KR20190070177A - Method and apparatus for determining drowsy state of vehicle driver - Google Patents

Abstract

The present invention relates to a method and an apparatus for determining a drowsy state of a vehicle driver. According to an embodiment of the present invention, the method for determining the drowsy state of the vehicle driver, which is conducted by the apparatus for determining the drowsy state of the vehicle driver, comprises the following steps of: calculating a normal drowsy index, which is a reference for determining a drowsy state, when the vehicle is normally driving, by learning driving patterns of the driver in a longitudinal direction and a transverse direction; collecting the driving patterns of the driver in a longitudinal direction and a transverse direction, when the vehicle is currently driving, to calculate a current drowsy index, which shows drowsy characteristics of the current driver, to analyze the current drowsy index calculated based on the calculated normal drowsy index, and to determine the drowsy state of the driver; and generating a drowsy driving warning to the driver when the driving pattern of the driver is determined as a drowsy driving. The present invention aims to provide a method and apparatus for determining the drowsy state of a vehicle driver, which are able to determine drowsy driving without an additional machine apparatus, and generate a warning.

Description

TECHNICAL FIELD The present invention relates to a method and apparatus for determining the drowsiness state of a driver of a vehicle,

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to safety of a vehicle driver, and more particularly, to a method and apparatus for determining a drowsy state of a vehicle driver.

Generally, highways, long straight roads, or low-grade roads have gentle curvature of roads, and road conditions are monotonous. Therefore, the driver runs the vehicle with little steering operation, gear shifting, or braking operation. Therefore, the driver is liable to drowsiness because there is little movement of the body and there is little change of the peripheral visual field. However, large-scale accidents occur frequently due to such driver's drowsiness driving. Drowsiness driving is a direct or indirect cause of four out of ten motorway accidents, and there is a high need for a system to prevent or prevent them.

Conventionally, in order to prevent driver's drowsy driving, a camera for grasping the facial expression of the driver or a sensor attached to the handle and sensing the force of the driver's hand is used to monitor whether the driver is driving the drowsy, And informed the driver of the drowsy driving.

Korean Patent Publication No. 2003-0018919 discloses a "vehicle brake system " which monitors the driver's sleep-driving operation by grasping the amount of eyelid cover and pupil enlargement at the driver's eye area using a digital camera installed on a moving object, A drowsy operation and an emergency situation recognition method using the same ".

In addition, there are various methods for judging the driver's drowsiness in the past. A method using a camera used for eye tracking, a method using a heartbeat sensor for collecting biometric data, and a method using an ECG (electrocardiogram) sensor.

The conventional method as described above notifies the driver of the drowsiness driving state in a state where the driver is already sleeping. Alternatively, the conventional method controls the moving body accordingly, so that the driver can make a mistake in operating the hovering operation in a state where the driver is less disturbed by drowsiness due to a sudden alarm sound or the like. Even when brake braking is followed, a large number of accidents may occur due to many risk factors such as the road surface and surrounding moving bodies.

Korean Patent Publication No. 10-2003-0018919 (published on Mar. 06, 2003)

A conventional method of determining a drowsy state of a driver focuses on a technique of determining a drowsy driving based on sensitive individual information such as a driver's face or a biological signal. Thus, there is a controversy about privacy violation. Further, in order to perform such a method of determining the drowsiness state, it is necessary to additionally mount the sensor only for determining the drowsiness state. The price of additional sensors is high, making it difficult to apply them to real vehicles.

In the embodiments of the present invention, the normal drowsiness index, which is a standard for judging the drowsy state, is learned by learning the driving pattern of the driver in the longitudinal direction and the lateral direction at the time of normal driving, and the driving pattern in the longitudinal direction and the lateral direction The drowsiness operation is determined by analyzing the current drowsiness index calculated based on the normal drowsiness index so as to determine the drowsiness operation without additional mechanical devices (e.g., a camera, a sensor, etc.) And a method and apparatus for determining a drowsy state of a driver of a vehicle.

The embodiments of the present invention set the safe area by learning the longitudinal and lateral direction travel patterns of the vehicle driver at the time of normal driving, determine the drowsy driving state of the driver in real time according to the set safe range, A method and an apparatus for determining a drowsiness state of a vehicle driver that can prevent drowsiness driving of a vehicle driver.

Embodiments of the present invention provide a method and apparatus for determining a drowsy state of a driver who can provide safe driving in cooperation with an ADAS system installed in a vehicle in consideration of a driver's condition, ≪ / RTI >

According to an embodiment of the present invention, there is provided a method for determining a sleepiness state of a vehicle driver performed by a sleepiness state determination apparatus, the method comprising: learning a driving pattern in a longitudinal direction and a lateral direction of a driver during normal driving, Calculating a normal drowsiness index; The driving pattern of the driver in the longitudinal direction and the lateral direction of the driver is collected to calculate the current drowsiness index indicating the drowsiness characteristic of the current driver and the calculated current drowsiness index is analyzed based on the calculated normal drowsiness index, Determining a drowsy state of the subject; And generating a drowsy driving warning to the driver when the driving pattern of the driver is determined to be a drowsy driving mode.

The method may further include the step of determining a running condition based on the running speed or the position information of the vehicle.

In the step of determining the driving situation, when navigation capable of interlocking with the vehicle is installed, the driving state can be determined using the position information provided in the navigation or the moving speed of the current road.

The step of determining the driving situation may determine the driving situation as any one of a driving in a city, a driving on an expressway, and a driving on a congested road.

The method may further include the step of re-learning the longitudinal and lateral direction travel patterns and re-shipping the normal drowsiness index if the determined travel condition exceeds the predetermined travel condition change amount or there is a re-search request from the driver can do.

The step of calculating the normal drowsiness index may calculate a normal drowsiness index using the size and the control period of the safety zone set from the running pattern of the driver in the longitudinal direction and the lateral direction at the time of normal driving.

The step of calculating the normal drowsiness index includes calculating a longitudinal error value and a longitudinal control period at the time when the sign of the relative speed between the preceding vehicle and the subject vehicle is changed, It is possible to set the safe region and the control period by using the lateral error value and the lateral control period.

Wherein the drowsiness index of the driver is calculated by summing the drowsiness indexes multiplied by the longitudinal and lateral coefficients on the longitudinal and transverse drowsiness indexes derived from the running patterns of the driver in the longitudinal and lateral directions, The drowsiness index can be calculated at present.

The step of determining the drowsy state of the driver may vary the longitudinal and lateral coefficients according to the current driving situation.

The generating of the alert may include displaying a warning icon on the vehicle cluster, generating a warning sound, or displaying a warning icon on the vehicle cluster according to the weight of the outliers as a result of analyzing the calculated current drowsiness index based on the calculated normal drowsiness index, The diaphragm provided on the seat can be vibrated.

According to another embodiment of the present invention, a driving pattern learning unit for calculating a normal drowsiness index as a reference for determining a drowsy state by learning a driving pattern in a longitudinal direction and a lateral direction of a driver during normal driving; The driving pattern of the driver in the longitudinal direction and the lateral direction of the driver is collected to calculate the current drowsiness index indicating the drowsiness characteristic of the current driver and the calculated current drowsiness index is analyzed based on the calculated normal drowsiness index, A drowsy state determination unit for determining a drowsy state of the subject; And an alarm generating unit for generating a warning signal for driving the sleeping driver when the driving pattern of the driver is determined to be a drowsy driving operation.

The apparatus may further include a running condition determining unit for determining a running condition based on the running speed or the position information of the vehicle.

The navigation state determination unit may determine the driving state using the position information provided in the navigation or the traveling speed of the current road when navigation capable of interlocking with the vehicle is mounted.

The driving situation judging unit can judge that the driving situation is any one of a city driving, a highway driving, and a congested road driving.

The traveling pattern learning unit may re-learn the traveling patterns in the longitudinal direction and the lateral direction to re-estimate the normal drowsiness index when the determined traveling state exceeds the predetermined traveling state change amount or there is a request for re-searching from the driver.

The travel pattern learning unit can calculate a normal drowsiness index using the size and the control period of the safety zone set from the travel patterns in the longitudinal and lateral directions of the driver during normal travel.

The traveling pattern learning section may calculate the longitudinal error value and the longitudinal control period at the time when the sign of the relative speed between the preceding vehicle and the vehicle is changed and the longitudinal error value at the time when the sign of the vehicle steering angular velocity operated by the vehicle driver is changed, And the lateral control period can be used to set the safety zone and the control period.

The drowsiness state determiner may calculate the current drowsiness index by summing the drowsiness indexes multiplied by the longitudinal and lateral coefficients of the longitudinal and lateral drowsiness indexes derived from the running patterns of the driver in the longitudinal and lateral directions can do.

The drowsiness state determiner may vary the longitudinal and lateral coefficients according to the determined driving situation.

The alarm generating unit analyzes the calculated current drowsiness index based on the calculated normal drowsiness index and displays a warning icon on the vehicle cluster according to the weight of the outliers, generates a warning sound, The diaphragm can be vibrated.

In the embodiments of the present invention, the normal drowsiness index, which is a standard for judging the drowsy state, is learned by learning the driving pattern of the driver in the longitudinal direction and the lateral direction at the time of normal driving, and the driving pattern in the longitudinal direction and the lateral direction The drowsiness operation is determined by analyzing the current drowsiness index calculated on the basis of the normal drowsiness index so that the drowsiness operation can be determined and the warning can be generated without using any additional mechanical device (e.g., camera, sensor, etc.) .

The embodiments of the present invention set the safe area by learning the longitudinal and lateral direction travel patterns of the vehicle driver at the time of normal driving, determine the drowsy driving state of the driver in real time according to the set safe range, The driver of the vehicle can be prevented from running drowsy.

Embodiments of the present invention can provide safe driving in conjunction with an Advanced Driver Assistance System (ADAS) system installed in a vehicle in consideration of a driver's condition.

1 is a block diagram for explaining a configuration of an apparatus for determining a drowsiness state of a vehicle driver according to an embodiment of the present invention.
2 is a view for explaining a safety area according to distance adjustment with respect to a front vehicle.
3 is a view for explaining the safe range and angular velocity of the steering wheel according to the running error of the driver.
4 is a diagram for explaining a size comparison of a safe area according to a driver's state.
5 is a view for explaining a steady-state steering operation change point.
6 is a view for explaining a point in time at which the steering operation is changed in the drowsy state.
7 is a diagram for explaining a safety zone and a control period in a normal state and a drowsy state.
8 is a flowchart illustrating a method for determining a sleeping state of a vehicle driver according to an embodiment of the present invention.

While the invention is susceptible to various modifications and alternative forms, specific embodiments thereof are shown by way of example in the drawings and will herein be described in detail.

It should be understood, however, that the invention is not intended to be limited to the particular embodiments, but includes all modifications, equivalents, and alternatives falling within the spirit and scope of the invention.

The terms first, second, etc. may be used to describe various components, but the components should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, the first component may be referred to as a second component, and similarly, the second component may also be referred to as a first component. And / or < / RTI > includes any combination of a plurality of related listed items or any of a plurality of related listed items.

It is to be understood that when an element is referred to as being "connected" or "connected" to another element, it may be directly connected or connected to the other element, . On the other hand, when an element is referred to as being "directly connected" or "directly connected" to another element, it should be understood that there are no other elements in between.

The terminology used in this application is used only to describe a specific embodiment and is not intended to limit the invention. The singular expressions include plural expressions unless the context clearly dictates otherwise. In the present application, the terms "comprises" or "having" and the like are used to specify that there is a feature, a number, a step, an operation, an element, a component or a combination thereof described in the specification, But do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, or combinations thereof.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the relevant art and are to be interpreted in an ideal or overly formal sense unless explicitly defined in the present application Do not.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In order to facilitate the understanding of the present invention, the same reference numerals are used for the same constituent elements in the drawings and redundant explanations for the same constituent elements are omitted.

1 is a block diagram for explaining a configuration of an apparatus for determining a drowsiness state of a vehicle driver according to an embodiment of the present invention.

1, an apparatus 100 for determining a drowsiness state of a vehicle driver according to an embodiment of the present invention includes a traveling state determination unit 110, a traveling pattern learning unit 120, a drowsiness state determination unit 130, And an alarm generating unit 140. Here, the drowsy state determination apparatus 100 may further include an input / output unit 150. However, not all illustrated components are required. The drowsiness determination apparatus 100 may be implemented by a larger number of components than the illustrated components, and the drowsiness determination apparatus 100 may be implemented by fewer components.

Hereinafter, the specific configuration and operation of the components of the apparatus 100 for determining the drowsiness state of the vehicle driver according to the embodiment of the present invention shown in FIG. 1 will be described.

The running condition determination unit 110 determines the running condition based on the running speed or the position information of the vehicle. Here, the navigation state determination unit 110 may determine the driving state using the position information provided in the navigation or the moving speed of the current road when navigation capable of interlocking with the vehicle is mounted. For example, the running condition determination unit 110 can determine the running condition as any one of running in the city, highway running, and congested road running.

The traveling pattern learning unit 120 learns the traveling patterns of the driver in the longitudinal direction and the lateral direction at the time of normal traveling, and calculates a normal drowsiness index as a reference for determining the drowsiness state.

The drowsy state determination unit 130 collects driving patterns in the longitudinal and lateral directions of the driver at the time of present driving, and calculates a current drowsiness index indicating the drowsiness characteristics of the current driver. The drowsiness state determiner 130 determines the drowsiness state of the driver by analyzing the calculated current drowsiness index based on the normal drowsiness index calculated by the driving pattern learning unit 120.

Specifically, the driving pattern learning unit 120 can calculate a normal drowsiness index using the size and the control period of the safety zone set from the driving pattern in the longitudinal and lateral directions of the driver during normal driving. At this time, the travel pattern learning unit 120 calculates the longitudinal direction error value and the longitudinal direction control value at the time when the sign of the vehicle steering angular velocity operated by the vehicle driver is changed By using the lateral error value and the lateral control period, the safe region and the control period can be set. Here, the error value at the time when the signs of the front vehicle and the vehicle relative speed are changed represents the difference between the average safe distance and the instant safety distance. The error value at the time when the sign of the vehicle steering angular velocity operated by the driver changes is the difference between the average running direction and the instantaneous running direction.

The drowsiness state determiner 130 adds the drowsiness index multiplied by the longitudinal and lateral coefficients to the longitudinal and transverse drowsiness indexes derived from the running patterns of the driver in the longitudinal and lateral directions at the time of the present driving, Can be calculated. That is, the drowsy state determination unit 130 compares the current safety distance and the steering data of the current driver with the steering data, and determines whether or not the driver is drowsy through the compared values. The drowsy state determination unit 130 may determine whether the driver is drowsy by comparing the longitudinal and lateral error values and the control cycle of the driver in the normal state with the longitudinal and lateral error values and the control cycle of the current real time driver. The drowsy state determination unit 130 may vary the longitudinal and lateral coefficients according to the current driving situation.

The warning generating unit 140 generates a drowsy driving warning to the current driver when it is determined that the driving pattern of the current driver is the drowsy driving. Here, the alarm generating unit 140 analyzes the derived longitudinal and lateral drowsiness indexes based on the calculated normal drowsiness index, and as a result, displays a warning icon in the vehicle cluster according to the weight of the outliers, Or to vibrate the diaphragm provided on the vehicle seat.

On the other hand, when the traveling state determined by the traveling state determination unit 110 exceeds the predetermined traveling state change amount or there is a request for searching again from the driver, the traveling pattern learning unit 120 may repeat the traveling pattern in the longitudinal direction and the lateral direction You can learn to reassess the normal drowsiness index.

Here, the input / output unit 150 receives the re-search command from the driver. Also, the input / output unit 150 may output the driving state determined by the driving state determination unit 110 or may output the drowsiness state determined by the drowsiness state determination unit 130.

2 is a view for explaining a safety area according to distance adjustment with respect to a front vehicle.

As shown in FIG. 2, the vehicle driver maintains the safety distance between the vehicle 10 and the front vehicle 20 during normal driving. The drowsy state determination apparatus 100 learns a traveling pattern that maintains the safety distance with respect to the forward vehicle 20 during normal traveling and analyzes the learned traveling pattern.

There is a certain pattern for each driver to maintain the safety distance with the front vehicle 20 when the driver is driving on the expressway or in the city during normal driving. In an embodiment of the present invention, a distance between a point 211, which accelerates in order to narrow the distance from the front vehicle 20 in FIG. 2, and a point 212, which decelerates in order to widen the distance, is defined as a longitudinal safety zone 210 .

The driver in the steady state operates on the basis of the safety distance that he deems appropriate according to the current vehicle speed. The steady state driver controls the accelerator pedal or the brake pedal when it recognizes that the safety distance has moved away from or near the range of the longitudinal safety zone 210. [

On the other hand, a sleepy driver may be driving farther or closer than the safety distance that he deems appropriate, depending on the current vehicle speed. Since the driver in the drowsy state recognizes that the safety distance is far from or near the range of the longitudinal safety zone 210, the accelerator pedal or the brake pedal can be controlled with a longer control period than during normal driving. That is, when the driver is in a drowsy state, the current operation region and the control period for controlling the safety distance may be different from the longitudinal safety zone 210 and the control period.

Therefore, the drowsiness state determination apparatus 100 learns the driving pattern of the driver for a predetermined period of time during normal driving, thereby setting the longitudinal safety zone 210 and the control period. Here, the longitudinal safety zone 210 represents an area controlled by the driver to keep the safety distance within a certain range with respect to the preceding vehicle.

Here, the drowsy state determination apparatus 100 calculates the longitudinal safety zone 210 and the control period using the error value and the control period at the time when the sign of the relative speed between the front vehicle 20 and the vehicle 10 is changed can do. Here, the error value can be expressed as a difference between an average safety distance and an instantaneous safety distance between the front vehicle 20 and the vehicle 10.

The distance to the front vehicle can be measured with the advanced driver assistance system (ADAS) or a radar or lidar sensor mounted on the vehicle for autonomous driving. The drowsy state determination apparatus 100 can acquire the distance between the vehicle 10 and the front vehicle from an advanced driver assistance system (ADAS), a radar, or a Lydia sensor mounted on the vehicle.

3 is a view for explaining the safe range and angular velocity of the steering wheel according to the running error of the driver.

As shown in FIG. 3, the analysis result of the traveling pattern in which the vehicle steering angular velocity is changed according to the driver's intention to travel will be described.

Most drivers do not steer to the center of the lane in order to drive without any error. For example, the driver in the steady state adjusts the steering wheel left or right in the interval 311 to 315 of FIG. Accordingly, the vehicle travels while moving appropriately to the left or right within a certain error range. In an embodiment of the present invention, when the driver travels within a certain error range, this error range is defined as the lateral safety zone 310.

The driver in the steady state operates on the basis of the lateral point determined as appropriate according to the current lane. When the driver recognizes that the vehicle has deviated from the center of the lane by more than the size of the lateral safety zone 310, the driver in the steady state controls the steering in the direction of reducing the error.

On the other hand, a driver in a drowsy state may be driven to the left or to the right or to the left or right rather than the lateral point determined as appropriate according to the current lane. The driver in the drowsy state can recognize that the vehicle has deviated from the center of the lane by more than the size of the lateral safety zone 310 and therefore can control the steering in the direction of slowly reducing the error to a longer control period in normal driving. That is, when the driver is in a drowsy state, the size of the current lateral operation region and the control period for adjusting the lateral direction may be different from the lateral safety zone 310 and the control period in the steady state.

Accordingly, the lateral safety zone 310 and the control period represent the magnitude of the error value and the control period for the maximum left and right lateral directions that the driver of the steady state observes for lane keeping.

4 is a diagram for explaining a size comparison of a safe area according to a driver's state.

As shown in FIG. 4, the size of the safe area varies depending on the driver's state. That is, the size of the safe area may vary depending on whether the driver is a normal state driver or a drowsy state driver. The safe area 412 when the driver of the drowsy state is driven becomes larger than the safe area 411 when the driver of the normal state is driving.

Such a safe area can be different from each other due to the characteristics of each driver even when the same lane is driven. This is because driving patterns are different for each driver. Also, in the driver individual, the size of the safe area can be changed in accordance with the condition of the day when the same driver drives.

In order to reflect such a change in the safety zone, the drowsiness state determination apparatus 100 can learn the driving pattern of the driver in the longitudinal direction and the lateral direction during normal driving, and determine the drowsiness state by reflecting the learned result.

In addition, since the safe zone can be varied depending on the traveling state, the drowsy state determination apparatus 100 determines the running state based on the running speed or the position information of the vehicle, The state can be judged.

5 is a view for explaining a steady-state steering operation change point.

Hereinafter, a case in which a driver in a steady state operates by adjusting a steering wheel will be described. The number of cases in which the driver in the steady state adjusts the steering wheel in the lateral direction, that is, the left direction or the right direction with respect to the center is counted. Here, the center of the steering wheel is zero. When the steering wheel is adjusted to the right side, it is counted as a positive error value (Error (m)), and when the steering wheel is adjusted to the right side, it is counted as a positive (+) error value.

As shown in FIG. 5, the steering operation change time point in the steady state has an error range of -0.2 in the left direction and +0.2 in the right direction with respect to 0 in the center. That is, when the steady state driver operates by adjusting the steering wheel, the error range of the steering wheel is concentrated toward the center.

6 is a view for explaining a point in time at which the steering operation is changed in the drowsy state.

Let's take a look at a case where a sleepy driver operates by adjusting the steering wheel. The number of cases in which the driver in the drowsy state adjusts the steering wheel in the lateral direction, that is, the left direction or the right direction with respect to the center is counted. Here, the center of the steering wheel is zero. The plus (+) error value is counted when the steering wheel is adjusted to the right, and the plus (+) error value is counted when the steering wheel is adjusted to the right.

As shown in Fig. 6, the steering operation change time point in the drowsy state has an error range of -0.3 in the left direction and +0.3 in the right direction with respect to 0 in the center. That is, the error range in FIG. 6 is larger than the error range in FIG.

In FIG. 5, the counts near 0 in the center are counted from 100 to 120, while in FIG. 6, counts in the vicinity of 0 in the center are counted from 50 to 70 counts. In FIG. 5, counts are concentrated on error values having a small difference from 0 in the center, while counts are generated in error values as well as error values having a small difference from 0 in the center in FIG. 6. The steady-state error values are concentrated around the center. On the other hand, the drowsiness error values are distributed not only in the center but also in the large error values. That is, the error values in the drowsy state are spread more widely than the error values in the steady state. When the steady state driver operates by adjusting the steering wheel, the error range of the steering wheel is concentrated toward the center. This error range at the time of normal traveling can be set as the safe area.

Thus, the size of the safe area changes according to the driver's condition. Therefore, the drowsiness state determination apparatus 100 learns the safe region when the driver is in the normal state, and sets the safe region based on the learned result. The drowsiness state determination apparatus 100 can determine the drowsiness state of the driver by comparing the size of the current safe area that is currently traveling with the safe area in the steady state. The drowsy state determination apparatus 100 compares longitudinal safety distances and lateral steering data of a driver in a normal state, that is, a driver in a drowsy state, and determines a drowsy state of the driver based on the comparison result .

7 is a diagram for explaining a safety zone and a control period in a normal state and a drowsy state.

The apparatus for determining the drowsiness state of a vehicle driver 100 according to an embodiment of the present invention is a device for determining the drowsiness state of a vehicle driver by comparing the longitudinal and lateral safety regions learned from the normal travel pattern, The driver is determined to be drowsy through the value. Here, the longitudinal safety zone is expressed by the magnitude of the error value at the time when the sign of the relative speed between the preceding vehicle and the preceding vehicle is changed. The lateral safety zone is expressed as the magnitude of the lateral error value at the time of sign change of the steering wheel angular velocity.

The drowsy state determination apparatus 100 can determine the drowsy state of the driver by storing the longitudinal and lateral safety zones and the control period at the time of the usual driver's driving and comparing them at every moment.

As shown in FIG. 7, the steady state value or the current state value can be represented by a graph in which the X axis is the Safe Distance and the Y axis is the Temporal Period. (Drowsy State, 712) corresponding to the operation region and the control period operated by the driver in the drowsy state is larger than the normal state (Normal State, 711) corresponding to the safe region and the control period learned in the normal state .

The drowsy state determination apparatus 100 multiplies the longitudinal drowsiness index x and the lateral drowsiness index y by the weighting factors a and b to calculate the final drowsiness index z, It is derived according to the index calculation formula z = ax + by. The drowsiness state determination apparatus 100 can derive the normal drowsiness index during normal driving and the current drowsiness index during the current driving according to the drowsiness index calculation formula z = ax + by. Here, the longitudinal drowsiness index (x) can be calculated as the value obtained by multiplying the magnitude of the longitudinal safety zone and the control period, or a sum thereof. In addition, the transverse drowsiness index (y) can be calculated as the value multiplied by the magnitude of the lateral safety zone and the control period or a sum thereof.

The process of determining the drowsiness state will be described as an example. When the longitudinal drowsiness index during normal driving is designated as x and the lateral drowsiness index is designated as y, the drowsiness index z at normal driving is derived as ax + by. Also, when the longitudinal drowsiness index at the time of the current driving is designated as x 'and the lateral drowsiness index is designated as y', the drowsiness index z 'at the present driving is derived as ax' + by '. Then, the drowsiness state determination apparatus 100 compares the drowsiness index z 'at the time of current driving with the drowsiness index z at the time of normal driving, and compares the index value at which the drowsiness index z' , The abnormal value can be calculated as 60%, 75%, or 90% or more.

As described above, the drowsy state determination apparatus 100 can variably determine the longitudinal coefficient a and the lateral coefficient b, which are weights, according to the current driving situation.

When the drowsy operation is judged by using merely the error value, the driver characteristic such as shifting to one side is judged as an abnormal state. However, the drowsiness state determination apparatus 100 according to an embodiment of the present invention can solve such a problem by determining the drowsiness by extracting the usual driving pattern of the driver.

As described above, the drowsiness state determination apparatus 100 according to an embodiment of the present invention can be easily applied by determining the drowsiness state of a driver by fusing technologies that are actually being commercialized, thereby reducing the drowsiness driving traffic accident rate.

8 is a flowchart illustrating a method of determining a sleeping state of a vehicle driver according to an embodiment of the present invention.

In step S101, the drowsiness state determination device 100 determines the running state of the vehicle based on the vehicle speed or the navigation position information. The drowsy state determination apparatus 100 determines a driving situation in which the driver is driving in a city, a highway, or a stagnation road based on the current driving speed of the vehicle, or the starting period after the stoppage. In the case of a vehicle equipped with an interlocking navigation system, the drowsiness state determination apparatus 100 can improve the accuracy of the driving situation determination by utilizing the position information provided in the navigation system or the average moving speed of the current road.

In step S102, the drowsy state determination apparatus 100 learns the driving pattern of the driver for a predetermined time (e.g., five minutes). At this time, the drowsy state determination apparatus 100 learns the driving pattern of the driver and can derive the magnitude and the control period of the longitudinal and lateral safety zones.

In step S103, the drowsiness state determination apparatus 100 determines the drowsiness state of the real-time driver at the time of present driving. The drowsy state determination apparatus 100 collects the longitudinal and lateral direction running patterns of the driver for a predetermined period of time (for example, a recommended period of 5 minutes) during normal driving, calculates a normal drowsiness index as a standard drowsiness index calculation expression z = ax + It can be derived by. Where x is the longitudinal normal drowsiness index and y is the transverse normal drowsiness index. In this case, the longitudinal and lateral coefficients a and b multiplied respectively by the longitudinal and transverse drowsiness indexes of the normal drowsiness index can be variably applied based on the driving situation judged at the step S101. For example, when it is difficult to keep the distance from the vehicle ahead constant, such as a congestion road, the drowsy state determination apparatus 100 may decrease the value of the longitudinal coefficient a. Or when it is difficult to run straight, such as a road or a curve without a lane, the drowsy state determination apparatus 100 may reduce the value of the lateral coefficient b.

If it is determined in step S104 that the real time driver is in a drowsy state at the time of the current driving, the drowsiness state determination apparatus 100 generates a warning according to the weight of the outliers. For example, the drowsiness state determination apparatus 100 can analyze a driving pattern of a predetermined time (for example, one minute in the past) based on the learned driver driving pattern and display a warning icon in the cluster when the abnormal value is 60% or more. Alternatively, the drowsiness determination device 100 may generate a warning sound when the abnormality value is 75% or more. Alternatively, the sleeping state determining apparatus 100 can vibrate the diaphragm provided on the seat when the abnormality value is 90% or more. The drowsiness state determination apparatus 100 can transmit a dangerous situation to the driver in a manner corresponding to each of the outliers. The kind, strength, or intensity of the warning is not limited to a specific warning, and may be changed.

On the other hand, if it is determined that the real time driver is not in the drowsy state at the time of the current driving (S103), the drowsiness state determination apparatus 100 can perform the operation from step S103 to determine the drowsiness state of the real time driver.

Thereafter, in step S105, the drowsy state determination apparatus 100 confirms whether there is a change in driving condition or a driver input.

If it is determined in step S105 that there is a change in driving condition or a driver input, the sleeping state determination apparatus 100 performs the process again from step S101 in which the driving state of the vehicle is determined based on the vehicle speed or the navigation position information. If the drowsiness state determination device 100 has to search for a drowsiness index that is a standard because there is a sudden change in the driving situation such as a stagnation situation on a highway or when the driver shows a correction intention through a button input on the vehicle It is possible to re-start from the step S101 which is the initial driving situation judging step.

On the other hand, if it is determined in step S105 that there is no change in driving condition or in the absence of a driver input, the drowsiness state determination apparatus 100 returns from step S103 to determine the drowsiness state of the real time driver.

The method for determining the drowsiness state of the vehicle driver according to the embodiments of the present invention described above can be implemented as a computer readable code on a computer readable recording medium. An automated digital analysis method in accordance with embodiments of the present invention is a computer-readable storage medium including instructions executable by a processor, the instructions causing the processor to perform at least one of a running pattern in a longitudinal direction and a lateral direction Calculating a normal drowsiness index as a criterion for determining a drowsiness state; calculating a current drowsiness index representing a drowsiness characteristic of a current driver by collecting driving patterns in a longitudinal direction and a lateral direction of the driver at the time of present driving; Determining a drowsiness state of the driver by analyzing the calculated current drowsiness index based on the calculated normal drowsiness index and generating a drowsiness driving warning to the driver when it is determined that the driving pattern of the driver is a drowsiness operation, Readable < / RTI > storage medium.

The computer-readable recording medium includes all kinds of recording media storing data that can be decoded by a computer system. For example, there may be a ROM (Read Only Memory), a RAM (Random Access Memory), a magnetic tape, a magnetic disk, a flash memory, an optical data storage device and the like. The computer-readable recording medium may also be distributed and executed in a computer system connected to a computer network and stored and executed as a code that can be read in a distributed manner.

It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit or scope of the invention as defined by the appended claims. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention.

In particular, the described features may be implemented within digital electronic circuitry, or computer hardware, firmware, or combinations thereof. The features may be implemented in a computer program product embodied in a storage device in a machine-readable storage device, for example, for execution by a programmable processor. And the features may be performed by a programmable processor executing a program of instructions for performing the functions of the described embodiments by operating on input data and generating an output. The described features include at least one programmable processor, at least one input device, and at least one output device, coupled to receive data and directives from a data storage system and to transmit data and directives to a data storage system, Such as a computer-readable recording medium. A computer program includes a set of directives that can be used directly or indirectly within a computer to perform a particular operation on a given result. A computer program may be written in any form of programming language including compiled or interpreted languages and may be implemented as a module, element, subroutine, or other unit suitable for use in other computer environments, or as a standalone program Can be used.

Suitable processors for execution of the program of instructions include, for example, both general purpose and special purpose microprocessors, and one of multiple processors of a single processor or other type of computer. Also, storage devices suitable for implementing the computer program instructions and data embodying the described features may be embodied in a computer-readable medium, such as, for example, semiconductor memory devices such as EPROM, EEPROM, and flash memory devices, Devices, magneto-optical disks, and non-volatile memory including CD-ROM and DVD-ROM disks. The processor and memory may be integrated within application-specific integrated circuits (ASICs) or added by ASICs.

While the invention has been shown and described with reference to certain preferred embodiments thereof, it will be understood by those of ordinary skill in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. It will be apparent to one skilled in the art to which the present invention pertains.

The combination of the above-described embodiments is not limited to the above-described embodiments, and various combinations and combinations of the above-described embodiments as well as the implementation and / or the necessity may be provided.

In the above-described embodiments, the methods are described on the basis of a flowchart as a series of steps or blocks, but the present invention is not limited to the order of steps, and some steps may occur in different orders or in a different order than the steps described above have. It will also be understood by those skilled in the art that the steps depicted in the flowchart illustrations are not exclusive and that other steps may be included or that one or more steps in the flowchart may be deleted without affecting the scope of the invention You will understand.

The foregoing embodiments include examples of various aspects. While it is not possible to describe every possible combination for expressing various aspects, one of ordinary skill in the art will recognize that other combinations are possible. Accordingly, it is intended that the invention include all alternatives, modifications and variations that fall within the scope of the following claims.

It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit or scope of the inventions as defined by the following claims It will be understood that various modifications and changes may be made thereto without departing from the spirit and scope of the invention.

100: Drowsiness judgment device
110:
120: travel pattern learning unit
130: drowsy state judging unit
140:
150: Input /

Claims (20)

A method for determining a drowsy state of a vehicle driver performed by a drowsiness state determination device,
Calculating a normal drowsiness index as a reference for determining a drowsiness state by learning a driving pattern in a longitudinal direction and a lateral direction of the driver during normal driving;
The driving pattern of the driver in the longitudinal direction and the lateral direction of the driver is collected to calculate the current drowsiness index indicating the drowsiness characteristic of the current driver and the calculated current drowsiness index is analyzed based on the calculated normal drowsiness index, Determining a drowsy state of the subject; And
And generating a drowsy driving warning to the driver when the driving pattern of the driver is determined to be a drowsy driving mode. The method according to claim 1,
Further comprising the step of determining a running condition based on the running speed or the position information of the vehicle. 3. The method of claim 2,
The step of determining the running condition may include:
And determining the driving state of the vehicle driver based on the position information provided by the navigation or the moving speed of the current road when navigation capable of interlocking with the vehicle is mounted. 3. The method of claim 2,
The step of determining the running condition may include:
Wherein the driving condition determining unit determines that the driving situation is any one of a city driving, a highway driving, and a congested road driving. 3. The method of claim 2,
Further comprising the step of re-learning the longitudinal and lateral direction travel patterns and restoring the normal drowsiness index when the determined travel condition exceeds the predetermined travel condition change amount or there is a re-search request from the driver, How to determine drowsiness. The method according to claim 1,
Wherein calculating the normal drowsiness index comprises:
A method for determining a drowsiness state of a driver who calculates a normal drowsiness index using a size and a control period of a safety zone set from a driving pattern of a driver in a longitudinal direction and a lateral direction during normal driving. The method according to claim 6,
Wherein calculating the normal drowsiness index comprises:
A longitudinal error value and a longitudinal control period at the time when the sign of the relative speed between the preceding vehicle and the vehicle are changed, a lateral error value at the time when the sign of the vehicle steering angular velocity operated by the vehicle driver is changed, To determine a sleeping state of a vehicle driver who sets a safe zone and a control period. The method according to claim 1,
The step of determining the drowsy state of the driver includes:
A drowsiness state of a vehicle driver calculating the present drowsiness index by adding the drowsiness index multiplied by the longitudinal and transverse coefficients to the longitudinal and transverse drowsiness indexes derived from the driving patterns of the driver in the longitudinal and lateral directions at the time of present driving, How to judge. 9. The method of claim 8,
The step of determining the drowsy state of the driver includes:
And determining the drowsy state of the vehicle driver to vary the longitudinal and lateral coefficients according to the current driving situation. The method according to claim 1,
The generating of the alert may comprise:
As a result of analyzing the calculated current drowsiness index on the basis of the calculated normal drowsiness index, it is possible to display a warning icon on the vehicle cluster, generate a warning sound or vibrate the diaphragm installed on the vehicle seat, A method of determining a driver 's drowsy state. A traveling pattern learning unit for calculating a normal drowsiness index as a reference for determining a drowsy state by learning a traveling pattern in a longitudinal direction and a lateral direction of the driver during normal traveling;
The driving pattern of the driver in the longitudinal direction and the lateral direction of the driver is collected to calculate the current drowsiness index indicating the drowsiness characteristic of the current driver and the calculated current drowsiness index is analyzed based on the calculated normal drowsiness index, A drowsy state determination unit for determining a drowsy state of the subject; And
And an alarm generating unit for generating a warning signal for driving the sleeping driver when the driving pattern of the driver is determined to be a sleeping driving operation. 12. The method of claim 11,
And a traveling state determining unit for determining the traveling state based on the traveling speed or the position information of the vehicle. 13. The method of claim 12,
The traveling condition judging unit judges,
Wherein the driving state determining unit determines the driving state of the vehicle driver based on the position information provided by the navigation system or the traveling speed of the current road when the navigation system is interlocked with the vehicle. 13. The method of claim 12,
The traveling condition judging unit judges,
Wherein the driving state determining unit determines that the driving state of the vehicle driver is any one of driving in the city, highway driving, and congestion road driving. 13. The method of claim 12,
The traveling pattern learning unit
Wherein the sleeping state determining device determines the sleepiness state of the vehicle driver when the determined traveling state exceeds the predetermined traveling state change amount or when there is a request for re-searching from the driver, re-learning the traveling pattern in the longitudinal and lateral directions to ship the normal drowsiness index. 13. The method of claim 12,
The traveling pattern learning unit
Wherein the normal drowsiness index is calculated using the size and the control period of the safety zone set from the driving pattern of the driver in the longitudinal direction and the lateral direction at the time of normal driving. 13. The method of claim 12,
The traveling pattern learning unit
A longitudinal error value and a longitudinal control period at the time when the sign of the relative speed between the preceding vehicle and the vehicle are changed, a lateral error value at the time when the sign of the vehicle steering angular velocity operated by the vehicle driver is changed, To determine a sleeping state of the vehicle driver who sets the safety zone and the control period. 13. The method of claim 12,
The drowsy state determination unit may determine,
A drowsiness state of a vehicle driver calculating the present drowsiness index by adding the drowsiness index multiplied by the longitudinal and transverse coefficients to the longitudinal and transverse drowsiness indexes derived from the driving patterns of the driver in the longitudinal and lateral directions at the time of present driving, Determination device. 19. The method of claim 18,
The drowsy state determination unit may determine,
Wherein the driver determines the drowsy state of the vehicle driver by varying the longitudinal and lateral coefficients according to the determined driving situation. 12. The method of claim 11,
Wherein the warning generating unit includes:
As a result of analyzing the calculated current drowsiness index on the basis of the calculated normal drowsiness index, it is possible to display a warning icon on the vehicle cluster, generate a warning sound or vibrate the diaphragm installed on the vehicle seat, A device for determining the sleepiness of a driver.

Images