KR102226842B1 - Estimation System of Driver's Danger Level - Google Patents

Abstract

The present invention relates to a system for estimating a driver's risk installed in a vehicle. An information processing unit that receives detection signal information according to the behavior of a part of the driver's body from the sensing unit, and derives a driver's risk according to the behavior based on the sensing signal information; A storage unit for storing comprehensive driving risk information on a driver generated by the information processing unit under the control of the information processing unit; And an alarm unit that provides an alarm to the driver according to the control of the information processing unit so that the driver can recognize when the driver's risk is higher than a preset alarm threshold value. Thus, a technology that can contribute to the driver's safe driving is disclosed.

Description

Estimation System of Driver's Danger Level}

The present invention relates to a driver risk estimation system for deriving a risk according to the behavior of a driver driving a vehicle.

As automobiles are widely distributed, they are becoming a representative means of transportation that can be used usefully. However, there are also safety issues, such as serious injuries or deaths of many people around the world due to vehicle traffic accidents.

There are various causes of traffic accidents such as drunk driving, drowsy driving, dangerous driving habits, and speeding. A lot of research is being conducted on technologies to prevent the occurrence of traffic accidents by reducing these causes.

Conventional techniques related to this mainly focus on reducing the risk of traffic accidents that may occur due to speeding or limited visibility, or Korean Patent Laid-Open No. 10-2010-0028253 (Name of invention: driving assist device and driving assist method ), a number of technologies to prevent the driver's drowsy driving by judging whether the driver is drowsy have been proposed.

However, since traffic accidents sometimes occur according to the driver's driving habits, especially the driver's movement while driving, there is also a need for a technology capable of lowering the possibility of accidents due to the driver's behavior.

Korean Patent Registration No. 10-2010-0028253

An object of the present invention is to solve the conventional problems as described above, and to provide a driver risk estimation system capable of deriving and estimating the risk according to the behavior of a driver driving a vehicle.

A driver risk estimation system according to an embodiment of the present invention for achieving the above object is a system installed in a vehicle to obtain information on a driver, comprising: a sensing unit detecting a behavior of a body part of a driver who is driving the vehicle; An information processing unit that receives detection signal information according to the behavior from the detection unit and derives a driver's risk level of the driver based on the detection signal information; A storage unit for storing the driver's risk level under the control of the information processing unit; And an alarm unit configured to provide an alarm to the driver according to the control of the information processing unit so that the driver can recognize when the driver's risk level is higher than a preset alarm threshold value by the information processing unit. You may.

Here, the driver's risk may include a risk according to the degree of the behavior and a risk according to a behavior time, which is a duration of the behavior.

Here, the sensing unit is disposed in the center console in the vehicle and senses a distance between the moving body part of the driver and the center console, and the risk according to the degree of the behavior is determined by the body part of the driver and the Another feature is that it is derived differently depending on the distance between the center consoles.

Here, the information processing unit measures the duration of the behavior when the sensing signal information detected that the distance between the driver's body part and the center console is within a reference distance is transmitted from the sensing unit. You may.

Here, the information processing unit calculates the risk according to the movement time in proportion to the measured movement time, and derives the driver risk by synthesizing the risk according to the level of the movement and the risk according to the movement time. It can also be a feature.

Here, the information processing unit may be further characterized by deriving the driver's risk of the driver by using linear regression analysis.

Here, the driver's risk estimation system includes: a driving information collecting unit collecting driving information on a driving state of the vehicle and transmitting it to the information processing unit; It may be another feature that further includes.

Here, the driving information may include at least one or more of driving route information, driving speed information, and driving time information of the vehicle.

In this case, the information processing unit is further characterized in that the driver's risk and the driving information are matched based on time to derive comprehensive driving risk information, and store the driving risk total information in the storage unit. May be.

In this case, the driver risk estimation system may further include an output unit for providing the driver's driver risk level or the total driving risk information stored in the storage unit to the outside.

Here, it may be another feature that the sensing unit includes a non-contact sensor for non-contact sensing the behavior of a part of the driver's body.

Here, the non-contact sensor may be an infrared sensor capable of detecting a distance using infrared rays.

Here, the infrared sensor may be installed in a plurality of the center console in the vehicle to detect the behavior of the driver's body part may be another feature.

Since the driver risk estimation system according to the present invention can derive and provide the driver with the driving risk of the driver while the vehicle is running, it has the effect of reducing the risk of traffic accidents by inducing the driver to promote safe driving. have.

1 is a block diagram schematically showing a system for estimating a driver's risk according to an embodiment of the present invention.
2 is an image showing an exemplary form in which the infrared sensor of the driver's risk estimation system according to an embodiment of the present invention is experimentally disposed on a center console of a vehicle.
3 is a graph schematically showing an analog output voltage according to a sensing distance of an infrared sensor in the driver's risk estimation system according to an embodiment of the present invention.
4 is a diagram schematically illustrating a process of estimating a driver's risk in a driver's risk estimation system according to an embodiment of the present invention.

Hereinafter, a preferred embodiment will be described with reference to the accompanying drawings so that the present invention may be more specifically understood.

1 is a block diagram schematically showing a system for estimating a driver's risk according to an embodiment of the present invention.

Referring to FIG. 1, a driver risk estimation system 100 according to an embodiment of the present invention is installed in a vehicle to obtain information on a driver, and a detection unit 110, an information processing unit 120, and a storage unit 130 And an alarm unit 150, and preferably, a driving information collection unit 140 and an output unit 160 may be further included.

The sensing unit 110 detects the behavior of a part of the body of a driver driving the vehicle.

It is preferable that the sensing unit 110 includes a non-contact sensing sensor that detects the behavior of a part of the body of the driver while driving. As a preferred non-contact sensor, an infrared sensor capable of detecting a distance using infrared rays can be heard.

Here, further reference is made to FIG. 2. FIG. 2 is an image schematically showing an infrared sensor in a driver's risk estimation system according to an embodiment of the present invention, which is experimentally arranged in a center console in a vehicle.

As shown in FIG. 2, as a preferred mounting type of the sensing unit 110, a plurality of infrared sensors are mounted on a center console in which an air conditioner control panel or an audio control panel is provided in a vehicle to control the behavior of a part of the driver's body. You can hear what you can detect.

When the driver who is driving the vehicle makes a behavior of bringing a body part, such as a hand, to the center console, the infrared sensor, which is the sensing unit 110, detects the distance between the driver's hand and obtains detection signal information.

Referring further to FIG. 3, FIG. 3 is a graph showing the detection signal of the infrared sensor according to the distance between the infrared sensor arranged as in FIG. 2 and the driver's hand in the driver's risk estimation system according to an embodiment of the present invention. Is shown.

As shown in FIG. 3, when the driver's hand approaches within a predetermined reference distance from the center console equipped with the infrared sensor, it is preferable that the infrared sensor detects it and measures the distance to the hand to obtain the detection signal information. .

Here, since the infrared sensor is mounted on the center console, the distance sensed by the infrared sensor can be said to be the distance between the center console and the driver's hand. The sensing signal information obtained by sensing by the infrared sensor of the sensing unit 110 is transmitted to the information processing unit 120.

The driving information collecting unit 140 collects driving information, which is information on the driving state of the vehicle, and transmits the collected driving information to the information processing unit 120.

Here, the driving information is information on a state in which the vehicle is running, and preferably includes at least one of driving route information, driving speed information, and driving time information of the vehicle.

The driving route information includes cornering driving information such as left-turning or right-turning driving, and straight-line driving information. The cornering driving information preferably includes information such as an angle at which the driver rotates the steering wheel left or right or the angle at which the steering wheel is steered for cornering driving.

When the driving route information and the detection signal information are matched to correspond to each other based on time, it is possible to derive the risk of the driver according to the driving direction of the vehicle. E.g. It is preferable because it is possible to grasp how long the driver's behavior has been performed during the cornering driving of the vehicle.

Even if the driver's behavior is performed for the same amount of time, it is desirable because it can be derived by varying the degree of risk depending on whether the driving state of the vehicle was driving on a straight path or cornering when the driver's hand approaches the center console.

Since it is more dangerous for the driver's hand to approach the center console during cornering compared to straight driving, it is desirable that the risk for the behavior of a part of the driver's body during cornering is evaluated relatively higher.

The driving speed information refers to information on the speed of the vehicle. Matching so as to correspond to the detection signal information based on time allows the vehicle speed to be known when the driver's behavior is detected. In addition, it is possible to determine the vehicle's speed during the duration of the driver's movement. If the detection signal information and the driving speed information are matched based on time as described above, it is preferable that the vehicle speed and the risk according to the driver's behavior can be distinguished and determined.

For example, when the motion of the driver's hand approaching the center console is detected 30 minutes after the start of the vehicle, the vehicle speed is determined to be 30 km/h or 100 km/h. It is desirable because it can be judged differently.

The driving time information includes a time when driving of the vehicle is started, a time when driving of the vehicle is ended, and a total driving time, and refers to time information related to vehicle driving. It is preferable because it is possible to identify the driver's risk by matching the driving information with the detection signal information based on the driving time information.

In addition, it is possible to know whether the vehicle was driven during the day or at night through the driving time information. Even if the driver's behavior during driving is the same, the driver's risk at night may be determined to be relatively higher than the driver's risk during the day.

In this way, the driving information collection unit 140 collects driving information on the driving state of the vehicle and transmits it to the information processing unit 120. The driving information is synthesized with the driver's risk in the information processing unit 120 to be described later, and is included in the driving risk comprehensive information.

The information processing unit 120 receives sensing signal information according to the driver's behavior from the sensing unit, and derives a driver's risk according to the driver's behavior based on the sensing signal information.

During vehicle operation, the infrared sensor detects that a part of the body such as the driver's hand, such as the driver's hand, is within a predetermined reference distance, thereby obtaining detection signal information.

Then, the sensing signal information obtained from the infrared sensor is transmitted to the information processing unit 120. The information processing unit 120 receiving the detection signal information measures the behavior time.

In addition, the information processing unit 120 estimates the driver's risk of the driver using linear regression analysis.

The information processing unit 120 matches the driving information collected by the driving information collection unit 140 and the detection signal information acquired by the detection unit 110 in correspondence with each other based on time, and reflects it in the derivation of the driver's risk of the driver. Or include it in the comprehensive driving risk information.

The comprehensive driving risk information includes detection signal information or driver risk of the driver. That is, the comprehensive driving risk information may be referred to as information including detection signal information, driver risk, and driving information.

The information processing unit 120 deriving the driver's risk based on the detection signal information will be described in more detail after mentioning the storage unit 130, the alarm unit 150, and the output unit 160.

The storage unit 130 stores the driver's risk level for a driver generated by the information processing unit 120 or comprehensive driving risk information including the same, according to the control of the information processing unit 130.

The storage unit 130 may provide the information processing unit 130 with various types of information, such as comprehensive driving risk information or driver risk, stored in the storage unit 130 under the control of the information processing unit 130.

The alarm unit 150 provides an alarm to the driver according to the control of the information processing unit when the driver's risk of the driving driver is more than the alarm threshold value.

It is also desirable to provide an alarm to the driver through the alarm unit 150 when the driver's risk is greater than a predetermined alarm threshold while the information processing unit determines the driver's risk in real time to induce safe driving of the driver.

It is also possible to provide an alarm to the driver by sound, such as a speaker, or to provide an alarm to the user visually through a display device such as an LED lamp or an LCD screen.

The output unit 160 is provided to provide the driver's driver risk level or comprehensive driving risk information stored in the storage unit 130 to the outside.

As an example of the output unit 160, there may be an output terminal such as a memory or a USB port provided to transmit and receive information to and from an external terminal, and a monitor that displays the driver's risk or comprehensive driving risk information visually. There may be the same display device.

Derivation of the driver's risk using the driver's risk estimation system 10 may be performed as follows.

4 is a diagram schematically illustrating derivation of a driver's risk of a driver using a driver risk estimation system according to an embodiment of the present invention.

As shown in FIG. 4, it can be obtained by measuring the distance and time of movement between the infrared sensor disposed on the center console of the vehicle and the driver's hand. In FIG. 4, N may be referred to as the total number of measured data, and this may be collectively referred to as frame data.

The detection signal information obtained from the infrared sensor is preferably noise removed through a filter in order to ensure accuracy.

Based on the detection signal information obtained from the infrared sensor, linear regression analysis is performed to calculate the linear regression coefficient and the driver's driver risk is estimated.

The process of deriving the driver's risk is as follows.

After the sensing signal information is collected, linear regression analysis can be applied to derive the distance between the driver's hand and the infrared sensor installed in the vehicle's center console and the driver's risk during the driving time.

Linear regression analysis can be classified into simple linear regression analysis with one predictor and multiple linear regression analysis with several predictors. In an embodiment, since several predictor variables may be considered, multiple linear regression analysis may be used.

The following linear regression analysis equation can be used to derive the driver's risk.

,

및

은 각기 운전자의 손과 적외선센서 IR1, IR2 및 IR3 사이의 거리를 나타낸다. here,

,

And

Represents the distance between the driver's hand and the infrared sensors IR1, IR2 and IR3 respectively.

은 운전자의 손과 3개의 적외선센서 IR1, IR2 및 IR3 각각의 사이에서 거동시간(time of movement)을 나타낸다.

Represents the time of movement between the driver's hand and each of the three infrared sensors IR1, IR2 and IR3.

는 선형회귀분석에 의해 추정된 선형회귀분석의 계수를 나타낸다.And, ev represents the derived driver's driver risk.

Denotes the coefficients of linear regression analysis estimated by linear regression analysis.

The linear regression analysis used in this embodiment shows how close the linear relationship is between the four predictor variables.

1st infrared sensor sensing distance

2nd infrared sensor sensing distance

3rd infrared sensor sensing distance

Operating time

Driver risk as a response variable

는 추정변수 u에 대한 응답변수인 운전자위험도 ev의 다중선형회귀분석에 대한 선형회귀계수의 도출된 추정값을 나타낸다. 추정변수는 운전자의 손과 3개의 적외선센서 사이의 거리 및 시간을 나타내고, 응답변수 ev는 운전자위험도이다.

Represents the derived estimate of the linear regression coefficient for the multiple linear regression analysis of the driver's risk ev, which is the response variable to the estimated variable u. The estimated variable represents the distance and time between the driver's hand and the three infrared sensors, and the response variable ev is the driver's risk.

를 기반으로, 운전자의 손과 3개의 적외선센서 사이의 거리 및 거동시간(time of movement)으로 구성된 프레임데이터에 대한 운전자위험도 값이 도출된다.The linear regression coefficient calculated in this process,

Based on, the driver's risk value for the frame data consisting of the distance between the driver's hand and the three infrared sensors and the time of movement is derived.

As such, the driver's risk can be derived from the distance and movement time between the driver's hand and the three infrared sensors of the center console.

It can be defined as "safe" if the driver's hand is not close to the center console. Also, the reference value of "safe" is set to zero. In addition, if the driver's hand is closer to the center console than the preset reference value, it may be defined as "danger".

The value for the driver's risk can be defined by taking into account the time of movement between the driver's hand and the center console. The longer the movement time between the driver's hand and the center console, the higher the driver's risk. In other words, the shorter the driving time, the lower the driver's risk.

Therefore, the reference value for the movement time can be defined as a value that increases by 0.1 in proportion to the driver's risk, assuming that the time increases every 0.2 seconds (5 frames/second).

The value for the driver's risk is determined in consideration of the distance between the driver's hand and the center console. The closer the distance between the driver's hand and the center console, the higher the driver's risk. On the other hand, the further the driver's hand is away from the center console, the lower the driver's risk.

Since the driver's risk is inversely proportional to the distance, the reference value of the distance can be defined as (1 / distance). Therefore, the reference value for the driver's risk, which combines distance and travel time, can be defined as a value obtained by multiplying the increasing time by 0.1 and adding (1 / distance) to the number of data.

For example, if the distance between the driver's hand and the infrared sensor <1> is 4 cm and the measured time is 0.2 seconds, the driver's risk according to the movement time is 0.1, and the distance between the driver's hand and the infrared sensor The resulting driver's risk is 0.25, which is the reciprocal of 4.

Therefore, by adding the risk according to the driving time and the risk according to the distance, the overall driver risk becomes 0.35.

Comprehensive driver risk can be derived by adding the risk according to the distance to the risk according to the driving time.

It is also desirable to set the alarm alarm to be made when the driver's risk is higher than the alarm threshold. For example, when the alarm reference value is set to 0.4 and the driver's risk is estimated to be 0.45, which is greater than 0.4, the information processing unit 120 provides an alarm to the driver through the alarm unit 150.

Providing an alarm like this is desirable because it induces the driver to immediately drive safely.

As described above, the driver risk estimation system according to the present invention can estimate the driver risk of the driver while the vehicle is running and provide it to the driver, thereby promoting the driver's safe driving and reducing the risk of traffic accidents. There is an advantage.

As described above, a detailed description of the present invention has been made by the embodiments with reference to the accompanying drawings, but the above-described embodiments are only described with reference to the preferred embodiments of the present invention. It should not be understood as being limited only to the embodiments, and the scope of the present invention should be understood as the claims and equivalent concepts to be described later.

100: driver risk estimation system
110: sensing unit 120: information processing unit
130: storage unit 140: operation information collection unit
150: alarm unit 160: output unit

Claims (13)

As a system installed in the vehicle to acquire information about the driver,
A sensing unit that detects a behavior of a body part of a driver while driving the vehicle;
The detection signal information according to the behavior is received from the sensing unit, and based on the detection signal information, the risk according to the degree of the driver's behavior and the risk according to the behavior time, which is the duration of the behavior, are synthesized to calculate the driver's risk. An information processing unit to derive;
A storage unit for storing the driver's risk level under the control of the information processing unit; And
An alarm unit configured to provide an alarm to the driver according to the control of the information processing unit so that the driver can recognize when the driver's risk level is greater than or equal to a preset alarm threshold value by the information processing unit; And
Includes; a driving information collection unit for collecting driving information on the driving state of the vehicle and transmitting it to the information processing unit,
The information processing unit,
Comprehensive driving risk information is derived by matching the driver risk and the driving information based on time, but based on the driving information, the risk of the driver's behavior during cornering driving is evaluated relatively higher than that of straight driving. , Judging the driver's risk at night relatively higher than the driver's risk at daytime,
The sensing unit,
It is arranged in the center console in the vehicle and detects the distance between the moving body part of the driver and the center console,
The degree of risk according to the degree of the above behavior is,
It is derived differently according to the distance between the driver's body part and the center console,
The information processing unit,
When the sensing signal information detected that the distance between the driver's body part and the center console is within a reference distance is transmitted from the sensing unit, the movement time is measured,
In the driving information, the risk of the driver's behavior is evaluated based on the driving speed information of the vehicle corresponding to the driving time, and the driver's risk is determined differently according to the driving speed information,
Driver risk estimation system.
delete delete delete delete The method of claim 1,
The information processing unit is characterized in that to derive the driver's risk of the driver using linear regression analysis,
Driver risk estimation system.
delete delete The method of claim 1,
The information processing unit,
Comprehensive driving risk information is derived by matching the driver risk and the driving information based on time,
Characterized in that storing the driving risk comprehensive information in the storage unit,
Driver risk estimation system.
The method of claim 9,
The driver risk estimation system,
Characterized in that it further comprises an output unit for providing the driver's driver risk level or the driving risk total information stored in the storage unit to the outside;
Driver risk estimation system.
The method of claim 10,
The sensing unit, characterized in that it comprises a non-contact sensor for sensing the behavior of the driver's body part in a non-contact manner,
Driver risk estimation system.
The method of claim 11,
The non-contact sensor is characterized in that it is an infrared sensor capable of detecting a distance using infrared,
Driver risk estimation system.
The method of claim 12,
The infrared sensor,
A plurality of units are mounted on the center console in the vehicle to detect the behavior of a part of the driver's body,
Driver risk estimation system.

Images