KR102403887B1 - System and method for protecting drowsy driving - Google Patents

Abstract

Disclosed are a system for preventing drowsiness of a driver and a method for preventing drowsiness of a driver. The present invention includes: an image acquiring unit acquiring a face image of a driver; a sever receiving the image and acquiring information on a drowsy state of the driver based on the image; a speaker outputting an alarm according to the drowsy state of the driver; and an input device in which predetermined input for turning off the alarm is input. The server can receive the predetermined input from the input device and control the alarm of the speaker to be turned off according to the predetermined input.

Description

Drowsy driving prevention system and method

The present invention relates to a system for preventing drowsy driving and a method therefor. More particularly, it relates to a drowsy driving prevention system and method for detecting a drowsy state by analyzing a driver's facial expression based on deep learning, and preventing the driver from drowsiness by using a unique input device of the present invention.

An automobile may be classified into an internal combustion engine automobile, an external combustion engine automobile, a gas turbine automobile, an electric vehicle, or the like, according to a type of a prime mover used.

Also, as is well known, drowsy driving has already increased its proportion and accounts for the largest portion of the cause of vehicle accidents, and many studies are being conducted to prevent this. Drowsy driving is an important cause of traffic accidents, and 36% of fatal traffic accidents and 43 to 54% of all traffic accidents are due to drowsy driving. Accordingly, a system for preventing the driver from drowsiness by detecting the driver's drowsiness is a very important technology for reducing traffic accidents. In addition, accidents due to drowsy driving in Korea continue to occur as shown below.

year 2014 2015 2016 Accident (case) 2426 2701 2433 death (persons) 130 108 98 Injuries (persons) 4679 5525 4899

In order to prevent the driver from drowsiness, there are traditional methods of detecting the driver's condition. Traditional methods can be broadly classified into three types.

First, there is a method of judging the driver's condition by observing the change of the vehicle. A typical example is a method that generates an alarm when the lane departure condition continues for a certain period of time but crosses a lane without a lane change signal.

Second, there is a method of recognizing the driver's condition based on physiological data such as the driver's brain waves and heartbeat. Although this method has high accuracy as it is medically used to treat drowsiness-related patients, it is difficult to apply in the real world because it is difficult to observe the change by wearing a measuring device to the driver.

These traditional methods have limitations in deriving a generalized drowsiness detection model because they do not reflect all the different characteristics of drivers.

In particular, Korean Patent No. 209610 discloses a device for preventing drowsiness using an EEG signal, but there is a problem that the installation of sensors for detecting EEG and heart rate may cause the driver to become sensitive as he/she receives the consciousness to be managed. Accordingly, there is a need for a method for detecting drowsiness in a situation in which the driver is not aware and for preventing the driver from drowsiness more effectively.

Also, the input device may be a communication means between the device and the user. The input device may include not only basic devices such as a mouse and keyboard, but also all devices using various principles such as gesture recognition and voice recognition. A keyboard, which is generally used as an input device, is simply operated by the principle of a switch. In other words, it follows the binary information input method using the simple principle that current flows when the switch is pressed and on the contrary, no current flows when the switch is not pressed.

In addition, in the case of the keyboard, there were disadvantages such as reduced mobility of the mobile device and a low recognition rate.

Recently, a ubiquitous computing technology called a wearable smart device or a wearable computer has emerged. These technologies could help make computers part of the human body by making them wearable like clothes or glasses. From the viewpoint of a wearable computer, development of an input device capable of more conveniently typing or inputting data is required.

In response to this demand, the conventional wearable input device using a finger generates input information differently and uses it as input information according to the motion of the finger or the location where the finger touches. It was a method in which a character was input by touching a specific part and using the corresponding gesture or input information assigned to the part of the body. In this case, when a specific gesture could not be properly recognized or a specific body part could not be touched, proper input information could not be generated. Accordingly, the need for a wearable keyboard with good mobility and convenient typing has increased.

As such, there is a need for various means for enabling the driver to wake up by providing feedback through the wearable keyboard as well as an effective means for detecting the driver's drowsiness.

KR 100209610 B1 KR 101416522 B1 JP 2000330692 A

SUMMARY OF THE INVENTION It is an object of the present invention to propose a system for preventing drowsy driving and a method therefor to solve the above problems.

Another object of the present invention is to more efficiently detect a driver's drowsiness state by using deep learning.

Another object of the present invention is to more effectively prevent a driver from drowsy driving by utilizing an input device unique to the present invention.

In order to solve the above problems, the present invention provides an image acquisition unit for acquiring an image of a driver's face, a server for receiving the image, and acquiring information on the drowsiness state of the driver based on the image, A speaker for outputting an alarm according to a drowsy state and an input device to which a predetermined input is input to turn off the alarm, wherein the server receives the predetermined input from the input device, and the predetermined input Accordingly, it is possible to control to turn off the alarm of the speaker.

Also, the server may extract a feature point for the face of the driver, and obtain information about the driver's drowsiness state based on the feature point.

In addition, the feature point is extracted along a periphery of the driver's mouth or eyes, and when the feature point moves more than a predetermined length, the server may define the driver's state as a drowsy state.

In addition, the speaker may output a pre-input dialog (dialog) as a voice.

Also, the input device may be a wearable keyboard worn by the driver.

In addition, in order to solve the above problems, the present invention provides the steps of: receiving a driver's face image; acquiring information on the driver's drowsiness state based on the face image; transmitting a command for outputting to a speaker, receiving a predetermined input from an input device, receiving the predetermined input, and controlling an alarm of the speaker to turn off according to the predetermined input may include

Also, the obtaining of the information on the drowsiness state may include extracting a feature point for the face of the driver and acquiring information on the drowsiness state based on the feature point.

In addition, the step of extracting the feature point extracts the feature point along or around the driver's mouth, and the step of obtaining the information on the drowsiness state includes the steps of obtaining the distance traveled by the feature point and the moving When the distance is greater than a predetermined length, the method may include defining the driver's state as a drowsy state.

In addition, the speaker may output a pre-input dialog (dialog) as a voice.

Also, the input device may be a wearable keyboard worn by the driver.

In addition, in order to solve the above problems, the present invention provides a non-transitory computer readable medium storing instructions, when the instructions are executed by a processor, causing the processor to perform the above-described method for preventing driver drowsiness, It may be a non-transitory computer-readable medium.

The present invention has the effect of providing a system and method for preventing drowsy driving for solving the above-described problems.

In addition, the present invention can not only accurately detect the driver's drowsiness state by utilizing deep learning, but also reduce the driver's drowsiness in that the drowsiness alarm is turned off only by using the input device unique to the present invention to perform a predetermined input. It can be effectively prevented.

In addition, the present invention utilizes a wearable keyboard to receive feedback from the driver, so that feedback can be input from the driver without greatly hindering driving while driving, thereby preventing the driver from drowsiness and maximizing the safety of driving the vehicle. have.

The effects obtainable according to the present invention are not limited to the above-mentioned effects, and other effects not mentioned may be clearly understood by those of ordinary skill in the art to which the present invention belongs from the following description. will be.

1 is a view showing a system for preventing drowsy driving according to the present invention.
2 is a diagram illustrating prevention of drowsiness of a driver through communication with the driver;
3 is a diagram illustrating a server according to the present invention.
4 is a diagram schematically illustrating an operation of a wearable keyboard, which is an input device according to the present invention.
5 is a flowchart for explaining a series of processes of determining an output value from an input signal in the wearable keyboard as an input device of the present invention and transmitting it to an external device.
6 is a view for explaining a detailed configuration of a wearable keyboard, which is an input device of the present invention.
7 is a view for explaining an operation of recognizing first sensed data in a wearable keyboard which is an input device of the present invention.
8 is a diagram for explaining the main configuration of a wearable keyboard, which is an input device of the present invention.
9 to 11 are views illustrating a method for preventing driver drowsiness according to the present invention.
BRIEF DESCRIPTION OF THE DRAWINGS The accompanying drawings, which are included as a part of the detailed description to facilitate the understanding of the present invention, provide embodiments of the present invention, and together with the detailed description, explain the technical features of the present invention.

Hereinafter, the embodiments disclosed in the present invention will be described in detail with reference to the accompanying drawings, but the same or similar components are assigned the same reference numbers regardless of reference numerals, and redundant description thereof will be omitted.

In addition, in describing the embodiments disclosed in the present invention, if it is determined that detailed descriptions of related known technologies may obscure the gist of the embodiments disclosed in the present invention, the detailed description thereof will be omitted.

In addition, the accompanying drawings are only for easy understanding of the embodiments disclosed in the present invention, and the technical spirit disclosed in the present invention is not limited by the accompanying drawings, and all changes included in the spirit and scope of the present invention , should be understood to include equivalents or substitutes.

Terms including an ordinal number such as 1st, 2nd, etc. may be used to describe various elements, but the elements are not limited by the terms. The above terms are used only for the purpose of distinguishing one component from another.

The singular expression includes the plural expression unless the context clearly dictates otherwise.

In the present application, terms such as “comprises” or “have” are intended to designate that a feature, number, step, operation, component, part, or combination thereof described in the specification exists, but one or more other features It should be understood that this does not preclude the existence or addition of numbers, steps, operations, components, parts, or combinations thereof.

Hereinafter, a system for preventing drowsy driving according to a preferred embodiment of the present invention will be described in detail based on the above description.

1 is a diagram illustrating a system for preventing drowsiness according to the present invention, and FIG. 2 is a diagram illustrating prevention of drowsiness of the driver through communication with the driver.

1 , a system according to the present invention may include a vehicle 200 and a server 300 . The vehicle 200 may communicate with the server 300 using V2X, etc., and the vehicle 200 includes an image acquisition unit 210 , a speaker 220 and an input device 100 in addition to basic devices necessary for driving. may further include. In addition, the vehicle 200 may further include a shock alleviator 211 capable of mitigating an impact on the image acquiring unit 210 .

1 and 2 , the image acquisition unit 210 may acquire a face image of the driver. The image acquisition unit 210 may be a camera that captures the driver's face in the vehicle 200 or may be an image reception unit that acquires an image from the camera.

Referring to FIG. 2 , the shock alleviator 211 is a device attached to the image acquisition unit 210 , and may refer to a device capable of preventing the driver's face image from shaking due to the shaking of the vehicle 200 . The shock alleviator 211 may include an elastic body such as a spring, and may use a suspension device to alleviate camera shake or an OIS device to mitigate camera shake.

1 and 2 , the speaker 220 may be a voice output device that delivers a dialog to the driver. The speaker 220 may transmit a message to the driver through vibration. The speaker 220 may receive a dialog from the server 300 and output the received dialog as a voice. The speaker 220 may receive a warning message from the server 300 and output an alarm according to the received warning message. That is, the speaker 220 may output an alarm according to the driver's drowsy state. In this case, the dialog may be previously input and stored.

Referring to FIG. 1 , the server 300 may receive an image of the driver's face from the image acquisition unit 210 , and may learn about the driver's face in the received image. Also, the server 300 may analyze the driver's face image according to the pre-stored learning data. In this case, the pre-stored learning data may be data learned from big data through deep learning or the like. That is, the server 300 may receive the image and may acquire information on the driver's drowsiness state based on the image. That is, the server 300 may extract a feature point for the driver's face and obtain information on the driver's drowsiness state based on the feature point.

Referring to FIG. 1 , the server 300 may extract a feature point from the driver's face image, and obtain information on whether the driver is in a drowsy state based on the extracted feature point. When the driver is in a drowsy state, the risk of a traffic accident may rapidly increase, so when information that the driver is drowsy is obtained, the server 300 outputs an alarm through the speaker 220 of the vehicle 200 . A warning message may be generated and transmitted to the vehicle 200 or the speaker 220 .

The server 300 may extract a feature point based on a specific part of the driver's face. The server 300 may extract the feature points along the periphery of the driver's mouth. Accordingly, it is possible to determine whether the driver is yawning or the like through the movement of the mouth shape. For example, when the driver yawns, unlike in the case of general speaking, the movement of the driver's mouth may increase. In addition, in the case of yawning, after the mouth grows to a predetermined size, the enlarged size may be maintained for a predetermined time. Therefore, the server 300 can extract a feature point around the driver's mouth and detect whether the feature point moves more than a preset distance, and after the feature point moves more than a preset distance, more than a preset time You can also sense whether it lasts for a long time.

Also, the server 300 may extract the feature points along the driver's eye periphery. Accordingly, it is possible to determine whether the driver is in a drowsy state or the like through eye movement. For example, when the distance between the feature points around the driver's eyes is smaller than a preset distance, the server 300 may detect that the driver's eyes are closed. In addition, when the distance between the feature points around the driver's eyes becomes smaller than the preset distance and the distance is maintained longer than the preset time, the server 300 may detect the driver's eyes as closed. have. In addition, the server 300 may check the number of times the feature points around the driver's eyes move for a predetermined time, and when the number of movements is smaller than the predetermined number, determine that the driver's state is a drowsy state.

However, since the blinking state of the driver's eyes may be different for each person, the server 300 may learn individual characteristics of the driver. That is, the server 300 may analyze the driver's eye and mouth movements and at the same time learn the driver's eye blinking state and number through deep learning, etc. FIG. Accordingly, the server 300 may determine the individual driver's personalized drowsiness state.

As described above, the server 300 may define a case in which the condition of the feature point satisfies a predetermined condition as the driver's drowsiness state, and may determine that the driver is in the drowsy state.

1 and 2 , the input device 100 is a device for the driver to input a specific command, and may be a microphone when inputting a voice. Also, the input device 100 may be a keyboard when the driver inputs text data. Also, the input device 100 may be changed according to what type of command the driver inputs. Also, the input device 100 may be a device to which a predetermined input is input to turn off the alarm of the speaker 220 .

Also, the input device 100 may mean a means for the user to input all commands required for the moving means. Also, the input device 100 may be a wearable keyboard worn by the driver. Details of the wearable keyboard will be described later.

When it is detected that the driver is in a drowsy state, the following scenario may be performed.

The server 300 may generate an alarm message for preventing the driver from drowsiness. The alarm message is transmitted to the driver through the speaker 220, and the driver can prevent drowsiness through the alarm. The alarm can be ended only after receiving a predetermined input from the driver. For example, in a state in which the driver wears a wearable keyboard, which will be described later, the server 300 may receive predetermined letters, numbers, or a combination thereof through the wearable keyboard. In addition, the server 300 receives a predetermined keyboard input, and in this case, the server 300 may generate an alarm cancellation message and transmit it to the speaker 220 to cancel the alarm. In this case, the predetermined input may be simple letters, numbers, or a combination thereof so that the driver can input while driving. Also, an input through the wearable keyboard is input according to a predetermined beat, and the server 300 may receive data on the corresponding beat. The server 300 may generate an alarm release message when the data for the beat satisfies the condition of the data for the beat stored in advance.

As such, in the present invention, after the driver wears the wearable keyboard 100 , which will be described later, a constant feedback is transmitted to the server 300 through this, thereby enabling the driver to more efficiently wake up from drowsiness. Also, the driver may wear the wearable keyboard 100 and grip the steering wheel of the vehicle. Accordingly, input may be possible by moving the wearable keyboard 100 while holding the steering wheel of the vehicle. Through this, there is an effect of preventing the driver from drowsiness and at the same time stably driving the vehicle.

Referring to FIG. 1 , the communication unit 230 is configured to enable communication between the mobile means and the server 300 . In addition, the communication unit 230 may communicate with the content provider using V2X communication. Accordingly, the communication unit 230 may communicate with the server 300 through a Road Side Unit (RSU). In the case of the communication unit 230 using wireless communication, it is connected to an internal/external antenna, and transmits/receives information to and from the base station by the mobile phone communication method through the antenna. The communication unit 230 using wireless communication includes a wireless communication unit (not shown) having a modulator, a demodulator, a signal processing unit, and the like.

The wireless communication refers to communication using a communication facility installed by telecommunication companies and a wireless communication network using the frequency. At this time, various radios such as code division multiple access (CDMA), frequency division multiple access (FDMA), time division multiple access (TDMA), orthogonal frequency division multiple access (OFDMA), single carrier frequency division multiple access (SC-FDMA), etc. It may be used in a communication system, as well as 3rd generation partnership project (3GPP) long term evolution (LTE) may be used. In addition, 5G communication, which is currently commercialized, can be mainly used, and 6G, which is scheduled to be commercialized in the future, may also be used. However, the present invention can utilize an existing communication network without being limited by such a wireless communication method. In addition, the communication unit 230 may support wireless communication functions such as Wi-Fi and Bluetooth in the mobile means.

In addition, the vehicle 200 according to the present invention may further include a computing device (not shown). The computing device (not shown) is configured to perform calculations necessary for communication with the server 300 and to control the image acquisition unit 210 , the speaker 220 , the input device 100 , and the like. In addition, since the computing device (not shown) does not require high computational power, it can be implemented as a small computing device such as a Raspberry Pi.

3 is a diagram illustrating a server according to the present invention.

Referring to FIG. 3 , the server 300 according to the present invention may include a processor 301 , a communication unit 230 , and a memory 303 . The processor 301 may be a subject that learns information about the driver and obtains information about the driver's drowsy state.

The processor 301 is a configuration capable of performing calculations and controlling the moving means. Mainly, it may mean a central processing unit (CPU), an application processor (AP), a graphics processing unit (GPU), or the like. In addition, the CPU, AP, or GPU may include one or more cores therein, and the CPU, AP, or GPU may operate using an operating voltage and a clock signal. However, a CPU or AP may consist of a few cores optimized for serial processing, whereas a GPU may consist of thousands of smaller and more efficient cores designed for parallel processing.

The memory 303 stores data supporting various functions of the transportation means. The memory 303 may store a plurality of application programs or applications driven in the mobile means, data for operation of the mobile means, and commands. At least some of these application programs may be performed through wireless communication. It may be downloaded from the external server 300 .

The memory 303 includes a flash memory type, a hard disk type, a solid state disk type, a silicon disk drive type, and a multimedia card micro type. ), card-type memory (such as SD or XD memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read (EEPROM) -only memory), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, and an optical disk may include at least one type of storage medium. Also, the memory 303 may include a web storage that performs a storage function on the Internet.

The communication module 302 is a transceiver, and may be configured to communicate with the communication unit 230 of the vehicle 200 . A detailed description of the communication module 302 will be omitted because it is the same as or overlapping with the description of the communication unit 230 .

4 is a diagram schematically illustrating an operation of a wearable keyboard, which is an input device according to the present invention.

According to one disclosure, the wearable keyboard 100 may be manufactured in the form of a pair of gloves. According to one disclosure, the wearable keyboard 100 is a device for performing input by being worn on the user's hand, and in particular, refers to a keyboard without a keyboard. According to one disclosure, the wearable keyboard 100 may recognize a user's hand motion through a sensor and transmit an output value of recognizing a character meaning a hand motion to the external device 600 using the wireless communication module 302 . .

According to one disclosure, the wearable keyboard 100 determines an input signal for inputting the virtual QWERTY keyboard from the first sensing data obtained from the pressure-sensitive sensor 101 , and virtual from the second sensing data obtained from the flex sensor 111 . Determine the position at which the input signal is detected in the QWERTY keyboard, and generate an output signal based on the result of determining the position of the input signal input from the index finger from the third sensing data obtained from the gyro sensor 103, and the communication module ( 302), the output signal can be transmitted to an external device.

According to one disclosure, the external device 600 includes a display capable of displaying data input from the outside through a communication module, and includes a notebook PC, a desktop PC, an MP3 player, a Portable Multimedia Player (PMP), and a Personal Digital Assistant (PDA). , it is obvious that it can be applied to all information and communication devices and multimedia devices such as tablet PCs, mobile phones, smart phones, etc. and their applications.

According to one disclosure, the wearable keyboard 100 and the external device 600 may be divided into a master terminal and a slave terminal according to who serves as a host or an access point. In other words, a terminal that generates an identifier, that is, an SSID (Service Set Identifier) for pairing and accepts pairing becomes a master, and a terminal that requests pairing from such a master terminal becomes a slave. Also, in the present invention, a terminal may be a master or a slave. In addition, in the present invention, the terminal may download and install an application for performing such a pairing function from an online market. In addition, in the present invention, the terminal may receive and use an application from a cloud server that provides a cloud computing service.

According to one disclosure, the wearable keyboard 100 may recognize a user's hand gesture using at least three types of sensors. More specifically, the wearable keyboard 100 uses the pressure sensor 101, the flex sensor 111, and the gyro sensor 103 to recognize the user's hand gesture, and from the recognized hand gesture, the user wants to input the character, etc. as an output value. may be transmitted to device 600 .

According to one disclosure, the pressure-sensitive sensor 101 may be installed to correspond to the positions of all finger tips of the user, and may determine whether the user inputs the virtual keyboard. When a pressure greater than or equal to a predetermined threshold is input, the wearable keyboard 100 may determine that the user has inputted the virtual keyboard, and may determine the signal input by the user as the input signal.

According to one disclosure, the flex sensor 111 may be installed so as to correspond to the first joint to the third joint of the user's finger. According to one disclosure, the flex sensor 111 may measure the bending information of the finger from a resistance value that is changed according to the bending degree of the user's finger in order to measure the bending degree of the user's finger. The flex sensor 111 may be made of a flexible element, and may include a bending resistance measuring element detachably attached to the terminal of the head socket. Accordingly, the flex sensor 111 is easily replaceable in the glove-type wearable keyboard 100 .

According to one disclosure, the gyro sensor 103 may be installed to correspond to the user's index finger. The gyro sensor 103 is generally used to accurately determine the input position of the index finger, which has the widest keyboard input range. More specifically, the wearable keyboard 100 may determine the output value by determining the left and right (x-axis) positions of the index finger from the sensing signal of the gyro sensor 103 .

It will be described in more detail below.

5 is a flowchart for explaining a series of processes of determining an output value from an input signal in the wearable keyboard, which is the input device 100 of the present invention, and transmitting it to an external device.

According to one disclosure, the virtual QWERTY keyboard is a means for receiving a key set for each finger of the wearable keyboard 100 rather than the actual keyboard, and the user can input the virtual QWERTY keyboard through a finger input according to inertia. have.

According to one disclosure, in block 201 , the wearable keyboard 100 may determine whether the first sensing data obtained from the pressure-sensitive sensor corresponds to a threshold value or more. According to one disclosure, the first sensed data represents a pressure signal recognized by the wearable keyboard 100 through a pressure sensor. For example, when a user applies pressure to a flat bottom surface while wearing the wearable keyboard 100, when the pressure applied by the pressure sensor corresponds to a threshold value or more, the input value is converted to the first sensing data can decide According to one disclosure, when the value of the first sensing data is less than or equal to the threshold value, the wearable keyboard 100 may reduce energy for analyzing unnecessary input by determining it as an error value rather than data for inputting the keyboard. .

According to one disclosure, the wearable keyboard 100 may compare the pressure input from the pressure sensor with a predetermined threshold, and select and recognize the input level according to the comparison result. The threshold value by one start may be a value preset by the user. In addition, the threshold value according to the initiation may be a pressure value customized to the user based on the user's profile.

According to one disclosure, the wearable keyboard 100 may set a time point at which a pressure greater than a threshold value is inputted as a specific time point or a specific time period, and selects the input level according to the pressure input at a recognition time. can be characterized as Here, the recognition time may be set to a time of 50 ms to 150 ms based on a point in time when a pressure equal to or greater than a predetermined level is input from the pressure-sensitive sensor.

According to one disclosure, in block 202, the wearable keyboard 100 may determine the y-axis position of the input signal from the second sensing data obtained from the flex sensor. According to one disclosure, the wearable keyboard 100 may determine a preliminary output value preset to the predetermined finger based on the predetermined finger that has acquired the first sensing data.

According to one disclosure, the preliminary output value indicates one keyboard key per line of a predetermined virtual QWERTY keyboard. For example, based on the English virtual QWERTY keyboard keyboard, W. S. X may be assigned to the left ring finger, and E, D, and C may be assigned to the left middle finger. However, in the case of the index finger, two keyboard keys may be assigned to each line of the virtual QWERTY keyboard. For example, Y, U, H, J, N, M may be assigned to the index finger of the right hand based on the English virtual QWERTY keyboard keyboard, and T, R, G, F, B, V may be assigned to the index finger of the left hand. can be

According to one disclosure, the wearable keyboard 100 may determine the output value of the signal input by the user by determining the y-axis position of the finger at which the input signal is detected from the second sensing data. In this case, the wearable keyboard 100 may determine a reference point for determining a y-axis position before inputting a character after starting pairing with the external device 600 . For example, the wearable keyboard 100 may receive a message requesting to start inputting text from the external device 600 , and may set a reference point according to receiving a message requesting to set a reference point on the y-axis. Also, according to another embodiment, the wearable keyboard 100 may set a reference point through an application for keyboard input. The method of setting the y-axis reference point is not limited.

According to one disclosure, in block 203 , the wearable keyboard 100 may determine whether the input signal is a signal obtained from the index finger. When the input signal is the index finger, since it has two preliminary output values at the same y-axis position, an additional process for accurate position determination is required.

According to one disclosure, in block 204 , when it is determined that the input signal is an input signal from the index finger, the wearable keyboard 100 may determine the x-axis position of the input signal from the third sensing data. According to one disclosure, the wearable keyboard 100 may preset a reference point for determining an x-axis position. According to one disclosure, the wearable keyboard 100 may set a reference point for determining the left and right positions of the input signal at a predetermined point in time after being connected to an external device. The wearable keyboard 100 may determine whether the signal is detected from the left side or the right side from the reference point using the signal sensed by the gyro sensor. For example, when the y-axis position of the input signal acquired from the right index finger is the uppermost part, the preliminary output values are Y and U, and when it is determined as the right value based on the reference point, the final output value is U.

According to one disclosure, in block 205 , the wearable keyboard 100 may determine an output value from location information of an input signal. The wearable keyboard 100 may determine the final output value by combining the position information of the input signal. For example, when a plurality of input signals are input, a value obtained by combining the plurality of input signals may be transmitted to an external device as an output value.

According to one disclosure, in block 206 , the wearable keyboard 100 may transmit an output value to the upper device using the communication module 114 . According to one disclosure, the communication module 114 may include a module capable of wireless or wired communication. More specifically, the communication module 114 may include a short-range wireless communication module 114, for example, the short-range wireless communication method includes NFC method, Bluetooth, Wi-Fi, Zigbee, barcode recognition method, QR code recognition method, etc. There may be many different ways of doing the same.

6 is a view for explaining a detailed configuration of a wearable keyboard, which is an input device of the present invention.

According to one disclosure, the wearable keyboard 100 may be manufactured in the form of a glove and mounted on the user's hand. In addition, the wearable keyboard may be made of a polyamide resin composition.

Preferably, here, the wearer polyamide resin composition is prepared by reacting vegetable oil with alcohol, and 15 to 25 wt% of an epoxy-based ester compound represented by Formula 1, a phthalate-based ester compound, and a terephthalate-based ester compound , 20 to 25% by weight of at least one ester compound selected from the group consisting of phthalate-based and terephthalate-based ester mixtures and trimellitate-based ester compounds, high-density polyethylene (HDPE), low-density polyethylene (LDPE), polypropylene (PP), At least one olefinic rubber polymer selected from ethylene-propylene copolymer (EPM), ethylene-propylene-diene copolymer (EPDM), ethylene-butene copolymer, ethylene-octene copolymer, and ethylene-butadiene copolymer 5 to 10% Vinyl containing 30 to 50 wt% of polyamide having a weight %, relative viscosity (25°C) of 2.0 to 2.8 cP and a number average molecular weight of 20,000 to 200,000 g/mol, conjugated diene rubber, aromatic vinyl compound and vinyl cyanide compound It is characterized in that it consists of a polyamide resin composition comprising 5 to 15 wt% of an aromatic compound-vinyl cyan compound copolymer.

[Formula 1]

이고, 상기 R_x 및 R_y는 각각 독립적으로 수소, (C1-C5)알킬 또는

이며, 상기 알킬은 (C1-C5)알킬 또는

이 더 치환될 수 있고, 상기 R₄₁ 및 R₄₂는 각각 독립적으로 (C8-C20)에폭시알킬이며, 상기 n은 1 내지 3에서 선택되는 정수임).(Wherein R4 is (C8-C20) epoxyalkyl, R5 is (C1-C10) alkyl or

and R _x and R _y are each independently hydrogen, (C1-C5)alkyl or

and wherein the alkyl is (C1-C5)alkyl or

may be further substituted, wherein R ₄₁ and R ₄₂ are each independently (C8-C20)epoxyalkyl, and n is an integer selected from 1 to 3).

In addition, the wearable keyboard may include a coating layer in order to increase the recognition rate of the input signal generated due to the operation of the user's finger.

The coating layer is more specifically an antistatic layer, it is possible to prevent the generation of static electricity to prevent the adhesion of dust, and to prevent impurities such as dust, it is possible to increase the recognition rate of the input signal. In addition, the adhesion to the polyamide resin composition is excellent, and thus the adhesion of the coating layer is excellent.

Preferably, the antistatic layer is polysiloxane represented by the following formula (2); Conductive fillers and graphite may include:

[Formula 2]

here,

m is an integer from 1 to 100,

p is an integer from 3 to 10,

R ₁ to R ₃ are the same as or different from each other, and each independently selected from the group consisting of hydrogen, deuterium, a hydroxy group, a substituted or unsubstituted C 1 to C 30 alkyl group, or a substituted or unsubstituted C 6 to C 30 aryl group, ,

Preferably, the substituted alkylene group, substituted arylene group, substituted alkyl group and substituted aryl group are hydrogen, deuterium, cyano group, nitro group, halogen group, hydroxyl group, alkyl group having 1 to 30 carbon atoms, alkyl group having 1 to 20 carbon atoms A cycloalkyl group, an alkenyl group having 2 to 30 carbon atoms, an alkynyl group having 2 to 24 carbon atoms, an aralkyl group having 7 to 30 carbon atoms, an aryl group having 6 to 30 carbon atoms, a heteroaryl group having 5 to 60 nuclear atoms, 6 to 30 carbon atoms of a heteroarylalkyl group, an alkoxy group having 1 to 30 carbon atoms, an alkylamino group having 1 to 30 carbon atoms, an arylamino group having 6 to 30 carbon atoms, an aralkylamino group having 6 to 30 carbon atoms, a heteroarylamino group having 2 to 24 carbon atoms, 1 to carbon atoms It is substituted with one or more substituents selected from the group consisting of a 30 alkylsilyl group, an arylsilyl group having 6 to 30 carbon atoms and an aryloxy group having 6 to 30 carbon atoms, and when substituted with a plurality of substituents, they are the same or different from each other.

More preferably, the compound represented by Formula 2 may be a compound represented by Formula 3 below.

[Formula 3]

Here, m and p are as defined in Formula 2 above.

Preferably, the conductive filler may be selected from the group consisting of silica, alumina and mixtures thereof, but preferably alumina, but not limited to the above example. The conductive filler has a particle diameter of 30 to 50 μm, but is not limited to the above example. The conductive filler may exhibit electrical conductivity.

The graphite may be included in a small amount to continuously maintain the antistatic effect in the antistatic layer. Considering that graphite is an expensive conductive filler, it is included in a small amount in the antistatic layer in the present invention to maintain a continuous antistatic effect.

More specifically, the antistatic layer of the present invention may include polysiloxane represented by Formula 2; By including a conductive filler and graphite, it may exhibit an antistatic effect. The polysiloxane is divided into a hydrophilic portion and a hydrophobic portion. The hydrophilic moiety is capable of hydrogen bonding with a water molecule by an oxygen atom containing a lone pair of electrons. On the other hand, the alkyl group acts as a hydrophobic group. Accordingly, the hydrophilic part is positioned on the surface of the antistatic layer, and the hydrophobic part is positioned in the opposite direction, thereby exhibiting a semi-permanent antistatic effect.

For forming the antistatic layer, the antistatic composition is more specifically polysiloxane represented by the formula (2); It can be prepared by mixing a conductive filler, graphite, and an organic solvent.

The organic solvent may be selected from the group consisting of ethanol, methanol, butanol, hexane, propane, toluene, phenol, and mixtures thereof.

Preferably, the antistatic composition may include 40 to 80 parts by weight of the polysiloxane represented by Formula 2, 30 to 50 parts by weight of the conductive filler, and 5 to 10 parts by weight of graphite based on 100 parts by weight of the organic solvent. In the case of the above range, a synergistic effect of critical significance is expressed as an antistatic synergistic effect due to the interaction of each component, and when it is out of the above range, the synergistic effect is rapidly reduced or almost absent.

More preferably, the viscosity of the antistatic composition is 1,200 to 1,500 cP, and when the viscosity is less than 1,200 cP, there is a problem that it is not easy to form an antistatic layer because it flows down during coating on one surface, and when it exceeds 1,500 cP There is a problem in that it is not easy to form a uniform antistatic layer.

[Preparation Example: Preparation of coating layer]

1. Preparation of coating composition

An antistatic composition was prepared by mixing polysiloxane represented by the following Chemical Formula 3, a conductive filler, and graphite in an organic solvent in which toluene and phenol were mixed in a weight ratio of 1:1:

[Formula 3]

Here, m is an integer from 10 to 30, and p is an integer from 3 to 5.

A more specific composition of the antistatic composition is shown in Table 2 below.

DY1 DY2 DY3 DY4 DY5 DY6 organic solvent 100 100 100 100 100 100 polysiloxane 20 30 40 60 80 100 alumina 10 20 30 40 50 60 graphite One 3 5 7 10 15

(Parts by weight) The alumina has a particle diameter of 30 to 50 μm.

2. Preparation of protective layer

An antistatic layer was formed by applying the antistatic composition of HS 1 to HS 6 on one surface of the base layer prepared using the polyamide resin, and then thermal curing.

[Experimental example: Antistatic effect test]

1. Viscosity Measurement

Before forming the antistatic layer on one surface of the polyamide base layer, the viscosity of the antistatic composition was measured. Viscosity was measured using a rheometer (Rheometer, Compac-100, Sun Sci. Co., Japan). The viscosity measurement results are shown in Table 3 below.

DY1 DY2 DY3 DY4 DY5 DY6 Viscosity (cP) 620 800 1010 1400 1950 2400

2. Measurement of surface electrical resistance

For the protective layer in which the antistatic layer of DY 1 to DY 6 was formed on one surface of the polyamide base layer, the surface electrical resistance was measured using a Resistance Meter SIMCO resistor ST-4 (25° C., 50% relative humidity).

As a comparative example, the surface electrical resistance of the polyamide base layer on which the antistatic layer was not formed was also measured.

comparative example DY1 DY2 DY3 DY4 DY5 DY6 surface electrical resistance
(Ω/cm ² ) 7.4×10 ¹¹ to 1.6×10 ¹² 6.4×10 ⁹ to 1.4×10 ¹⁰ 1.4×10 ⁹ to 1.6×10 ¹⁰ 7.2×10 ⁸ to 6.1×10 ⁹ 4.4×10 ⁷ to 2.1×10 ⁸ 6.5×10 ⁷ to 4.5×10 ⁸ 5.8×10 ⁸ to 7.8×10 ⁸

According to Table 4, compared to the comparative example in which the antistatic layer is not formed, since the surface electrical resistance of DY 1 to DY 6 is low, the electrical conductivity is excellent, and it can be confirmed that an excellent antistatic effect is exhibited.

3. Evaluation of surface appearance

Due to the difference in viscosity of the antistatic composition, after the coating layer was prepared, a sensory evaluation was performed on whether a uniform surface was formed. Whether or not a uniform coating layer was formed was evaluated, and evaluation was performed according to the following criteria.

○: uniform coating layer formation

×: Formation of a non-uniform coating layer

DY1 DY2 DY3 DY4 DY5 DY6 sensory evaluation × × ○ ○ ○ ×

When the coating layer is formed, if the viscosity is less than a certain level, flow occurs on the surface of the polyamide, and formation of a uniform coating layer is difficult in many cases. Accordingly, there may be a problem in that the production yield is lowered. In addition, even when the viscosity is too high, it is difficult to uniformly apply the composition to form a uniform coating layer.

According to one disclosure, the wearable keyboard 100 may include ten pressure-sensitive sensors 101 installed to correspond to the distal ends of each of the user's ten fingers. According to one disclosure, the ten pressure-sensitive sensors 101 may include unique identification information corresponding to each finger. Accordingly, when the pressure equal to or greater than the threshold value is sensed, the wearable keyboard 100 may determine the preliminary output value by determining the finger at which the signal is sensed.

According to one disclosure, the flex sensor 111 may be installed to correspond to the first joint to the third joint of the user's finger in order to measure the degree of bending of the user's finger. According to one disclosure, the flex sensor 111 may be attached to the glove only at both ends and the middle portion of the flex sensor 111 for the convenience of movement of the user's finger.

According to one disclosure, the gyro sensor 103 may be installed on the index finger of both hands of the user to determine the x-axis position to which the index finger is input. The gyro sensor 103 measures the direction information of the hand. Additionally, the wearable keyboard 100 may include an acceleration sensor for measuring acceleration information, a gyro sensor for measuring rotation information of the hand, and a geomagnetic sensor for measuring the direction of the geomagnetism. The measured value of the gyro sensor 103 may be provided to an inertial measurement unit (IMU). The inertial measurement device may be provided in the form of one integrated unit consisting of a total of three sensors: an accelerometer capable of measuring movement inertia, a gyrometer capable of measuring rotational inertia, and a magnetic field capable of measuring an azimuth. Rotation information on three axes, that is, pitch, roll, and yaw, may be obtained by using the measured values for the gyro and magnetic fields.

According to one disclosure, the processor 115 sets the hysteresis parameter range to less than 20% in order to reduce the error rate of the user input signal recognized by the pressure-sensitive sensor 101 , the gyro sensor 103 and the flex sensor 111 . can

7 is a diagram for explaining an operation of recognizing first sensing data in the wearable keyboard, which is the input device 100 of the present invention.

In FIG. 7 , L1, L2, and L3 refer to graphs representing increases and decreases in pressure when the user intentionally applies forces of different magnitudes to the first to third input levels. In other words, it refers to a case where the force is applied to a weak level, a medium level, and a strong level, respectively. By the start, it can be confirmed that the force applied to the floor according to the user's input starts to increase rapidly at about 40-50 ms, peaks at about 80-100 ms, and then ends at about 110-120 ms.

Preferably, in consideration of the experimental results as described above, the recognition time is preferably set to a time of 50 ms to 150 ms based on a point in time when the pressure of a predetermined size or more is started to be input from the pressure-sensitive sensor unit. And more preferably, it is preferably set to a time of 70 ms to 110 ms. Here, if a time less than 50 ms or greater than 150 ms is set as the recognition time, it can be seen that the magnitude of the pressure applied according to the input applied to the wearable keyboard cannot be measured correctly.

The recognition time may be set based on a time when the pressure has a maximum value during a predetermined time from a time when the pressure of a predetermined level or more is started to be input from the pressure reduction sensor 101 . Preferably, the time when the pressure has a maximum value may be the recognition time.

Here, the wearable keyboard 100 may analyze a change in the magnitude of the input pressure without setting a fixed recognition time, and select the input level based on the magnitude of the pressure at the point in time when the pressure has a maximum value. In this way, when the maximum pressure value is used, there is an effect of more accurately recognizing the size of the pressure intended by the user and determining the input level accordingly.

To this end, the wearable keyboard 100 may store the amount of pressure input from the pressure-sensitive sensor 101 over time according to time, and determine the input level using the largest pressure among the stored pressures.

However, in the case of using the maximum value as described above, memory is required to identify the maximum value and power for signal processing may be consumed. Therefore, the previously set recognition time may be used to save memory and power. When the preset recognition time is used as described above, since the input level can be determined using only the pressure input at the corresponding recognition time, memory can be saved and power consumed for signal processing can be minimized.

According to another embodiment, the wearable keyboard 100 may set a threshold value most suitable for each user according to the user's input in order to recognize the input level.

According to one disclosure, the threshold value may be selected and set according to a user's selection input from among a plurality of values presented to the user by a setting program driven by the wearable keyboard 100 . For example, the designer of the setting program measures the degree of force applied when input to the wearable keyboard 100 for users of each age, gender, and physical condition according to the statistics of the experiment result to measure each age, gender, and physical condition A threshold value most suitable for a user having a condition may be determined, and accordingly, a threshold value for each user profile may be set in a setting program according to the user's age, gender, and physical condition. For example, in a setting program driven by the wearable keyboard 100, a threshold value is preset for each user profile, and a preset threshold value can be used for the selected profile by receiving a user's selection input for the user profile. . For example, if the setting program pre-stores a threshold value corresponding to a user profile for each age and age group, and the user selects a female user profile or a user profile in her twenties, the wearable keyboard 100 displays the user profile of a woman or a user in their twenties. A preset threshold value (first threshold: 0.5N, second threshold 3N) may be used.

Alternatively, the threshold value may be set in such a way that the wearable keyboard 100 uses pressure generated according to each user's touch input. Here, the wearable keyboard 100 may set a predetermined threshold as a comparison standard in order to select the input level using the pressure input from the pressure-sensitive sensor 101 .

8 is a view for explaining the main configuration of the wearable keyboard, which is the input device 100 of the present invention.

The wearable keyboard 100 may include a sensor unit 105 , a communication module 114 , a battery 116 , a control unit 115 , and a memory 112 .

According to one disclosure, the sensor unit 105 may include various sensors including a pressure sensor, a gyro sensor, and a flex sensor. For example, the sensor unit 105 may include a gesture sensor, a gyro sensor, a barometric pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biometric sensor, a temperature sensor, a humidity sensor, or It may include an illuminance sensor.

According to one disclosure, the battery 116 includes a battery that supplies power required to perform a function of the wearable keyboard 100 , and may include, for example, a lithium polymer battery.

In addition, the wearable keyboard 100 may include a memory 112 that stores one or more instructions and a processor 115 that executes one or more instructions stored in the memory 112 .

According to one disclosure, the processor 115, for example, by driving software (eg, a program) to at least one other component (eg, hardware or software component) of the wearable keyboard 100 connected to the processor 115 can be controlled, and various data processing and operations can be performed. The processor 115 may load a command or data received from another component (communication module 114 ) into a volatile memory for processing, and store the result data in a non-volatile memory. According to an embodiment, the processor 115 operates independently of the main processor (eg, a central processing unit or an application processor), and additionally or alternatively, uses less power than the main processor or an auxiliary specialized for a specified function. It may include a processor (eg, a graphic processing unit, an image signal processor, a sensor hub processor, or a communication processor). Here, the auxiliary processor may be operated separately from or embedded in the main processor.

According to one disclosure, the communication module 114 may support establishment of a wired or wireless communication channel between the wearable keyboard 100 and the external device 600 and performing communication through the established communication channel. The communication module 114 may include one or more communication processors that support wired communication or wireless communication, operated independently of the processor 115 (eg, an application processor). According to an embodiment, the communication module 114 is a wireless communication module (eg, a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module (eg, a local area network (LAN) ) communication module, or a power line communication module).

According to one disclosure, when the first keyboard input is an input by the index finger, the processor 115 additionally determines the position of the first keyboard input in the x-axis direction by using the third sensing data, and It is characterized in that an output value corresponding to the x-axis position and the y-axis position is determined.

According to one disclosure, the processor 115 determines a threshold value of the first sensed data based on the user's profile, and when a pressure equal to or greater than the threshold value is sensed through the pressure sensor, at least one corresponding to the finger for which the pressure is sensed. A key of , may be determined as a preliminary output value, and any one of the preliminary output values may be determined as an output value based on location information obtained from at least one of the second sensing data and the third sensing data.

According to one disclosure, the processor 115 maps at least one preliminary output value to each of the ten pressure-sensitive sensors installed on the wearable keyboard, and when it is determined that the position of the input signal is not clear, the input signal is mapped to the pressure-sensitive sensor obtained The at least one preliminary output value may be transmitted to an external device, and the output signal may be determined based on a user input for selecting one of the at least one preliminary output values.

According to one disclosure, the memory 112 may store a program for processing and controlling the processor 115 , and may also store data input to or output from the apparatus of the present invention. Programs stored in the memory 112 may be classified into a plurality of modules according to their functions, where the plurality of modules are software, not hardware, and are functionally operated modules.

Programs stored in the memory 112 may be classified into a plurality of modules according to their functions, where the plurality of modules are software, not hardware, and may refer to modules that operate functionally.

[Application example]

Accordingly, examples using the wearable keyboard described above may be as follows.

[Example 1]

a pressure sensor installed to correspond to the distal end of all of the user's fingers;

a flex sensor installed to correspond to the first joint to the third joint of the user's finger;

a gyro sensor installed at the distal end of the user's index finger;

a communication module for communicating with an external device;

a memory storing one or more instructions; and

a processor executing the one or more instructions stored in the memory;

The processor determines an input signal for inputting a virtual QWERTY keyboard from the first sensing data obtained from the pressure-sensitive sensor, and determines a position where the input signal is detected from the virtual QWERTY keyboard from the second sensing data obtained from the flex sensor and generating an output signal based on a result of determining the position of the input signal input from the index finger from the third sensing data obtained from the gyro sensor, and transmitting the output signal to an external device through the communication module. keyboard.

[Second example]

In the first example,

The processor is

It is determined whether the first sensed data is detected above a threshold,

The first sensing data detected above the threshold is determined as a first keyboard input, and the y-axis direction position of the first keyboard input is determined from the second sensing data that changes according to the degree of bending of the user's finger, and ,

determining an output value corresponding to the determined y-axis position of the first keyboard input;

A wearable keyboard, characterized in that it transmits the output value to an external device using the communication module.

[3rd example]

In the second example,

When the first keyboard input is input by the index finger, a position in the x-axis direction of the first keyboard input is additionally determined using third sensing data, and an x-axis position and a y-axis position of the first keyboard input are determined. Characterized in determining the output value corresponding to the position, wearable keyboard.

[4th example]

In the first example,

The processor is

Determining a threshold value of the first sensing data based on the user's profile,

When a pressure equal to or greater than the threshold value is sensed through the pressure sensor, at least one key corresponding to a finger for which the pressure is sensed is determined as a preliminary output value,

Based on the location information obtained from at least one of the second sensing data and the third sensing data, any one of the preliminary output values is determined as an output value, the wearable keyboard.

[5th example]

In the first example,

The processor is

mapping at least one preliminary output value to each of the ten pressure-sensitive sensors installed in the wearable keyboard;

When it is determined that the position of the input signal is not clear, at least one preliminary output value mapped to the pressure-sensitive sensor that obtained the input signal is transmitted to an external device,

The wearable keyboard, characterized in that the output signal is determined based on a user input for selecting any one of the at least one preliminary output value.

[6th example]

In the first example,

The processor is

The wearable keyboard, characterized in that the hysteresis parameter range is set to less than 20% in order to reduce the error rate of the user input signal recognized by at least one of the pressure-sensitive sensor, the gyro sensor, and the flex sensor.

[Seventh example]

In the first example,

The wearable keyboard is made of a polyamide resin composition,

The polyamide resin composition comprises:

15 to 25 wt% of an epoxy-based ester compound represented by Formula 1, which is prepared by reacting vegetable oil with alcohol;

20 to 25 wt% of at least one ester compound selected from the group consisting of a phthalate-based ester compound, a terephthalate-based ester compound, a phthalate-based and terephthalate-based ester mixture, and a trimellitate-based ester compound;

High density polyethylene (HDPE), low density polyethylene (LDPE), polypropylene (PP), ethylene-propylene copolymer (EPM), ethylene-propylene-diene copolymer (EPDM), ethylene-butene copolymer, ethylene-octene copolymer, 5 to 10% by weight of at least one olefinic rubber polymer selected from among ethylene-butadiene copolymers;

30 to 50 wt% of a polyamide having a relative viscosity (25°C) of 2.0 to 2.8 cP and a number average molecular weight of 20,000 to 200,000 g/mol;

A wearable keyboard comprising a polyamide resin composition comprising 5 to 15 wt% of a conjugated diene rubber, an aromatic vinyl compound and a vinyl aromatic compound including a vinyl cyan compound-vinyl cyan compound copolymer.

[Formula 1]

이고, 상기 R_x 및 R_y는 각각 독립적으로 수소, (C1-C5)알킬 또는

이며, 상기 알킬은 (C1-C5)알킬 또는

이 더 치환될 수 있고, 상기 R₄₁ 및 R₄₂는 각각 독립적으로 (C8-C20)에폭시알킬이며, 상기 n은 1 내지 3에서 선택되는 정수임).(Wherein R4 is (C8-C20) epoxyalkyl, R5 is (C1-C10) alkyl or

and R _x and R _y are each independently hydrogen, (C1-C5)alkyl or

and wherein the alkyl is (C1-C5)alkyl or

may be further substituted, wherein R ₄₁ and R ₄₂ are each independently (C8-C20)epoxyalkyl, and n is an integer selected from 1 to 3).

Hereinafter, a method for preventing driver's drowsiness according to a second preferred embodiment of the present specification based on the above description is as follows. In this case, the subject performing the control method according to the second embodiment may be the server according to the above-described first embodiment or a processor of the server.

9 to 11 are views illustrating a method for preventing driver drowsiness according to the present invention.

According to FIG. 9 , the method for preventing driver drowsiness according to the present invention includes the steps of receiving a driver's face image (S1100), acquiring information on the driver's drowsiness state based on the face image (S1200), and drowsy state Transmitting a command for outputting an alarm in response to the speaker 220 (S1300), receiving a predetermined input from the input device 100 (S1400), and receiving a predetermined input, according to the predetermined input, the speaker It may further include a step (S1500) of controlling to turn off (off) the alarm of (220).

Referring to FIG. 10 , step S1200 according to the present invention may include extracting a feature point for the driver's face ( S1210 ) and obtaining information on a drowsy state based on the feature point ( S1220 ).

Referring to FIG. 11 , step S1220 according to the present invention includes the steps of obtaining the distance traveled by the feature point (S1221) and defining the driver's state as a drowsy state when the moved distance is greater than a predetermined length (S1222) may include In this case, the feature point may be a feature point extracted from around the driver's eyes or mouth.

An example of the step of transmitting a command for outputting an alarm according to the drowsy state to the speaker 220 (S1300) and the step of receiving a predetermined input from the input device 100 (S1400) are as follows.

The alarm according to the speaker may be as follows.

(1) beep sound

(2) Dialog that informs the state of drowsiness

(3) Drowsy driving warning message

An input required by the driver to turn off such an alarm may be predetermined as follows.

(1) input of a predetermined alphabet

(2) input of a predetermined number

(3) Combination of the above alphabets and numbers

(4) random combinations of alphabets or numbers

(5) Input according to a predetermined beat

The server may request an input according to a driver's selection among the above inputs. The driver may input the above predetermined input through the wearable keyboard 100 .

In addition, the server 300 or the processor 301 according to the present invention may control the driver's drowsiness prevention system according to the above-described method.

The present invention described above can be modeled as computer readable code on a medium in which a program is recorded. The computer-readable medium includes all types of recording devices in which data readable by a computer system is stored. Examples of computer-readable media include Hard Disk Drive (HDD), Solid State Disk (SSD), Silicon Disk Drive (SDD), ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc. It also includes modeling in the form of a carrier wave (eg, transmission over the Internet). Accordingly, the above detailed description should not be construed as restrictive in all respects but as exemplary. The scope of the present invention should be determined by a reasonable interpretation of the appended claims, and all modifications within the equivalent scope of the present invention are included in the scope of the present invention.

Any or other embodiments of the present invention described above are not mutually exclusive or distinct. Any of the above-described embodiments or other embodiments of the present invention may be combined or combined with each configuration or function.

The above detailed description should not be construed as restrictive in all respects and should be considered as illustrative. The scope of the present invention should be determined by a reasonable interpretation of the appended claims, and all modifications within the equivalent scope of the present invention are included in the scope of the present invention.

100: input device, wearable keyboard
200: vehicle
210: image acquisition unit
220: speaker
230: communication department
300: server

Claims (11)

an image acquisition unit acquiring an image of the driver's face;
a server receiving the image and obtaining information on the driver's drowsiness state based on the image;
a speaker outputting an alarm according to the drowsy state of the driver; and
Including; an input device to which a predetermined input is input in order to turn off the alarm;
The server is
Receive the predetermined input from the input device, and control to turn off the alarm of the speaker according to the predetermined input,
The input device is a wearable keyboard,
a pressure sensor installed to correspond to the distal end of all fingers of the user;
a flex sensor installed to correspond to the first joint to the third joint of the user's finger;
a gyro sensor installed at the distal end of the user's index finger;
a communication module for communicating with an external device;
a memory storing one or more instructions; and
a processor executing the one or more instructions stored in the memory;
The wearable keyboard is made of a polyamide resin composition,
The polyamide resin composition comprises:
15 to 25 wt% of an epoxy-based ester compound represented by Formula 1, which is prepared by reacting vegetable oil with alcohol;
20 to 25 wt% of at least one ester compound selected from the group consisting of a phthalate-based ester compound, a terephthalate-based ester compound, a phthalate-based and terephthalate-based ester mixture, and a trimellitate-based ester compound;
High density polyethylene (HDPE), low density polyethylene (LDPE), polypropylene (PP), ethylene-propylene copolymer (EPM), ethylene-propylene-diene copolymer (EPDM), ethylene-butene copolymer, ethylene-octene copolymer, 5 to 10% by weight of at least one olefinic rubber polymer selected from among ethylene-butadiene copolymers;
30 to 50 wt% of a polyamide having a relative viscosity (25°C) of 2.0 to 2.8 cP and a number average molecular weight of 20,000 to 200,000 g/mol;
A system for preventing driver's drowsiness, characterized in that it consists of a polyamide resin composition comprising 5 to 15 wt% of a vinyl aromatic compound-vinyl cyan compound copolymer including a conjugated diene rubber, an aromatic vinyl compound, and a vinyl cyan compound.
[Formula 1]

(Wherein R4 is (C8-C20) epoxyalkyl, R5 is (C1-C10) alkyl or

and R _x and R _y are each independently hydrogen, (C1-C5)alkyl or

and wherein the alkyl is (C1-C5)alkyl or

may be further substituted, wherein R ₄₁ and R ₄₂ are each independently (C8-C20)epoxyalkyl, and n is an integer selected from 1 to 3). According to claim 1,
The server is
The system for preventing drowsiness by extracting feature points for the face of the driver and acquiring information on the driver's drowsiness state based on the feature points. 3. The method of claim 2,
The feature point is extracted along a periphery of the driver's mouth or eyes,
The server is
and when the feature point moves more than a predetermined length, defining the driver's state as a drowsy state. According to claim 1,
The speaker is to output a pre-input dialog (dialog) as a voice, driver's drowsiness prevention system. According to claim 1,
The input device is a wearable keyboard worn by the driver, the driver's drowsiness prevention system. delete delete delete delete delete delete

Images