=67698371
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910521885.2A Active CN110171361B (en) | 2019-06-17 | 2019-06-17 | Automobile safety early warning method based on emotion and driving tendency of driver |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110171361B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110516658A (en) * | 2019-09-06 | 2019-11-29 | 山东理工大学 | A kind of recognizer design of driver's mood based on face-image and vehicle operating information |
| CN110525446A (en) * | 2019-09-06 | 2019-12-03 | 山东理工大学 | A kind of automobile pressure lane-change decision safe early warning method considering mood |
| CN110742602B (en) * | 2019-10-15 | 2021-02-19 | 武汉理工大学 | Method for recognizing aggressive driving state based on electroencephalogram and vehicle driving data |
| CN110758325A (en) * | 2019-10-23 | 2020-02-07 | 上海能塔智能科技有限公司 | Face authentication method and device for vehicle, storage medium, terminal and automobile |
| CN111202533A (en) * | 2019-12-25 | 2020-05-29 | Oppo广东移动通信有限公司 | Information processing method and related product |
| CN111991012B (en) * | 2020-09-04 | 2022-12-06 | 北京中科心研科技有限公司 | Method and device for monitoring driving road rage state |
| CN112232254B (en) * | 2020-10-26 | 2021-04-30 | 清华大学 | Pedestrian risk assessment method considering pedestrian acceleration rate |
| CN113347243A (en) * | 2021-05-31 | 2021-09-03 | 重庆工程职业技术学院 | Driving information recording system and method based on block chain |
| CN114360241B (en) * | 2021-12-10 | 2023-05-16 | 斑马网络技术有限公司 | Vehicle interaction method, vehicle interaction device and storage medium |
| CN115713754B (en) * | 2022-12-16 | 2023-10-03 | 吉林大学 | Staged hierarchical intervention method and system based on driver fear emotion recognition |
| CN116238544B (en) * | 2023-05-12 | 2023-07-14 | 禾多科技（北京）有限公司 | Running control method and system for automatic driving vehicle |
| CN117022294A (en) * | 2023-08-17 | 2023-11-10 | 山东理工大学 | Dangerous driving behavior identification and early warning method and system |
| CN117584985B (en) * | 2024-01-18 | 2024-03-19 | 吉林大学 | Driving anger index detection and vehicle control method and system based on driving state |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101561972A (en) * | 2008-04-17 | 2009-10-21 | 北京宣爱智能模拟技术有限公司 | Method and system for interactive automobile driving case teaching |
| CN104228840A (en) * | 2013-06-07 | 2014-12-24 | 现代自动车株式会社 | Apparatus and method for determining short-term driving tendency |
| CN104463191A (en) * | 2014-10-30 | 2015-03-25 | 华南理工大学 | Robot visual processing method based on attention mechanism |
| CN105011952A (en) * | 2015-08-07 | 2015-11-04 | 北京环度智慧智能技术研究所有限公司 | Driver limiting speed evaluation system and method |
| CN106127126A (en) * | 2016-06-17 | 2016-11-16 | 杭州好好开车科技有限公司 | The recognition methods of radical driving behaviors based on three anxious data |
| CN107662611A (en) * | 2017-11-06 | 2018-02-06 | 吉林大学 | A kind of automatic driving mode switching system based on driver's Emotion identification |
| KR20180072136A (en) * | 2016-12-21 | 2018-06-29 | 주식회사 이앤지테크 | Communication system capable of displaying emotion information ,and Drive Method of the Same |
| CN108268887A (en) * | 2017-12-15 | 2018-07-10 | 西安电子科技大学 | Driver's awareness of safety appraisal procedure based on virtual driving and EEG detections |
| CN109367541A (en) * | 2018-10-15 | 2019-02-22 | 吉林大学 | A kind of intelligent vehicle class people's lane change decision-making technique based on driver behavior pattern |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9493130B2 (en) * | 2011-04-22 | 2016-11-15 | Angel A. Penilla | Methods and systems for communicating content to connected vehicle users based detected tone/mood in voice input |
-
2019
- 2019-06-17 CN CN201910521885.2A patent/CN110171361B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101561972A (en) * | 2008-04-17 | 2009-10-21 | 北京宣爱智能模拟技术有限公司 | Method and system for interactive automobile driving case teaching |
| CN104228840A (en) * | 2013-06-07 | 2014-12-24 | 现代自动车株式会社 | Apparatus and method for determining short-term driving tendency |
| CN104463191A (en) * | 2014-10-30 | 2015-03-25 | 华南理工大学 | Robot visual processing method based on attention mechanism |
| CN105011952A (en) * | 2015-08-07 | 2015-11-04 | 北京环度智慧智能技术研究所有限公司 | Driver limiting speed evaluation system and method |
| CN106127126A (en) * | 2016-06-17 | 2016-11-16 | 杭州好好开车科技有限公司 | The recognition methods of radical driving behaviors based on three anxious data |
| KR20180072136A (en) * | 2016-12-21 | 2018-06-29 | 주식회사 이앤지테크 | Communication system capable of displaying emotion information ,and Drive Method of the Same |
| CN107662611A (en) * | 2017-11-06 | 2018-02-06 | 吉林大学 | A kind of automatic driving mode switching system based on driver's Emotion identification |
| CN108268887A (en) * | 2017-12-15 | 2018-07-10 | 西安电子科技大学 | Driver's awareness of safety appraisal procedure based on virtual driving and EEG detections |
| CN109367541A (en) * | 2018-10-15 | 2019-02-22 | 吉林大学 | A kind of intelligent vehicle class people's lane change decision-making technique based on driver behavior pattern |
Non-Patent Citations (1)
| Title |
|---|
| 多车道复杂环境下驾驶倾向性状态辨识;张敬磊;《交通信息与安全》;20140531;130-137 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110171361A (en) | 2019-08-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110171361B (en) | Automobile safety early warning method based on emotion and driving tendency of driver | |
| US20230154207A1 (en) | Driver fatigue detection method and system based on combining a pseudo-3d convolutional neural network and an attention mechanism | |
| Moukafih et al. | Aggressive driving detection using deep learning-based time series classification | |
| Eren et al. | Estimating driving behavior by a smartphone | |
| CN110949398B (en) | Method for detecting abnormal driving behavior of first-vehicle drivers in vehicle formation driving | |
| DE102017106535B4 (en) | Method for determining a surface condition of a movement path | |
| Sathyanarayana et al. | Information fusion for robust ‘context and driver aware’active vehicle safety systems | |
| CN110866427A (en) | Vehicle behavior detection method and device | |
| KR101845769B1 (en) | Car rear detection system using convolution neural network, and method thereof | |
| CN110895662A (en) | Vehicle overload alarm method and device, electronic equipment and storage medium | |
| CN112677977B (en) | Driving state identification method and device, electronic equipment and steering lamp control method | |
| CN112793576B (en) | Lane change decision method and system based on rule and machine learning fusion | |
| CN113486822A (en) | Surrounding vehicle track prediction method and system based on driving intention | |
| CN111626170B (en) | Image recognition method for railway side slope falling stone intrusion detection | |
| CN111815959A (en) | Vehicle violation detection method and device and computer readable storage medium | |
| Won et al. | Implementation of road traffic signs detection based on saliency map model | |
| CN111563468A (en) | Driver abnormal behavior detection method based on attention of neural network | |
| KR101050687B1 (en) | Pedestrian recognition device and method using posterior probability and pedestrian protection device using it | |
| Qiu et al. | Use of triplet-loss function to improve driving anomaly detection using conditional generative adversarial network | |
| Wowo et al. | Towards sub-maneuver selection for automated driver identification | |
| CN114120250B (en) | Video-based motor vehicle illegal manned detection method | |
| US20230237584A1 (en) | Systems and methods for evaluating vehicle insurance claims | |
| CN116129405A (en) | Method for identifying anger emotion of driver based on multi-mode hybrid fusion | |
| CN111985386B (en) | Method for identifying pedestrian illegal-passing behavior based on planned behavior theory | |
| Utaminingrum et al. | Feature selection of gray-level Cooccurrence matrix using genetic algorithm with Extreme learning machine classification for early detection of Pole roads |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |