KR20060126352A - Drowsiness detection using reflected image on eye iris - Google Patents

Abstract

A method and an apparatus for detecting drowsiness using a reflected image on an eye iris are provided to accurately detect whether a driver is sleepy by using a visual ray blocking unit. An optical source(110) irradiates a predetermined near IR(InfraRed) ray on a user's face to obtain a face image. An image acquiring unit(130) acquires the near IR ray face image for a predetermined time interval after a vehicle is started and extracts the shape of the image of the optical source, which is focused on an eye iris. The acquired image is determined to be an arousal state. A visual ray is removed from the image of the user's face by using a visual ray blocking unit(120). The shape of the optical source image focused on the iris is extracted from the near IR ray face image. An image processor(140) compares the obtained image with the arousal state image to determine whether user's eyes are closed. The image processor detects drowsiness based on the duration of the closed eyes. An alarm generator(150) generates alarm sound to the user based on the detected result from the image processor.

Description

Drowsiness detection using reflected image on eye iris}

1 is a block diagram showing an embodiment of an iris reflection image-based drowsiness detection apparatus according to the present invention

FIG. 2A is an image obtained when no visible light is blocked, FIG. 2B is an image when a visible light blocking filter is used without a near infrared light source, and FIG. 2C is a face obtained when a visible light blocking filter is used and a near infrared light source is used. Drawing showing the image of

Figure 3 is a flow chart showing an embodiment of the iris reflection image-based drowsiness detection method according to the present invention

4 is a diagram illustrating an example of a face image for extracting a shape of an image of a light source according to the face image processing of FIG. 3;

Explanation of symbols for main parts of the drawings

110: light source unit 120: visible light blocking unit

130: image acquisition unit 140: image processing unit

150: alarm generator 200: camera phone

The present invention relates to an apparatus and a method for detecting drowsiness, and in particular, after a near infrared ray is irradiated to a human face and a near infrared ray face image is obtained by using a camera equipped with a visible ray blocking unit, the obtained near infrared ray face image is obtained. Search for the image of the light source formed on the iris having high reflectance and convex mirror shape in response to the irradiated infrared light, and determine the eyes closed according to the deformation of the image of the light source, and detect drowsiness based on the information of the duration, The present invention relates to an iris reflection image-based drowsiness detecting apparatus and method for discriminating.

When the drowsiness comes while driving the vehicle is very likely to develop into a large personnel accidents, prevention of drowsy driving is a very important problem in preventing vehicle safety accidents, and various technical approaches are taken to prevent such drowsiness driving have.

Conventional technology detects and determines whether the driver is asleep by using physical characteristics, especially the closed pattern of the eyelids on the face or the shape of the pupil when the user is sleepy, and alerts by alerting when the driver is asleep. A technique for making it known is known.

To do this, a person's face is photographed with a camera to acquire a face image, and the position of the eye is found from the acquired face image to detect whether it is dozing in accordance with the gap between the upper and lower eyelid borders or to find a pupil in the eye. How to detect the drowsiness by detecting the deformation form from the original form of is introduced.

In the prior art, a method of detecting an eye position extracts all boundary lines due to contrast differences from a face image acquired by a camera, and from this, the geometric of the face such as the distance between both eyes and the distance between the eyes and the nose, and the position of the eyebrows and eyes The element was calculated to find the eye position.

However, the disadvantage of this method is that the lighting conditions of the face such as the change of light direction, backlight or shadow are constantly changing while the vehicle is running, and when the glasses are worn, it is difficult to accurately locate the eyes due to the light or the image reflected on the glasses. Even though the eye position is found, the difference in brightness decreases, making it more difficult to extract the border of the eyelid.When detecting the deformation of the pupil, the contrast between the iris and the pupil is not large and the pupil size is very small in bright and dark conditions. This almost impossible problem has been an obstacle to practical use.

In addition, in the prior art, since the geometrical characteristics of both eyes, nose and nose change according to the direction of the face or the head bowing, it is frequently detected that the eyebrows, the nose, the eyeglass frame, etc. are not the eyes, so that the drowsiness driving judgment There is a disadvantage that the reliability of information that can be used as a basis is low, and due to such problems, errors in detecting and determining drowsiness are not practical.

Accordingly, the present invention has been made to solve the above problems, and after the near-infrared ray is irradiated to the face of a person and obtained by using a camera equipped with a visible ray blocking unit, the near-infrared face image from which the visible ray is removed is obtained. Search for the image of the light source formed on the iris having high reflectance and convex mirror shape in response to the irradiated infrared light in the near-infrared face image, and judge the eyes closed according to the deformation of the image of the light source and drowsiness based on the information of the duration An object of the present invention is to provide an iris drowsiness detection apparatus and method for detecting and determining whether the iris is reflected.

A feature of the iris reflection image-based drowsiness detection apparatus according to the present invention for achieving the above object, the light source unit for irradiating a predetermined near-infrared rays to the face of a person to obtain a face image; When the vehicle is started in conjunction with the light source unit or the device is turned on, a near-infrared face image is acquired for a predetermined time to extract a shape of the light source formed on the iris and defined as a high arousal state. An image acquisition unit equipped with a visible light blocking unit for obtaining a near infrared face image in which visible light is blocked from a face image of a person irradiated with near infrared rays; The shape of the image of the light source formed on the iris is extracted from the near-infrared face image acquired by the image acquisition unit, and the shape of the image of the light source is compared with the standard shape obtained at the point of high arousal, and the eyes are closed according to the degree of deformation. An image processing unit for grasping and judging whether or not to fall asleep with information of a duration of time when judging eyes closed; And an alarm generator configured to generate a drowsiness alert to the driver according to the result of determining whether the image is drowsy.

A feature of the iris reflection image-based drowsiness detection method according to the present invention for achieving the above object is (a) a face image irradiated with near infrared rays toward the face to obtain a face image through the light source unit Blocking the visible light through the visible light blocking unit to obtain a near-infrared face image from the image acquisition unit; (b) extracting, by the image processor, the shape of the light source image formed on the iris having a convex mirror shape from the near-infrared face image obtained in step (a); (c) The driver's arousal degree is defined when the image of the light source formed on the iris is extracted by taking a near-infrared face image for a predetermined time after the vehicle is started or the device is turned on. Searching for whether is high and storing the driver's light source image in a standard form when the arousal is high, and calculating a difference between the extracted form of the light source image and the standard form; (d) comparing the difference value calculated in the step (c) is greater than the first threshold value, and comparing the difference value if the difference value is greater than the first threshold value and comparing the duration value to the second threshold value. If it is larger than the threshold value comprises the step of generating an alarm through the alarm generator.

Other objects, features and advantages of the present invention will become apparent from the following detailed description of embodiments taken in conjunction with the accompanying drawings.

Hereinafter, a preferred embodiment of the iris reflection image-based drowsiness detection apparatus and method according to the present invention will be described.

1 is a view showing an embodiment of an iris reflection image based drowsiness detecting apparatus according to the present invention, the light source unit 110, visible light blocking unit 120, image acquisition unit 130, image processing unit 140 And an alarm generating unit 150.

The light source unit 110 irradiates a predetermined near-infrared ray on the face of a person in order to acquire a face image.

The light source unit 110 may use any one of near-infrared LED, near-infrared lamp, and strobe as a near-infrared light source. The light source unit 110 may be embedded in the image acquisition unit 130 or may be provided in a form separated from the image acquisition unit 130. can do.

The image acquisition unit 130 extracts the image of the light source image formed on the iris by acquiring a near-infrared face image for a predetermined time after the vehicle is started or the device is powered on in conjunction with the light source unit 110. When it is defined as a state of high arousal, the visible light blocking unit 120 for acquiring the near infrared face image from which visible light is blocked from the face image of the person irradiated with the near infrared ray is mounted.

The visible light blocking unit 120 may be installed outside the image acquisition unit 130.

The image acquisition unit 130 may use a digital camera as well as a general CCD camera or CMOS camera, it is installed in a suitable place around the driver's seat facing the driver's face.

The image processor 140 extracts a shape of a light source formed on the iris from the near-infrared face image acquired by the image acquisition unit 130 and compares the shape of the light source image with a standard shape obtained at a high arousal point. Determine the eyes closed according to the degree of deformation and judge the sleepiness based on the information of the duration when the eyes are closed.

The alarm generation unit 150 generates a drowsiness alert to the driver according to the result of determining whether the image is sleepy by the image processor 140.

The image acquisition unit 130, the image processing unit 140, and the alarm generation unit 150 may use a camera phone 200 or a mobile terminal that may be built in or external to the camera phone 200 or a mobile terminal.

FIG. 2A is an image obtained when no visible light is blocked, FIG. 2B is an image when a visible light blocking filter is used without a near infrared light source, and FIG. 2C is a face obtained when a visible light blocking filter is used and a near infrared light source is used. 3 is a flowchart illustrating an embodiment of an iris reflection image-based drowsiness detection method according to the present invention, and FIG. 4 is a diagram illustrating extracting an image of a light source according to the facial image processing of FIG. 3. A diagram illustrating an example of a face image for the sake of simplicity.

An iris reflection image-based drowsiness detection apparatus and method according to the present invention configured as described above will be described in detail with reference to FIGS. 1 to 4.

First, as shown in Figures 1 and 3, when the light source unit 110 is installed in front of the driver's seat so that the image of the light source is formed in the center portion of the iris, the near-infrared rays are irradiated with the driver's face to form the convex mirror. Because of the shape, the image of the light source always forms on the iris unless the geometric position of the eye and the light source is significantly changed (S1).

Then, the visible light blocking unit 120 blocks the visible light as shown in FIG. 2B from the face image as shown in FIG. 2A irradiated from the light source 110 and reflected from the face, and thus is shown in FIG. 2C. The near-infrared face image is output as shown (S2).

Subsequently, the image acquisition unit 130 interlocks with the light source unit 110 and acquires a near-infrared face image for a predetermined time after the vehicle is started or the device is turned on, and extracts the shape of the image of the light source formed on the iris. When it is defined as a state of high arousal, the visible light removing unit 120 as shown in FIG. 4 acquires a near-infrared face image of the driver whose visible light is blocked (S3).

Then, the image processing unit 140 in the near-infrared face image acquired by the image acquisition unit 130, as shown in Figure 4a the image portion of the light source formed on the iris appears bright and the iris portion around the dark appear in the face image The brightness difference between the adjacent pixels having the highest brightness and displayed as the comparison area as shown in FIG. 4B is found to find a pixel area of a predetermined value or more, and the position and shape of the image of the light source are extracted (S4).

The standard form of the image of the light source is an example of a point in time at which the driver's arousal is high and is acquired and stored at the same point in time as when the vehicle is started (S5 and S6).

As illustrated in FIGS. 4C and 4D, the image processor 140 detects a shape of the extracted image of the light source and compares the shape with a stored standard shape (S7) so that the degree of deformation is greater than the first threshold. If it is large, it is determined that it is a sign of drowsiness (S8), and if the duration is greater than the second threshold (S9) it is determined that it is dozing, and outputs an alarm signal.

Accordingly, the alarm generating unit 150 generates an alarm in accordance with the alarm generating signal output from the image processing unit 140 (S10).

As described above, the iris reflection image-based drowsiness detecting apparatus and method according to the present invention has the following effects.

First, a near-infrared face image is obtained by irradiating near-infrared light on a human face and removing the visible light by using a camera equipped with a visible light blocking unit, and then, among the acquired near-infrared face images, pixels in the surrounding area having the highest brightness By finding a group of pixels whose brightness difference is greater than or equal to a certain value, the image of the light source formed on the iris can be searched, and the eyes are closed according to the deformation of the light source image, and whether the sleepiness is detected based on the information of the duration, Can be determined.

Second, it is not affected by changes in lighting conditions, does not need to detect geometric elements such as eyes, nose and eyebrows, and is not significantly affected by wearing glasses or sunglasses, and also works robustly in changing relative positions of the camera and face. There will be almost no alarm errors that can be made.

Thirdly, it is not necessary to detect the geometrical features of the face to search the position of the eye, and it is easy to detect the position of the light source image from the obtained image without the need to detect the boundary of the eyelid or the shape of the pupil. This eases the algorithm for determining sleepiness and makes the processing very fast.

In addition, by blocking visible light, high accuracy can be obtained because it can minimize the reflection of the image or light formed on the lens even when wearing glasses or sunglasses, as well as in environments with poor external contrast conditions such as in direct sunlight, at night, or in dark tunnels. Because of the convex mirror shape, even if there is a change in the position and posture of the driver's face, the image of the light source is formed on the iris, so the detection rate of the image of the light source is high.

Those skilled in the art will appreciate that various changes and modifications can be made without departing from the spirit of the present invention.

Therefore, the technical scope of the present invention should not be limited to the contents described in the embodiments, but should be defined by the claims and their equivalents.

Claims (8)

A light source unit for irradiating a predetermined near-infrared ray on a face of a person to acquire a face image; When the vehicle is started in conjunction with the light source unit or the device is turned on, a near-infrared face image is acquired for a predetermined time to extract a shape of the light source formed on the iris and defined as a high arousal state. An image acquisition unit equipped with a visible light blocking unit for obtaining a near infrared face image in which visible light is blocked from a face image of a person irradiated with near infrared rays; The shape of the image of the light source formed on the iris is extracted from the near-infrared face image acquired by the image acquisition unit, and the shape of the image of the light source is compared with the standard shape obtained at the point of high arousal, and the eyes are closed according to the degree of deformation. An image processing unit for grasping and judging whether or not to fall asleep with information of a duration of time when judging eyes closed; An iris reflex image-based drowsiness detection apparatus comprising an alarm generator for generating a drowsiness alert to a driver according to a result of determining whether drowsiness in the image processor. The method of claim 1, The light source unit is arranged so that the shape of the light source reflected on the iris of the eye by arranging the near-infrared LED (LED) in a circular or vertical manner so that the deformation can be easily detected as the eyelid is closed. . The method of claim 1, The visible light blocking unit is an iris reflection image-based drowsiness detection device, characterized in that for blocking the initial light by attaching a lyrics light blocking filter to the image acquisition unit. The method of claim 1, The image processor In the near-infrared face image acquired by the image acquisition unit, the position and shape of the image of the light source are extracted by finding a pixel group having the largest brightness value of each pixel and a difference in brightness values of pixels in a peripheral comparison region of a constant distance or more. Drowsiness detection device based on the iris reflection image, characterized in that. The method of claim 1, The image processor When the image of the light source formed on the iris is extracted by defining a near-infrared face image for a predetermined time after the vehicle is started or the device is turned on, and defined as a high arousal state, each driver's awake state is Acquire the shape of the image of the light source obtained at a high state and store it in a standard form, and compare the shape of the image of the light source, and if the change value is larger than the first threshold value, it is determined as a sign of eye closure and if the duration is larger than the second threshold value An iris reflex image-based drowsiness detecting apparatus, characterized in that it is determined to be sleepy to generate an alarm. The method of claim 1, Install a light source block for irradiating near infrared rays and a visible light cut filter for obtaining near infrared rays on a mobile phone or mobile terminal equipped with a camera, and use the camera embedded in a mobile phone or mobile terminal as an image acquisition unit. Iris reflection image-based drowsiness detection device, characterized in that the use of the built-in speaker to detect and alarm drowsiness by using as an alarm generator. (a) irradiating near-infrared toward the face to obtain a face image through the light source unit, and blocking the visible light through the visible light blocking unit in the near-infrared irradiated face image to obtain a near-infrared face image in the image acquisition unit; (b) extracting, by the image processor, the shape of the light source image formed on the iris having a convex mirror shape from the near-infrared face image obtained in step (a); (c) The driver's arousal degree is defined when the image of the light source formed on the iris is extracted by taking a near-infrared face image for a predetermined time after the vehicle is started or the device is turned on. Searching for whether is high and storing the image of the light source in a standard form when the arousal is high, and calculating a difference between the extracted form from each image and the standard form; (d) comparing the difference value calculated in the step (c) is greater than the first threshold value, and comparing the difference value if the difference value is greater than the first threshold value and comparing the duration value to the second threshold value. Iris reflection image-based drowsiness detection method comprising the step of generating an alarm through the alarm generator if the threshold value is greater than. The method of claim 7, wherein In step (b) From the near-infrared face image acquired in step (a), the pixel group having the largest brightness value of each pixel and a difference in brightness value of pixels in a peripheral comparison region of a constant distance or more is determined to find a position and shape of the image of the light source. Iris reflection image-based drowsiness detection method characterized in that the extraction from the processing unit.

Images