CN115107786A - Driving behavior correction system and method for intelligent automobile - Google Patents

Abstract

The invention provides a driving behavior correction system and method for an intelligent automobile, wherein the method comprises the steps of obtaining historical driving event data and generating a driving habit model according to the historical driving event data; acquiring current driver data, current running vehicle data, current running road data and current time data; obtaining current driving habit models of other drivers from the driving habit models; judging whether a preset standard driving behavior model is safe or not according to the current driving habit model; when the driver is determined to be unsafe, modifying the standard driving behavior model to obtain a current standard driving behavior model; judging whether the driving behavior of the current driver is safe or not according to the current standard driving behavior model, the current driver data and the current running vehicle data; and when the driver is unsafe, sending out driving behavior correction alarm information. The driving behavior of the driver can be corrected through the scheme, so that the adverse effect of other vehicles on the current vehicle is effectively avoided.

Description

Driving behavior correction system and method for intelligent automobile

Technical Field

The invention relates to the technical field of intelligent automobile control, in particular to a driving behavior correction system and method for an intelligent automobile.

Background

With the rapid development of economy and the improvement of living standard of people, various types of motor vehicles are put into use more and more, the pressure of road traffic is higher and higher, and the frequency of traffic accidents is higher and higher. When traffic accidents happen frequently, the daily life of people is seriously lost. The bad driving behavior is one of the main causes of traffic accidents, and in order to prevent the traffic accidents, it is more important to make the drivers develop good driving habits, in addition to strengthening the safety education for the drivers. However, the effect obtained by the current safety education is not ideal enough, and the timeliness is not good and the intelligence is not enough after the traffic accident or the illegal driving of the driver frequently occurs.

Therefore, a solution for correcting the driving behavior of the driver in real time in a vehicle is needed.

Disclosure of Invention

The invention provides a driving behavior correction system and method for an intelligent automobile based on the problems, and through implementation of the scheme of the invention, the driving habits of other vehicles on a road where the automobile runs can be predicted in advance, and a standard driving behavior model of a driver of the current automobile is modified, so that adverse effects of the other vehicles on the current automobile are effectively avoided.

In view of the above, an aspect of the present invention provides a driving behavior correction system for an intelligent vehicle, including: the driving habit model building method comprises an acquisition module, a driving habit model building module and a control processing module;

the acquisition module is used for acquiring historical driving event data;

the driving habit model building module is used for generating a driving habit model according to time dimension or road dimension or vehicle type dimension or driver dimension according to the historical driving event data;

the acquisition module is also used for acquiring current driver data, current running vehicle data, current running road data and current time data;

the control processing module is used for:

obtaining current driving habit models of other drivers from the driving habit models according to the current driving road data and/or the current time data;

judging whether a preset standard driving behavior model is safe or not according to the current driving habit model;

when the standard driving behavior model is determined to be unsafe, modifying the standard driving behavior model according to the current driving habit model to obtain a current standard driving behavior model;

judging whether the driving behavior of the current driver is safe or not according to the current standard driving behavior model, the current driver data and the current running vehicle data;

when the driving behavior of the current driver is unsafe, sending driving behavior correction alarm information;

wherein the historical driving event data includes at least driver data, driving vehicle data, driving region data, driving time data, and driving road data.

Optionally, the driver data comprises driver eye rotation data, eyelid state data, and head movement information, and driver stimulus-response time data, driver physiological data, and driver operational behavior data; wherein the driver operation behavior data includes at least data such as inter-vehicle distance holding data, accelerator pedal stepping data, brake pedal stepping data, turn signal use data, and steering wheel rotation data;

the running vehicle data comprises vehicle position data, vehicle speed data, oil consumption/power consumption data, steering data and vehicle-mounted machine data;

the driving road data comprises road address data, lane number data, lane driving identification data, road surface evenness data, camber data and gradient data.

Optionally, the obtaining module is further configured to obtain first image data of the steering wheel in a return state;

the control processing module is further configured to perform character recognition on the first image data, and determine a central axis of the steering wheel according to a character group in a horizontal direction;

the acquisition module is also used for acquiring the current image data of the steering wheel of the vehicle in a driving state;

the control processing module is further configured to obtain a deflection angle of the central axis according to the current image data and the first image data, so as to obtain a rotation angle of the steering wheel;

the acquisition module is further used for acquiring the rotation time of the steering wheel;

and the control processing module is also used for calculating the rotation speed according to the rotation angle and the rotation time.

Optionally, the acquiring module is further configured to acquire road surface image data of a driving road;

the control processing module is also used for identifying a water accumulation area, a damaged area, an obstacle and a sharp object from the image data;

the acquisition module is further used for respectively acquiring three-dimensional data of the ponding area, the damaged area, the barrier and the sharp object;

the control processing module is further used for respectively calculating ponding area data, damaged area data, barrier data and sharp object data according to the three-dimensional data; the water accumulation area data at least comprise a water accumulation position and a water accumulation depth, the damaged area data at least comprise a damaged area position and a damaged degree, the obstacle data at least comprise an obstacle position and an obstacle volume, and the sharp object data at least comprise a distribution position and a sharp degree of a sharp object;

and the control processing module is also used for obtaining the road surface evenness data according to the water accumulation area data, the damaged area data, the obstacle data and the sharp object data.

Optionally, the obtaining module is further configured to collect first face data and first head posture data of the current driver;

the control processing module is further configured to:

determining an eye area according to the first face data to obtain a first eye picture;

extracting first eye movement data, and processing the first eye movement data to obtain first eye movement characteristic data;

and inputting a preset head recognition model according to the first head posture data and the first eye movement characteristic data so as to judge whether unsafe driving behaviors exist in the current driver.

Another aspect of the present invention provides a driving behavior correction method for an intelligent vehicle, the driving behavior correction method including:

acquiring historical driving event data;

generating a driving habit model according to time dimension, road dimension, vehicle type dimension or driver dimension according to the historical driving event data;

acquiring current driver data, current running vehicle data, current running road data and current time data;

obtaining current driving habit models of other drivers from the driving habit models according to the current driving road data and/or the current time data;

judging whether a preset standard driving behavior model is safe or not according to the current driving habit model;

when the standard driving behavior model is determined to be unsafe, modifying the standard driving behavior model according to the current driving habit model to obtain a current standard driving behavior model;

judging whether the driving behavior of the current driver is safe or not according to the current standard driving behavior model, the current driver data and the current running vehicle data;

when the driving behavior of the current driver is unsafe, sending driving behavior correction alarm information;

wherein the historical driving event data includes at least driver data, driving vehicle data, driving region data, driving time data, and driving road data.

Optionally, the driver data comprises driver eye rotation data, eyelid state data and head motion information, and stimulation-response time data of the driver, physiological data of the driver, and driver operational behavior data; wherein the driver operation behavior data includes at least data such as inter-vehicle distance holding data, accelerator pedal stepping data, brake pedal stepping data, turn signal use data, and steering wheel rotation data;

the running vehicle data comprises vehicle position data, vehicle speed data, oil consumption/power consumption data, steering data and vehicle-mounted machine data;

the driving road data comprises road address data, lane number data, lane driving identification data, road surface evenness data, camber data and gradient data.

Optionally, the method for acquiring steering wheel rotation data includes:

acquiring first image data of a steering wheel in a return state;

performing character recognition on the first image data, and determining a central axis of the steering wheel according to a character group in the horizontal direction;

acquiring current image data of a steering wheel of a vehicle in a driving state;

obtaining a deflection angle of the central axis according to the current image data and the first image data to obtain a rotation angle of the steering wheel;

acquiring the rotation time of the steering wheel;

and calculating to obtain the rotating speed according to the rotating angle and the rotating time.

Optionally, the method for acquiring the road flatness data includes:

collecting road surface image data of a driving road, and identifying a water accumulation area, a damaged area, an obstacle and a sharp object from the image data;

respectively collecting three-dimensional data of the water accumulation area, the damaged area, the barrier and the sharp object;

respectively calculating ponding area data, damaged area data, barrier data and sharp object data according to the three-dimensional data; the water accumulation area data at least comprise a water accumulation position and a water accumulation depth, the damaged area data at least comprise a damaged area position and a damaged degree, the obstacle data at least comprise an obstacle position and an obstacle volume, and the sharp object data at least comprise a distribution position and a sharp degree of a sharp object;

and obtaining the road surface flatness data according to the water accumulation area data, the damaged area data, the barrier data and the sharp object data.

Optionally, the driving behavior correction method further includes:

collecting first face data and first head posture data of the current driver;

determining an eye area according to the first face data to obtain a first eye picture;

extracting first eye movement data, and processing the first eye movement data to obtain first eye movement characteristic data;

and inputting a preset head recognition model according to the first head posture data and the first eye movement characteristic data so as to judge whether unsafe driving behaviors exist in the current driver.

By adopting the technical scheme, the driving behavior correction system comprises an acquisition module, a driving habit model construction module and a control processing module; the acquisition module is used for acquiring historical driving event data; the driving habit model building module is used for generating a driving habit model according to time dimension or road dimension or vehicle type dimension or driver dimension according to the historical driving event data; the acquisition module is also used for acquiring current driver data, current running vehicle data, current running road data and current time data; the control processing module is used for: obtaining current driving habit models of other drivers from the driving habit models according to the current driving road data and/or the current time data; judging whether a preset standard driving behavior model is safe or not according to the current driving habit model; when the standard driving behavior model is determined to be unsafe, modifying the standard driving behavior model according to the current driving habit model to obtain a current standard driving behavior model; judging whether the driving behavior of the current driver is safe or not according to the current standard driving behavior model, the current driver data and the current running vehicle data; and when the driving behavior of the current driver is unsafe, sending driving behavior correction alarm information. By implementing the scheme, the driving habits of other vehicles on the road where the vehicle runs can be predicted in advance, and the standard driving behavior model of the driver of the current vehicle is modified, so that the adverse effect of the other vehicles on the current vehicle is effectively avoided.

Drawings

FIG. 1 is a schematic block diagram of a driving behavior correction system for an intelligent vehicle provided by one embodiment of the present invention;

fig. 2 is a flowchart of a driving behavior correction method for an intelligent vehicle according to another embodiment of the present invention.

Detailed Description

In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced otherwise than as specifically described herein, and thus the scope of the present invention is not limited by the specific embodiments disclosed below.

The terms "first," "second," and the like in the description and claims of the present application and in the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.

A driving behavior correction system and method for an intelligent vehicle according to some embodiments of the present invention will be described with reference to fig. 1 to 2.

As shown in fig. 1, an embodiment of the present invention provides a driving behavior correction system for an intelligent vehicle, including: the driving habit model building method comprises an acquisition module, a driving habit model building module and a control processing module;

the acquisition module is used for acquiring historical driving event data;

the driving habit model building module is used for generating a driving habit model according to time dimension, road dimension, vehicle model dimension or driver dimension according to the historical driving event data;

the acquisition module is also used for acquiring current driver data, current running vehicle data, current running road data and current time data;

the control processing module is used for:

obtaining current driving habit models of other drivers from the driving habit models according to the current driving road data and/or the current time data;

judging whether a preset standard driving behavior model is safe or not according to the current driving habit model;

when the standard driving behavior model is determined to be unsafe, modifying the standard driving behavior model according to the current driving habit model to obtain a current standard driving behavior model;

judging whether the driving behavior of the current driver is safe or not according to the current standard driving behavior model, the current driver data and the current running vehicle data;

when the driving behavior of the current driver is unsafe, sending driving behavior correction alarm information;

wherein the historical driving event data includes at least driver data, driving vehicle data, driving region data, driving time data, and driving road data.

It will be appreciated that a standard driving behavior model for the driver may be established based on road traffic related regulatory requirements and road traffic safety test data.

In the actual driving process of the vehicle, because the road traffic condition changes instantly and constantly under the influence of factors such as sudden change of weather, change of road surface condition, unpredictable driving conditions of other drivers and the like, the driving behavior of the drivers needs to be standardized according to a standard which is stricter than a standard driving behavior model sometimes, and the occurrence of traffic accidents can be effectively avoided.

In an embodiment of the present invention, the historical driving event data includes at least driver data, traveling vehicle data, traveling region data, traveling time data, traveling road data; the driving habit model building module is used for generating a driving habit model according to time dimension or road dimension or vehicle type dimension or driver dimension by utilizing a neural network trained in advance according to the historical driving event data, and it can be understood that a plurality of driving habit models can be generated according to the time dimension, the road dimension, the vehicle type dimension and the driver dimension respectively. It should be noted that the driving habit model is constructed based on historical driving event data, and may represent the driving habits of other vehicles passing through the road, such as "on XX road, 9: 00 to 19: 00, 30 to 40 large trucks pass through each hour, the speed of about 60 percent of the large trucks exceeds the speed limit by more than 10 percent, the situation that the auxiliary road vehicles are not lighted and suddenly blocked to the main road traffic flow at the main entrance road of the YY road and the situation that the auxiliary road vehicles are not lighted and the lane change situation occurs at 80 percent of the probability at the TT time interval, ZZ road and large traffic flow, and the like.

For the driver of the current vehicle implemented by the driving behavior correction system provided in the embodiment of the present invention, first, the current driving habit models of other drivers may be obtained from the driving habit models according to the current driving road data and/or the current time data, so as to determine the style of the vehicle driven by other drivers on the current traffic road. And then, according to the current driving habit model, judging whether a preset standard driving behavior model is safe, namely judging whether the risk caused by driving of other vehicles with the current driving habit model can be prevented/actively avoided according to the requirement on the driving behavior determined by the standard driving behavior model, for example, whether the safe distance can be kept to avoid sudden braking of the front vehicle, whether the collision caused by sudden lane change of other vehicles can be avoided and the like under the condition of driving with the standard driving behavior model. And when the standard driving behavior model is determined to be unsafe, modifying the standard driving behavior model according to the current driving habit model to obtain the current standard driving behavior model, such as reducing the highest speed limit of the standard driving behavior model, increasing the standard requirement of the distance between the standard driving behavior model and a front vehicle, and the like. And finally, judging whether the driving behavior of the current driver is safe or not according to the current standard driving behavior model, the current driver data and the current running vehicle data, and sending out driving behavior correction alarm information when the driving behavior of the current driver is unsafe so as to urge the driver to correct the driving behavior of the driver according to the requirement.

By adopting the technical scheme of the embodiment, the driving behavior correction system comprises an acquisition module, a driving habit model construction module and a control processing module; the acquisition module is used for acquiring historical driving event data; the driving habit model building module is used for generating a driving habit model according to time dimension or road dimension or vehicle type dimension or driver dimension according to the historical driving event data; the acquisition module is also used for acquiring current driver data, current running vehicle data, current running road data and current time data; the control processing module is used for: obtaining current driving habit models of other drivers from the driving habit models according to the current driving road data and/or the current time data; judging whether a preset standard driving behavior model is safe or not according to the current driving habit model; when the standard driving behavior model is determined to be unsafe, modifying the standard driving behavior model according to the current driving habit model to obtain a current standard driving behavior model; judging whether the driving behavior of the current driver is safe or not according to the current standard driving behavior model, the current driver data and the current running vehicle data; and when the driving behavior of the current driver is unsafe, sending driving behavior correction alarm information. Through the implementation of the scheme, the driving habits of other vehicles on the road where the vehicle runs can be predicted in advance, and the standard driving behavior model of the driver of the current vehicle is modified, so that the adverse effect of the other vehicles on the current vehicle is effectively avoided.

It should be understood that the block diagram of the driving behavior correction system for an intelligent vehicle shown in fig. 1 is only schematic, and the number of the modules shown is not intended to limit the scope of the present invention.

In some possible embodiments of the invention, the driver data comprises driver eye rotation data, eyelid state data, and head movement information, and driver stimulus-response time data, driver physiological data, and driver operational behavior data; wherein the driver operation behavior data includes at least data such as inter-vehicle distance holding data, accelerator pedal stepping data, brake pedal stepping data, turn signal use data, and steering wheel rotation data;

the running vehicle data comprises vehicle position data, vehicle speed data, oil consumption/electricity consumption data, steering data and vehicle data (such as navigation and music use states);

the driving road data comprises road address data, lane number data, lane driving identification data, road surface evenness data, camber data and gradient data.

It is understood that, in the embodiment of the present invention, the eyeball rotation data, the eyelid state data, the head movement information, and the like of the driver may be obtained through image acquisition and recognition technology, and the stimulation-response time data of the driver, the physiological data of the driver, and the like may be calculated by collecting relevant data (such as heartbeat, body temperature, nerve response data, blood glucose content, blood oxygen content, respiratory frequency, and the like) through a sensor and then using the collected data, and the data, such as the eyeball rotation data, the eyelid state data, and the head movement information of the driver, the stimulation-response time data of the driver, the physiological data of the driver, may accurately analyze the mental state of the driver and determine whether there is unsafe driving movement of the driver, and the like.

The data of the driver operation behaviors at least comprise inter-vehicle distance keeping data, accelerator pedal stepping data, brake pedal stepping data, steering lamp use data and steering wheel rotation data, the data can be obtained by acquiring original data through an in-vehicle camera, a pressure sensor and the like and analyzing and processing the original data, the data is the most direct embodiment of the driver driving behaviors, and accurate data support can be provided for determining whether the driver driving behaviors are safe or not.

The road condition is one of the factors which have great influence on the safe driving of the vehicle, and the driving road data can be collected, processed and analyzed through a camera, a three-dimensional measuring device, a positioning device and other collection equipment and a control processing module. The driving road data at least comprises road address data, lane number data, lane driving identification data, road surface evenness data, camber data, gradient data and the like. By collecting the data of the driving road, a more accurate driving habit model can be determined according to the special road conditions in a random strain mode.

In some possible embodiments of the present invention, the obtaining module is further configured to obtain first image data of the steering wheel in a return state;

the control processing module is further configured to perform character recognition on the first image data, and determine a central axis of the steering wheel according to a character group in a horizontal direction;

the acquisition module is also used for acquiring the current image data of the steering wheel of the vehicle in a driving state;

the control processing module is further configured to obtain a deflection angle of the central axis according to the current image data and the first image data, so as to obtain a rotation angle of the steering wheel;

the acquisition module is further used for acquiring the rotation time of the steering wheel;

and the control processing module is also used for calculating the rotation speed according to the rotation angle and the rotation time.

It is understood that the steering wheel is a core control component of the vehicle driving process, and in the embodiment of the invention, whether the control of the steering wheel by the driver is safe can be judged by collecting and analyzing the moving image data of the steering wheel. Specifically, first image data of the steering wheel in a return state is acquired, character recognition is performed on the first image data, a horizontal line is determined according to a character group (such as vehicle trademark characters or figures, identification characters of control keys and the like) in the horizontal direction, and then a straight line perpendicular to the horizontal line and equally dividing the character group (or the whole steering wheel), namely a central axis of the steering wheel, is determined according to symmetry of the character group (or the whole steering wheel). In the running process of the vehicle, acquiring current image data of a steering wheel of the vehicle in a running state in real time; then obtaining a deflection angle of the central axis according to the current image data and the first image data (for example, a coordinate system is established by taking the rotation center of the steering wheel as an origin, the central axis as a Y axis and a vertical line of the central axis as an X axis, and the deflection angle can be obtained by measuring the length of an intersecting line segment and combining coordinate calculation), namely obtaining the rotation angle of the steering wheel; meanwhile, the rotation time that the steering wheel rotates can be obtained (for example, a special timer is controlled to time), and finally, the rotation speed is calculated according to the rotation angle and the rotation time. The rotation angle and the rotation speed of the steering wheel can reflect whether the control of the steering wheel by the driver is safe or not.

It will be appreciated that for more than one revolution, the number of revolutions may be recorded by the camera, and the rotation angle may be obtained by adding 360 degrees to the yaw angle.

In some possible embodiments of the present invention, the obtaining module is further configured to collect road surface image data of a driving road;

the control processing module is also used for identifying a water accumulation area, a damaged area, an obstacle and a sharp object from the image data;

the acquisition module is further used for respectively acquiring three-dimensional data of the water accumulation area, the damaged area, the barrier and the sharp object;

the control processing module is also used for respectively calculating ponding area data, damaged area data, barrier data and sharp object data according to the three-dimensional data; the water accumulation area data at least comprise a water accumulation position and a water accumulation depth, the damaged area data at least comprise a damaged area position and a damaged degree, the obstacle data at least comprise an obstacle position and an obstacle volume, and the sharp object data at least comprise a distribution position and a sharp degree of a sharp object;

and the control processing module is also used for obtaining the road surface evenness data according to the water accumulation area data, the damaged area data, the obstacle data and the sharp object data.

It can be understood that, in order to obtain more detailed road information to establish a more accurate driving habit model, in an embodiment of the present invention, the road surface image data of the driving road may be collected, the water accumulation region, the damaged region, the obstacle and the sharp object may be identified from the image data according to pre-stored model data of the water accumulation region, the damaged region, the obstacle and the sharp object, the three-dimensional data of the water accumulation region, the damaged region, the obstacle and the sharp object may be further collected respectively (for example, three-dimensional data collected by a laser scanning device, an ultrasonic scanning device, a multi-view camera device, a structured light image collecting device, etc.), at least the water accumulation position and the water accumulation depth of the water accumulation region, the damaged region position and the damaged degree, the obstacle position and the obstacle volume may be calculated according to a preset measurement algorithm or a measurement model, the distribution position and the sharpness degree of the sharp objects and the like; and obtaining the road surface flatness data according to the water accumulation area data, the damaged area data, the barrier data and the sharp object data.

In some possible embodiments of the present invention, the obtaining module is further configured to collect first face data and first head posture data of the current driver;

the control processing module is further configured to:

determining an eye area according to the first face data to obtain a first eye picture;

extracting first eye movement data, and processing the first eye movement data to obtain first eye movement characteristic data;

and inputting a preset head recognition model according to the first head posture data and the first eye movement characteristic data so as to judge whether unsafe driving behaviors exist in the current driver or not.

It can be understood that, in the driving process, a driver should watch the road information at the maximum visual angle, and if the driver has a sudden visual line, is not focused, has an incorrect head posture, and the like, accidents may occur, in the embodiment of the present invention, by collecting the first face data and the first head posture data of the current driver, the first face data is subjected to eye recognition, a eye region is determined, a first eye picture is obtained, then the first eye movement data is extracted, and the first eye movement data is processed, so that first eye movement characteristic data is obtained; and finally, inputting a preset head recognition model according to the first head posture data and the first eye movement characteristic data so as to judge whether the current driver has unsafe driving behaviors. By the scheme of the embodiment, whether unsafe driving behaviors exist in the current driver can be accurately identified through the states of human eyes and the head.

Referring to fig. 2, another embodiment of the present invention provides a driving behavior correction method for an intelligent vehicle, where the driving behavior correction method includes:

acquiring historical driving event data;

generating a driving habit model according to time dimension, road dimension, vehicle type dimension or driver dimension according to the historical driving event data;

acquiring current driver data, current running vehicle data, current running road data and current time data;

obtaining current driving habit models of other drivers from the driving habit models according to the current driving road data and/or the current time data;

judging whether a preset standard driving behavior model is safe or not according to the current driving habit model;

when the standard driving behavior model is determined to be unsafe, modifying the standard driving behavior model according to the current driving habit model to obtain a current standard driving behavior model;

judging whether the driving behavior of the current driver is safe or not according to the current standard driving behavior model, the current driver data and the current running vehicle data;

when the driving behavior of the current driver is unsafe, sending driving behavior correction alarm information;

wherein the historical driving event data includes at least driver data, driving vehicle data, driving region data, driving time data, and driving road data.

It will be appreciated that a standard driving behavior model for the driver may be established based on road traffic related regulatory requirements and road traffic safety test data.

In the actual driving process of the vehicle, because the road traffic condition changes instantly and constantly under the influence of factors such as sudden change of weather, change of road surface condition, unpredictable driving conditions of other drivers and the like, the driving behavior of the drivers needs to be standardized according to a standard which is stricter than a standard driving behavior model sometimes, and the occurrence of traffic accidents can be effectively avoided.

In an embodiment of the present invention, the historical driving event data includes at least driver data, traveling vehicle data, traveling region data, traveling time data, traveling road data; the driving habit model building module is used for generating a driving habit model according to time dimension or road dimension or vehicle type dimension or driver dimension by utilizing a neural network trained in advance according to the historical driving event data, and it can be understood that a plurality of driving habit models can be generated according to the time dimension, the road dimension, the vehicle type dimension and the driver dimension respectively. It should be noted that the driving habit model is constructed based on historical driving event data, and may represent the driving habits of other vehicles passing through the road, such as "on XX road, 9: 00 to 19: 00, 30 to 40 large trucks pass through each hour, the speed of about 60 percent of the large trucks exceeds the speed limit by more than 10 percent, the situation that the auxiliary road vehicles are not lighted and suddenly blocked to the main road traffic flow at the main entrance road of the YY road and the situation that the auxiliary road vehicles are not lighted and the lane change situation occurs at 80 percent of the probability at the TT time interval, ZZ road and large traffic flow, and the like.

For the driver of the current vehicle implemented by the driving behavior correction system provided in the embodiment of the present invention, first, the current driving habit models of other drivers may be obtained from the driving habit models according to the current driving road data and/or the current time data, so as to determine the style of the vehicle driven by other drivers on the current traffic road. And then, according to the current driving habit model, judging whether a preset standard driving behavior model is safe, namely judging whether the risk caused by driving of other vehicles with the current driving habit model can be prevented/actively avoided according to the requirement on the driving behavior determined by the standard driving behavior model, for example, whether the safe distance can be kept to avoid sudden braking of the front vehicle, whether the collision caused by sudden lane change of other vehicles can be avoided and the like under the condition of driving with the standard driving behavior model. And when the standard driving behavior model is determined to be unsafe, modifying the standard driving behavior model according to the current driving habit model to obtain the current standard driving behavior model, such as reducing the highest speed limit of the standard driving behavior model, increasing the standard requirement of the distance between the standard driving behavior model and a front vehicle, and the like. And finally, judging whether the driving behavior of the current driver is safe or not according to the current standard driving behavior model, the current driver data and the current running vehicle data, and sending out driving behavior correction alarm information when the driving behavior of the current driver is unsafe so as to urge the driver to correct the driving behavior of the driver according to the requirement.

By adopting the technical scheme of the embodiment, the driving habit model is generated according to the historical driving event data by acquiring the historical driving event data; acquiring current driver data, current running vehicle data, current running road data and current time data; obtaining current driving habit models of other drivers from the driving habit models according to the current driving road data and/or the current time data; judging whether a preset standard driving behavior model is safe or not according to the current driving habit model; when the standard driving behavior model is determined to be unsafe, modifying the standard driving behavior model according to the current driving habit model to obtain a current standard driving behavior model; judging whether the driving behavior of the current driver is safe or not according to the current standard driving behavior model, the current driver data and the current running vehicle data; and when the driving behavior of the current driver is unsafe, sending driving behavior correction alarm information. By implementing the scheme, the driving habits of other vehicles on the road where the vehicle runs can be predicted in advance, and the standard driving behavior model of the driver of the current vehicle is modified, so that the adverse effect of the other vehicles on the current vehicle is effectively avoided.

In some possible embodiments of the invention, the driver data comprises driver eye rotation data, eyelid state data, and head movement information, and driver stimulus-response time data, driver physiological data, and driver operational behavior data; wherein the driver operation behavior data includes at least data such as inter-vehicle distance holding data, accelerator pedal stepping data, brake pedal stepping data, turn signal use data, and steering wheel rotation data;

the running vehicle data comprises vehicle position data, vehicle speed data, oil consumption/electricity consumption data, steering data and vehicle data (such as navigation and music use states);

the driving road data comprises road address data, lane number data, lane driving identification data, road surface evenness data, camber data and gradient data.

It is understood that, in the embodiment of the present invention, the eyeball rotation data, the eyelid state data, the head movement information, and the like of the driver may be obtained through image acquisition and recognition technology, and the stimulation-response time data of the driver, the physiological data of the driver, and the like may be calculated by collecting relevant data (such as heartbeat, body temperature, nerve response data, blood glucose content, blood oxygen content, respiratory frequency, and the like) through a sensor and then using the collected data, and the data, such as the eyeball rotation data, the eyelid state data, and the head movement information of the driver, the stimulation-response time data of the driver, the physiological data of the driver, may accurately analyze the mental state of the driver and determine whether there is unsafe driving movement of the driver, and the like.

The data of the driver operation behaviors at least comprise inter-vehicle distance keeping data, accelerator pedal stepping data, brake pedal stepping data, steering lamp use data and steering wheel rotation data, the data can be obtained by acquiring original data through an in-vehicle camera, a pressure sensor and the like and analyzing and processing the original data, the data is the most direct embodiment of the driver driving behaviors, and accurate data support can be provided for determining whether the driver driving behaviors are safe or not.

The road condition is one of the factors which have great influence on the safe driving of the vehicle, and the driving road data can be collected, processed and analyzed through a camera, a three-dimensional measuring device, a positioning device and other collection equipment and a control processing module. The driving road data at least comprises road address data, lane number data, lane driving identification data, road surface evenness data, camber data, gradient data and the like. By collecting the data of the driving road, a more accurate driving habit model can be determined according to the special road conditions in a random strain mode.

In some possible embodiments of the present invention, the method for acquiring steering wheel rotation data includes:

acquiring first image data of a steering wheel in a return state;

performing character recognition on the first image data, and determining a central axis of the steering wheel according to a character group in the horizontal direction;

acquiring current image data of a steering wheel of a vehicle in a driving state;

obtaining a deflection angle of the central axis according to the current image data and the first image data to obtain a rotation angle of the steering wheel;

acquiring the rotation time of the steering wheel;

and calculating to obtain the rotating speed according to the rotating angle and the rotating time.

It is understood that the steering wheel is a core control component of the vehicle driving process, and in the embodiment of the invention, whether the control of the steering wheel by the driver is safe can be judged by collecting and analyzing the moving image data of the steering wheel. Specifically, first image data of the steering wheel in a return state is acquired, character recognition is performed on the first image data, a horizontal line is determined according to a character group (such as vehicle trademark characters or figures, identification characters of control keys and the like) in the horizontal direction, and then a straight line perpendicular to the horizontal line and equally dividing the character group (or the whole steering wheel), namely a central axis of the steering wheel, is determined according to symmetry of the character group (or the whole steering wheel). Acquiring current image data of a steering wheel of a vehicle in a driving state in real time in the driving process of the vehicle; then obtaining a deflection angle of the central axis according to the current image data and the first image data (for example, a coordinate system is established by taking the rotation center of the steering wheel as an origin, the central axis as a Y axis and a vertical line of the central axis as an X axis, and the deflection angle can be obtained by measuring the length of an intersecting line segment and combining coordinate calculation), namely obtaining the rotation angle of the steering wheel; meanwhile, the rotation time of the steering wheel can be acquired (for example, a special timer is controlled for timing), and finally, the rotation speed is calculated according to the rotation angle and the rotation time. The rotation angle and the rotation speed of the steering wheel can reflect whether the control of the steering wheel by the driver is safe or not.

It will be appreciated that for more than one revolution, the number of revolutions may be recorded by the camera, and the rotation angle may be obtained by adding 360 degrees to the yaw angle.

In some possible embodiments of the present invention, the method for acquiring road flatness data includes:

collecting road surface image data of a driving road, and identifying a water accumulation area, a damaged area, an obstacle and a sharp object from the image data;

respectively collecting three-dimensional data of the ponding area, the damage area, the barrier and the sharp object;

respectively calculating ponding area data, damaged area data, barrier data and sharp object data according to the three-dimensional data; the water accumulation area data at least comprise a water accumulation position and a water accumulation depth, the damaged area data at least comprise a damaged area position and a damaged degree, the obstacle data at least comprise an obstacle position and an obstacle volume, and the sharp object data at least comprise a distribution position and a sharp degree of a sharp object;

and obtaining the road surface flatness data according to the water accumulation area data, the damaged area data, the barrier data and the sharp object data.

It can be understood that, in order to obtain more detailed road information to establish a more accurate driving habit model, in an embodiment of the present invention, the road surface image data of the driving road may be collected, the water accumulation region, the damaged region, the obstacle and the sharp object may be identified from the image data according to pre-stored model data of the water accumulation region, the damaged region, the obstacle and the sharp object, the three-dimensional data of the water accumulation region, the damaged region, the obstacle and the sharp object may be further collected respectively (for example, three-dimensional data collected by a laser scanning device, an ultrasonic scanning device, a multi-view camera device, a structured light image collecting device, etc.), at least the water accumulation position and the water accumulation depth of the water accumulation region, the damaged region position and the damaged degree, the obstacle position and the obstacle volume may be calculated according to a preset measurement algorithm or a measurement model, the distribution position and the sharpness degree of the sharp objects and the like; and obtaining the road surface flatness data according to the water accumulation area data, the damaged area data, the barrier data and the sharp object data.

In some possible embodiments of the present invention, the driving behavior correction method further includes:

collecting first face data and first head posture data of the current driver;

determining an eye area according to the first face data to obtain a first eye picture;

extracting first eye movement data, and processing the first eye movement data to obtain first eye movement characteristic data;

and inputting a preset head recognition model according to the first head posture data and the first eye movement characteristic data so as to judge whether unsafe driving behaviors exist in the current driver.

It can be understood that, in the driving process, a driver should watch the road information at the maximum visual angle, and if the driver has a sudden visual line, is not focused, has an incorrect head posture, and the like, accidents may occur, in the embodiment of the present invention, by collecting the first face data and the first head posture data of the current driver, the first face data is subjected to eye recognition, a eye region is determined, a first eye picture is obtained, then the first eye movement data is extracted, and the first eye movement data is processed, so that first eye movement characteristic data is obtained; and finally, inputting a preset head recognition model according to the first head posture data and the first eye movement characteristic data so as to judge whether the current driver has unsafe driving behaviors. By the scheme of the embodiment, whether unsafe driving behaviors exist in the current driver can be accurately identified through the states of human eyes and the head.

It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present application is not limited by the order of acts described, as some steps may occur in other orders or concurrently depending on the application. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required in this application.

In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the above-described embodiments of the apparatus are merely illustrative, and for example, the above-described division of the units is only one type of division of logical functions, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of some interfaces, devices or units, and may be an electric or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated unit may be stored in a computer readable memory if it is implemented in the form of a software functional unit and sold or used as a stand-alone product. Based on such understanding, the technical solution of the present application may be substantially implemented or a part of or all or part of the technical solution contributing to the prior art may be embodied in the form of a software product stored in a memory, and including several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the above-mentioned method of the embodiments of the present application. And the aforementioned memory comprises: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.

Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by associated hardware instructed by a program, which may be stored in a computer-readable memory, which may include: flash Memory disks, Read-Only memories (ROMs), Random Access Memories (RAMs), magnetic or optical disks, and the like.

The foregoing embodiments have been described in detail, and specific examples are used herein to explain the principles and implementations of the present application, where the above description of the embodiments is only intended to help understand the method and its core ideas of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Although the present invention is disclosed above, the present invention is not limited thereto. Various changes and modifications can be easily made by those skilled in the art without departing from the spirit and scope of the present invention, and it is within the scope of the present invention to include different functions, combination of implementation steps, software and hardware implementations.

Claims (10)

1. A driving behavior correction system for an intelligent vehicle, comprising: the driving habit model building method comprises an acquisition module, a driving habit model building module and a control processing module;

the acquisition module is used for acquiring historical driving event data;

the driving habit model building module is used for generating a driving habit model according to time dimension or road dimension or vehicle type dimension or driver dimension according to the historical driving event data;

the acquisition module is also used for acquiring current driver data, current running vehicle data, current running road data and current time data;

the control processing module is used for:

obtaining current driving habit models of other drivers from the driving habit models according to the current driving road data and/or the current time data;

judging whether a preset standard driving behavior model is safe or not according to the current driving habit model;

when the standard driving behavior model is determined to be unsafe, modifying the standard driving behavior model according to the current driving habit model to obtain a current standard driving behavior model;

judging whether the driving behavior of the current driver is safe or not according to the current standard driving behavior model, the current driver data and the current running vehicle data;

when the driving behavior of the current driver is unsafe, sending driving behavior correction alarm information;

wherein the historical driving event data includes at least driver data, driving vehicle data, driving region data, driving time data, and driving road data.

2. The driving behavior correction system for smart car according to claim 1, wherein the driver data includes driver eyeball rotation data, eyelid state data and head motion information, and driver stimulus-response time data, driver physiological data, and driver operational behavior data; wherein the driver operation behavior data includes at least data such as inter-vehicle distance holding data, accelerator pedal stepping data, brake pedal stepping data, turn signal use data, and steering wheel rotation data;

the running vehicle data comprises vehicle position data, vehicle speed data, oil consumption/power consumption data, steering data and vehicle-mounted machine data;

the driving road data comprises road address data, lane number data, lane driving identification data, road surface evenness data, camber data and gradient data.

3. The driving behavior correction system for the intelligent automobile according to claim 2, wherein the obtaining module is further configured to obtain first image data of the steering wheel in a return state;

the control processing module is further configured to perform character recognition on the first image data, and determine a central axis of the steering wheel according to a character group in a horizontal direction;

the acquisition module is further used for acquiring current image data of a steering wheel of a vehicle in a driving state;

the control processing module is further configured to obtain a deflection angle of the central axis according to the current image data and the first image data, so as to obtain a rotation angle of the steering wheel;

the acquisition module is further used for acquiring the rotation time of the steering wheel;

and the control processing module is also used for calculating the rotation speed according to the rotation angle and the rotation time.

4. The driving behavior correction system for the intelligent automobile according to claim 3, wherein the acquiring module is further configured to acquire road surface image data of a driving road;

the control processing module is also used for identifying a water accumulation area, a damaged area, an obstacle and a sharp object from the image data;

the acquisition module is further used for respectively acquiring three-dimensional data of the water accumulation area, the damaged area, the barrier and the sharp object;

the control processing module is further used for respectively calculating ponding area data, damaged area data, barrier data and sharp object data according to the three-dimensional data; the water accumulation area data at least comprise a water accumulation position and a water accumulation depth, the damaged area data at least comprise a damaged area position and a damaged degree, the obstacle data at least comprise an obstacle position and an obstacle volume, and the sharp object data at least comprise a distribution position and a sharp degree of a sharp object;

and the control processing module is also used for obtaining the road surface evenness data according to the water accumulation area data, the damaged area data, the obstacle data and the sharp object data.

5. The driving behavior correction system for intelligent automobile as claimed in claim 4, wherein the obtaining module is further configured to collect first face data and first head posture data of the current driver;

the control processing module is further configured to:

determining an eye area according to the first face data to obtain a first eye picture;

extracting first eye movement data, and processing the first eye movement data to obtain first eye movement characteristic data;

and inputting a preset head recognition model according to the first head posture data and the first eye movement characteristic data so as to judge whether unsafe driving behaviors exist in the current driver.

6. A driving behavior correction method for an intelligent automobile, characterized by comprising:

acquiring historical driving event data;

generating a driving habit model according to time dimension, road dimension, vehicle type dimension or driver dimension according to the historical driving event data;

acquiring current driver data, current running vehicle data, current running road data and current time data;

obtaining current driving habit models of other drivers from the driving habit models according to the current driving road data and/or the current time data;

judging whether a preset standard driving behavior model is safe or not according to the current driving habit model;

when the standard driving behavior model is determined to be unsafe, modifying the standard driving behavior model according to the current driving habit model to obtain a current standard driving behavior model;

judging whether the driving behavior of the current driver is safe or not according to the current standard driving behavior model, the current driver data and the current running vehicle data;

when the driving behavior of the current driver is unsafe, sending driving behavior correction alarm information;

wherein the historical driving event data includes at least driver data, driving vehicle data, driving region data, driving time data, and driving road data.

7. The driving behavior correction method for the intelligent automobile as claimed in claim 6, wherein the driver data comprises driver eyeball rotation data, eyelid state data and head movement information, and stimulation-reaction time data of the driver, physiological data of the driver, and driver operation behavior data; wherein the driver operation behavior data includes at least data such as inter-vehicle distance holding data, accelerator pedal stepping data, brake pedal stepping data, turn signal use data, and steering wheel rotation data;

the running vehicle data comprises vehicle position data, vehicle speed data, oil consumption/electricity consumption data, steering data and vehicle-mounted machine data;

the driving road data comprises road address data, lane number data, lane driving identification data, road surface evenness data, camber data and gradient data.

8. The driving behavior correction method for an intelligent automobile according to claim 7, wherein the steering wheel rotation data acquisition method includes:

acquiring first image data of a steering wheel in a return state;

performing character recognition on the first image data, and determining a central axis of the steering wheel according to a character group in the horizontal direction;

acquiring current image data of a steering wheel of a vehicle in a driving state;

obtaining a deflection angle of the central axis according to the current image data and the first image data to obtain a rotation angle of the steering wheel;

acquiring the rotation time of the steering wheel;

and calculating to obtain the rotating speed according to the rotating angle and the rotating time.

9. The driving behavior correction method for the intelligent automobile according to claim 8, wherein the acquisition method of the road flatness data comprises:

collecting road surface image data of a driving road, and identifying a water accumulation area, a damaged area, an obstacle and a sharp object from the image data;

respectively collecting three-dimensional data of the water accumulation area, the damaged area, the barrier and the sharp object;

respectively calculating ponding area data, damaged area data, barrier data and sharp object data according to the three-dimensional data; the data of the ponding area at least comprise a ponding position and a ponding depth, the data of the damaged area at least comprise a damaged area position and a damaged degree, the data of the obstacle at least comprise an obstacle position and an obstacle volume, and the data of the sharp object at least comprise a distribution position and a sharp degree of the sharp object;

and obtaining the road surface flatness data according to the water accumulation area data, the damaged area data, the barrier data and the sharp object data.

10. The driving behavior correction method for the smart car according to claim 9, characterized in that the driving behavior correction method further comprises:

collecting first face data and first head posture data of the current driver;

determining an eye area according to the first face data to obtain a first eye picture;

extracting first eye movement data, and processing the first eye movement data to obtain first eye movement characteristic data;

and inputting a preset head recognition model according to the first head posture data and the first eye movement characteristic data so as to judge whether unsafe driving behaviors exist in the current driver.

Images