JPS6141903A - Recognizing device for position of eye of vehicle driver - Google Patents

Abstract

PURPOSE:To recognize the accurate positions of driver's eyes by estimating parameters, i.e. two singular point positions of the face part of a driver in image data detected by an image detecting means. CONSTITUTION:A light emitting part 5 which irradiates the upper body of the driver slantingly from left and an image detection part 6 which receives reflected light traveling from the driver through the irradiation of the light emitting part 5 and picks up an image of at least the face part of the driver from leftward as two-dimensional image data are provided in front of a navigator's seat. Then, an image signal processing part 8 controls the image detection part 6 and detect two singular point positions on the face part of the driver from image data stored after A/D conversion through a CPU14, ROM16, and RAM18 and recognizes the three-dimensional position of the driver from those two singular point positions in a series of processes.

Description

Detailed Description of the Invention [Industrial Application Field] The present invention relates to a vehicle driver's eye position RFL recognition device that recognizes the position of the vehicle driver's eyes. 3 of the driver's eyes based on the two types of singularity positions.
This invention relates to a vehicle driver's eye position amount &It device that recognizes dimensional position.

[Prior art] With the rapid development of electronic equipment in recent years, research into new MA4 is underway with the aim of improving vehicle operability, comfort, accident avoidance, etc. riding position,
In particular, it recognizes the position of the eyes and adjusts the angle of the rearview mirror, air-conditioned air outlet, or steering wheel, etc. It also detects drowsy driving and alerts the driver. The idea is to give information.

By the way, as an eye position recognition device for recognizing the position of the eyes in the driver's cab used in the above-mentioned A, II Ill, conventionally, the driver's upper body is captured as image data at two locations in front of the driver's seat, for example. An image detection unit is installed, and the 21 black areas in the horizontal direction of the face in the image data are estimated as the positions of the eyes, and the three-dimensional position of the eyes is recognized using the principle of triangulation. An image detection unit is installed at a location 1rB diagonally forward of One idea is to recognize the three-dimensional position of the eyes assuming that there is no movement in the left-right direction. However, in the case of the latter recognition device, the error is large because the eye position is simply estimated from one singular point position, and it is difficult to accurately recognize the eye position. There is a problem in that it is difficult to recognize the position of the eyes.

[Object of the Invention] The present invention has been made to solve the above problem, and the position of the eyes is estimated from the positions of two types of singular points on the driver's face in the image data obtained by the image detection unit. The purpose of this is to enable accurate recognition of the position of the eyes.

[Structure of the Invention] As shown in FIG. 1, the structure of the present invention to achieve the above object includes a light emitting means (2) for illuminating the vehicle driver (2), and a light reflected from the pre-driving type by the illumination of the light emitting means. image detecting means (2) for detecting at least the pre-driving type facial region as image data; and a singular point position for detecting a singular point position at a predetermined position 21a of the driver's facial region in the detected image data. Using the detection means IV and the detected singular point position of 2Ia as a parameter, the upper 3il! of the vehicle is detected. The gist of the present invention is a vehicle driver's eye position recognition device characterized by comprising: an eye position mapping means V for calculating the three-dimensional position of the driver's eyes.

[Example] An embodiment of the present invention will be described below with reference to the drawings.

Figure 2 shows the eye position recognition device of this embodiment installed! l
It is a perspective view showing the instrument panel part and its surroundings of the i-car, where 1 is the driver, 2 is the driver's seat, and 3 is the instrument panel. and the diagonally forward left side of the instrument panel 3 relative to the driver's seat 2, that is,
In front of the passenger seat side, there is a light emitting unit 5 that illuminates the driver's upper body from the left, and a light emitting unit 5 that receives reflected light from the driver 1 due to the illumination of the light emitting unit 5, and illuminates the driver's upper body from the left. An image detection unit 6 that captures a two-dimensional image is provided. ~Here, the light emitting unit 5 corresponds to the above-mentioned light emitting means (2), and an infrared strobe that emits infrared light is used so as not to dazzle the driver 1 when irradiating the light, as shown in Fig. 3. , an infrared light emitter 5a, a lens 5b for broadly irradiating the driver with infrared light emitted by the infrared light emitter 5a, and an infrared filter 5c that transmits infrared light but blocks visible light. and a case 5d for storing the infrared light emitter 5a, lens 5b, and infrared filter 5c and attaching it to a predetermined position on the instrument panel 3.

Further, the image detection section 6 corresponds to the above-mentioned image detection means (2), and is for capturing the foul light from the driver 1 caused by the irradiation of the light emitting section 5 as an image of the driver's 1 body. 6, as shown in FIG. 4, reflected light from the driver 1;
That is, an infrared filter 6a for transmitting infrared light, and a lens 6b having a focal length of, for example, 12.511111 for focusing an image of the driver's 1's body on an imaging surface of a solid-state scanning @ element 6e, which will be described later. , a liquid crystal diaphragm element 6c for adjusting the light m, a foot drive transistor d for detecting the amount of light transmitted through the liquid crystal diaphragm element 6C, the infrared filter 6a, and the lens 6b.
and a MOS consisting of a photosensor and a switching circuit, which extracts the image on the 'Ffi image plane transmitted through the liquid crystal aperture element 6C and formed as an electric signal by switching scanning.
A solid-state camera is used, which is composed of a solid-state image sensor 6C, and a case 6f for storing the above-mentioned parts and attaching it to the instrument panel 3.

Next, the overall configuration of the eye position recognition device of this embodiment will be explained based on the block diagram shown in FIG. 5.

As shown in the figure, in addition to the light emitting unit 5 and image detecting unit 6, this recognition device processes image signals obtained by the image detecting unit 6, and performs image signal processing to recognize the position of the eyes of the driver 1. It is equipped with part 8. The image signal processing section 8 controls the image detection section 6, converts the image signal obtained by the image detection section 6 into a digital signal, and temporarily stores the converted digital signal as image data. an irradiation signal output section 12 that outputs an irradiation signal for causing the light emitting section 5 to emit light; Detects two singular point positions (0 and chin position in this example) on the face of the driver 1 from A central processing unit (CPU) 14 that executes the eye position recognition process, and a one-drive only memory (ROM) in which control programs and data for executing the eye position recognition process in the CPtJ 14 are stored in advance.
16, and a random access memory (RAM) into which data used for performance processing is temporarily read and written.
18, a path line 20 that connects each of the above sections and serves as a path for image signals and control signals, and a power supply circuit 22 that supplies power to each of the above sections.

Next, the eye position recognition processing performed by the CPU 14 of the image processing section 8 will be described in detail with reference to the flowchart shown in FIG.

When the process is started, first in step 101, a light emission process is executed in which the irradiation signal output section 12 outputs an irradiation signal in order to cause the light emitting section 5 to emit light.

This process is carried out by the synchronization signal generation circuit 10a of the image data input section.
This is to cause the light emitting unit 5 to emit light in synchronization with the vertical synchronization signal output from the vertical synchronization signal, so that good image data can be obtained at the image data input unit, as shown in FIG.
The irradiation signal is output after a predetermined delay time ΔT has elapsed from the rise time of the vertical synchronization signal so that the light emission of the light emitting unit 5 coincides with the vertical retrace time [1]. In this way, one physical information signal is converted into a digital signal by the light emitting unit 5, and the digital signal is stored as image data in the image data storage circuit 1Qc.

In this image data storage circuit 10c, since the light emitting section 5 and the image detecting section C are provided diagonally forward to the left with respect to the driver's seat 2, the driver 1 is placed on the left as shown in FIG. The image taken diagonally from the front is shown in Figure 9.
Image data G (0, ~ O)...G (239, 255>
is stored as.

Next, in step 102, a predetermined area set in advance in the image data, that is, 30 areas shown in FIG. A pixel with brightness is searched (hereinafter referred to as score search) and its position is stored.This process is a process to limit the outside search range when detecting the position of the nose in the next step 103. The position of the determined pixel is used as the base point for searching for ^.In this bright spot search process, the existence area 30 of Fig. 8 is used.
Starting from the pixel at the upper left end of , the search is performed sequentially in the vertical direction, and the position of the first pixel whose brightness is higher than a certain level is stored.

When the bright spot search is executed in this way and the position of the pixel that exists on the left side of the existence area D and has a brightness above a certain level is determined, this position is determined in step 103, which follows as described above. The nose position is determined by searching for the base point, but this process involves searching for a preset first pixel in the vicinity of the bright spot search.
The degree of correlation between the image data and the standard pattern of the sister roar shown in Figure 0 is examined, and the position of the image where the correlation is maximum is considered to be the position where the nose exists, and the position of the nose is determined. .

In other words, the digit 1 of the pixel found in step 102 above
Centering on iiiG(x, y), as shown in FIG.
Center position in the standard pattern of the fold shown in Figure 0 (
0, 0), and calculates the correlation value between the image data and the standard pattern, and recognizes the pixel position where the value is the largest as the position of the tip of the nose (the so-called head of longevity) @G (hx, hy). Here, the center position affm (0, 0) in the standard pattern of Fig. 10 is set in advance as a part corresponding to the tip of the nose, and the correlation value is given by the following formula 1
It can be obtained from the formula %). The problem with i and j above is that the standard pattern of the nose is configured as data with a spread of 16 on the top, 7 on the bottom, 1 on the left, and 6 on the right with respect to the center (0, O). Therefore, i has (-1) to (+6
), an integer value between (-16) and (+7) may be used for j.

Also, the correlation value is the center position ff1 in the standard pattern of the nose.
It is calculated by applying a total of 121 pixels to ll(0,0), 5 pixels each on the top, bottom, left and right of the image data shown in Figure 11, centering on pixel G (x, y). Therefore, the values of X and Y in the above formula are, respectively,
An integer W1 where X is between X±5 and Y is between y±5. w1, and in the end a maximum of 121 correlation values are calculated by combinations of X and Y, and the maximum value is pixel G (X
SY) is detected as the nose position G (hx, hy).

Once the longevity digit ff1G (hx, hy) is determined in this way, the process moves to the subsequent step 104, where the position of the jaw is determined based on this 0 digit @G (hx, by). Here, when trying to find the position of the jaw,
First of all, the nose is v! 10 to the right of tG (hx, hy),
The position of the pixel shifted down by 35 ff1G (hx+10,
hy+35) is determined, and the degree of correlation between the image data and a standard jaw pattern as shown in FIG. 12, which has been set in advance in the neighborhood of n, is determined, and the jaw position fHG (aX, ay) is determined. Note that this determination method is based on step 10 above.
Since this can be done in the same manner as the position determination in No. 3, the explanation will be omitted.

In the following step 105, the ^ position @G (hx, hy) on the pixel data obtained in the above steps 103 and 104 and the jaw position Q (ax, ay
), calculate the digit 1G (IX, my) using the following formula (where 1, 2, and 3 are constants). For the values of gear 1, stand 2, and i3, images of multiple vehicle drivers may be taken in advance and the average data may be used.The required eye position VI G (mxSmy) and nose position G (hx , hy) and jaw position G (axlay
) is as shown in FIG.

Once the eye position G (ax, my) on the pixel data is determined through the processing in steps 102 to 105, the process moves to step 106, where the three-dimensional position of the driver 1's eyes in the vehicle interior is determined. Prizes are sought.

In this embodiment, since the image detection section 6 is fixed, the eye position G (ix, my) obtained in step 105 above is determined in the image obtained by this.
Using this, the three-dimensional position of the eyes is determined assuming that the driver 1 does not move in the left-right direction. In other words, assuming that the driver 1 does not move in the left-right (Z) direction shown in FIG. YSO), the position of the eyes can be recognized. Note that this process is performed because the image detection section 6 is fixed.
The position G(px, py) of the standard point P on the image data is stored in advance and this reference position ff1G(px.

This can be easily carried out by calculating the deviation of the eye position G (mx, my) with respect to py).

As explained above, the eye position recognition device of this embodiment processes the image data obtained by one image detection unit 6 provided diagonally in front of the driver's seat 1, and 21i! (ii) Recognizing the three-dimensional position of driver 1's eyes from the singular point position (agreed). It demonstrates its ability as a method for detecting the position of the eyes when wearing glasses or sunglasses.Therefore, the eye position recognition device of this embodiment can be used to automatically adjust the angle of the rearview mirror and prevent drowsy driving. in case of,
It will be possible to carry out more precise control of the country.

In this embodiment, one image detecting section 6 consisting of a MOS type solid-state m-image element installed obliquely in front of the driver's seat is used as the image detecting means (2). Two parts 6 may be provided in front of the driver's seat to recognize the three-dimensional position of the driver's eyes using the principle of triangulation, in which case the driver's movement in the left and right direction may be detected. However, the three-dimensional position of the eyes can be recognized accordingly, resulting in a more accurate eye position recognition device. In addition, the image detection section 6 is a MOS type solid-state device (
In addition to the 9 elements, other solid-state imaging elements such as COD may also be used.

In addition, in this embodiment, J3 includes the above-mentioned singularity position detection means IV.
Steps 102 to 104 in the eye position recognition process shown in FIG.
Examples of the process executed in step 105 and step 106 correspond to the eye position calculation means V. In this embodiment, the position of the nose and the position of the chin are detected as the singular point position of 2Zii, but this means that when the driver 1 is viewed from the front left, the position of the nose and chin is 8. This is because it is the easiest position to detect, and when capturing the driver 1 from the front as described above, for example, the position of the jaw and the position of the ear may be detected as the singularity position. Alternatively, the position of the mouth may be detected as one singular point position.

[Effect of the Invention 1] As detailed above, the vehicle driver's eye position recognition device of the present invention includes a light emitting means for illuminating the vehicle driver, and an image of the reflected light from the driving position caused by the illumination of the light emitting means. The image detection means detects data as data, and is configured to recognize the three-dimensional position of the vehicle driver's eyes from two singular point positions on the image data. Therefore, even if the vehicle driver is wearing glasses or sunglasses, the position of the eyes can be recognized well, and the eye position can be recognized with higher accuracy than simply recognizing the three-dimensional position of the eye from the position of the singular point at 1gI. be able to recognize the location of

[Brief explanation of drawings]

FIG. 1 is a block diagram showing the configuration of the present invention, FIGS. 2 to 14 show an embodiment of the present invention, and FIG. 2 is a perspective view showing the instrument panel of the vehicle of this embodiment and its surroundings. , FIG. 3 is an explanatory diagram of the light emitting unit 5, FIG. 4 is an explanatory diagram of the image detecting unit 6, FIG. 5 is an overall configuration diagram of the eye position recognition device of this embodiment, and FIG. 6 is an explanatory diagram of the eye position recognition device. 7 is an explanatory diagram of the light emission process, and is a time chart showing the relationship between the vertical synchronization signal, the irradiation signal, and the light emission timing of the light emitting unit 5. FIG. FIG. 9 is an explanatory diagram showing the image data, FIG. 10 is a data diagram showing the 43 semi-patterns, and FIG. 11 is an image of the driver 1 captured by the camera. Explanatory diagram, 1st
Figure 2 is a data diagram showing the standard pattern of the jaw, Figure 13 is an explanatory diagram of the eye position protrusion processing, and Figure 14 is an explanatory diagram explaining the three-dimensional position of the eyes. 1 is a plan view of the driver 1, and (b) is a side view of the driver 1. ■... Light emitting means ■... Image detecting means IV.
...Singular point position detection means■...Eye position calculation means 5...Light emitting section 6...Image detection section 8...
Image No. 48 processing section 10...Image data input section 12...Irradiation (No. 3 output section 14...CPU

Claims (5)

[Claims] 1. a light emitting means for illuminating a vehicle driver; an image detecting means for receiving reflected light from the driver due to the illumination of the light emitting means and detecting at least the face of the driver as image data; and the detected image data. a singular point position detection means for detecting two predetermined singular point positions on the driver's face; and using the detected two singular point positions as parameters,
An eye position recognition device for a vehicle driver, comprising: eye position calculation means for calculating a three-dimensional position of the driver's eyes in the vehicle. 2. The vehicle driver's eye position recognition device according to claim 1, wherein the two singular points are the driver's nose and chin. 3. A vehicle driver's eye position recognition device according to claim 1 or 2, wherein one image detection means is provided diagonally in front of the driver's seat. 4. A device for recognizing the position of the eyes of a vehicle driver according to any one of claims 1 to 3, wherein the image detection means comprises a two-dimensional solid-state image sensor. 5. A device for recognizing the position of a vehicle driver's eyes according to any one of claims 1 to 4, wherein the light emitting means is configured to emit infrared light.