JPS6166906A - Recognizing device for vehicle driver position - Google Patents

Abstract

PURPOSE:To recognize the position of a vehicle driver by providing a light emitting means and an image pickup means which recognize a specific position of a driver precisely. CONSTITUTION:The recognizing device consists of a light emitting part 5, image detection part 6, and image processing part 8, and reflected light of irradiation light which illuminates the upper body of the driver leftward from the light emitting part 5 beside the navigator's seat of a vehicle is captures as a two-dimensional image by the image detection part 6 beside the navigator's seat. The image signal obtained by the image detection part 6 is converted by an image input part 10 into a digital signal, which is stored as image data. Then, the image data stored in the image input part 10 is supplied to a CPU14 to detect the singular point position of a specific part of the face part of the driver and, for example, the position of the nose of the driver is recognized from the singular point position. Thus, position recognition is performed precisely.

Description

DETAILED DESCRIPTION OF THE INVENTION (Summary of the Invention) The present invention provides a system for optically and electrically recognizing at least a curved surface of a vehicle driver as a recognition part. 1",
In order to maintain good recognition accuracy, the light emitting means and the imaging means are arranged in two ways.

(Field of Application of Industry-1-) The present invention captures the riding condition of a heavy vehicle driver as an image,
This invention relates to a device for recognizing the position of a vehicle driver that locates the vehicle driver's location within the cabin of the vehicle.

(Prior Art) With the rapid development of electronic devices, research is underway on new devices aimed at improving vehicle operation, comfort, etc. It recognizes the position of the driver's mouth and head and automatically adjusts the position and angle of the rearview mirror, headrest, air conditioner, etc., or the steering wheel, etc. One possibility is to detect drowsy driving based on periodic changes in the device and issue a warning to the driver. The riding position recognition device for recognizing the riding position of the vehicle driver, which is necessary to execute this L) control, takes an image of the vehicle driver's busy state and detects it as an image point. An image detection unit consisting of a camera, etc., analyzes the detected image by so-called image processing, and detects a predetermined position such as the position of the driver's head in the image. It is believed that the driver's position can be recognized by using a microphone and an image processing unit consisting of a computer, etc., to calculate the position of that part in the vehicle interior.

(Problems to be Solved by the Invention) The above-mentioned recognition device is required to accurately recognize a predetermined part of the driver's stroke, such as the position of the eyes or the position of the nose.

SUMMARY OF THE INVENTION An object of the present invention is to provide a vehicle driver (iγ7j) recognition device having an arrangement of a light emitting device and an imaging device that can accurately recognize a predetermined part of the driver.

(Means to solve the problem) Therefore, the present invention is a device that optically and electrically recognizes an area where at least the face of a vehicle driver is normally located as a recognized area (+'t). 1. The light emitting means for emitting a light beam to the recognition area is located at a predetermined first position with respect to the front and rear direction of the vehicle.
The imaging means, which is arranged at an angle and receives the inverse Il error from the recognition area due to the irradiation of this one stage of light and converts it into an electrical signal, is located at the front side of the driver's seat at a position where 1-i=identification is located. It is characterized in that it is arranged so as to have a predetermined second angle smaller than the first angle with respect to the longitudinal direction of the vehicle.

(Function and Effect) In the configuration L, the imaging means disposed at the front left side of the conductor in a right-hand drive vehicle (in the front right side of the cabin in a left-hand drive vehicle) cooperates with the light emitting means to illuminate the vehicle il! The image of the left side of the driver's face is converted into an electrical signal. In this case, the light emitting means illuminates the left side (right side) of the vehicle driver's nose and hardly illuminates the right (left) cheek, so the imaging means can clearly recognize the shape of the nose. In addition, the optical axes of the light emitting means and the imaging means are not obstructed by the passenger in the passenger seat.
Further, the obtained image may include a component in the front and rear directions of the vehicle driver.

(Example) A first embodiment of the present invention will be described below with reference to the drawings.

FIG. 1 is a perspective view showing the instrument panel part and its surroundings of a vehicle in which the occupant position recognition device of this embodiment is installed, where l represents the driver, 2 represents the driver's seat, and 3 represents the instrument panel. ing. The instrument panel 3 is diagonally forward to the left of the driver's seat 2, that is, in front of the passenger's seat.There is a light emitting unit 5 that illuminates the driver's body from the left, and a light emitting unit 5 that illuminates the driver's 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, and an infrared i-robo that emits infrared light is used so as not to dazzle the driver 1 at the time of daylight hours 1.1. As shown in the figure, the infrared light emitter 5a and the infrared light emitted by the infrared light emitter 5a are widely transmitted to the driver. :(A lens 5b for 1.1, an infrared filter 5C that transmits infrared light but does not transmit visible light, and stores the infrared emitter 5a, lens 5b, and infrared filter 5C, and and a case 5d for attaching to the panel 3 at a predetermined position.

Further, the image detection unit 6 corresponds to the above-mentioned imaging means, and as shown in FIG. A lens 6b having a focal length of, for example, 12.5 mm to form an image, and a liquid crystal aperture element 6C for adjusting the light.
a phototransistor 6d that is used to automatically adjust the aperture of the liquid crystal aperture element 6C and detects the amount of light transmitted through the liquid crystal aperture element 6c; - the infrared filter 6a; and the lens 6;
b and the image formed on the imaging surface through the liquid crystal aperture element 6C is taken out as an electrical signal by switching scanning.
A MOS-type solid-state image sensor 6e consisting of a photodiode array and a switching circuit, and a single storage space 6f for storing each of the 12 parts and attaching it to the instrument panel 3.
A solid-state camera consisting of

Next, the overall configuration of the vehicle position recognition device of this embodiment will be explained based on the block diagram shown in FIG. 4.

As shown in the figure, in addition to the light emitting section 5 and the image detecting section 6, this recognition device processes the image of the driver 1 captured by the image detecting section 6, and processes the driver's position (in this embodiment, The camera is equipped with an image processing unit 8 that recognizes the position of the nose. The image 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 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; and an irradiation signal output section 12 that outputs an irradiation signal for causing the light emitting section 5 to emit light. A central process detects the position of a singular point in a predetermined part of the person's face (in this example, the position of the tip of the nose), and executes a series of position recognition processes such as recognizing the position of the nose of the person when driving from this singular point position. ,
Thingunisoto (CPU) 14 and CP tJ 14
A read-only memory (ROM) in which control programs and data for executing position recognition processing are written in advance.
) 16 and random access memory (R
AM) 18, a lotus line 2o that connects the above sections and serves as a path for image signals and control symbols, and a power supply circuit 22 that supplies power to each section. The image input section 10 also includes a synchronization signal generation circuit 10a that generates a vertical synchronization signal and a horizontal synchronization signal to the image detection section 6, and an image signal obtained by the image detection section 6, for example, at 256. A/D conversion circuit 10b that converts into image data consisting of digital signals representing the brightness of 240 vertical pixels
and an image data storage circuit 10C capable of storing the converted image data for the past two frames.

Next, the operation of the position recognition process executed by the image processing section 8 will be explained in detail with reference to the flowchart shown in FIG. This process is executed when a request to recognize the position of the driver 1 is input by a signal of a certain number of laps or a signal from a switch. The position of the nose will be recognized as the position.

As shown in the figure, when the process is started, step 101 is first executed, and the image detection section 6 outputs an irradiation signal to the light emitting section 5 so that an image is detected when the light emitting section 5 emits light. An image data reading process is executed in which the detected image is stored in the image input section 10 as image data G consisting of a digital signal.

Here, the image input section 10 includes synchronization signal generation circuits 10a and A.
It is equipped with a /D conversion circuit 10b and an image data storage circuit 10c, and controls the image detection unit 6 according to the vertical synchronization signal and horizontal synchronization signal output from the synchronization signal generation circuit 10a, and detects the image output from the image detection circuit 10a. Since the image signals that are sequentially taken in and converted into digital signals via the A/D conversion circuit 10b can be recorded in the recording circuit 10c as image data G, the image data reading process is performed as follows: This can be easily performed by simply operating the input section 1o and causing the light emitting section 5 to emit light in synchronization with vertical synchronization (a) output from the synchronization signal generating circuit 10a.

In other words, as shown in FIG. 6, the vertical synchronizing signal first rises at the rising time t. After a predetermined time T has elapsed, an irradiation signal S is output to the light emitting unit 5 to cause the light emitting unit 5 to emit light in coincidence with the vertical blanking time ΔL1, and an image obtained by the light emission is read as image data G. It will be executed.

The image data G that is A/D-converted and stored in the image input section 10 is the image obtained by the image detection section 6, as described above, which is horizontally 256. It represents the brightness of pixels divided into 240 vertically, and as shown in Figure 7, the brightness G is determined for each pixel.
(x, y) is stored.

In this way, in step 101, the light emitting unit 5, the image (l
O) The detection unit 6 and the image input unit IO are braked, and the image input unit I
When the image data G is read in O, the following step 102 is executed, and a predetermined area in the image data G, that is, a region 30 not shown in FIG. A bright spot search process is performed in which a pixel on the left side having a constant brightness of -1- or more is searched and its (☆ position is written ↑a). This process is performed in the next step 103 when the driver Processing for limiting the range to search for the nose when detecting the position of the nose,
The determined positions of both key points are used as the base points for searching for the nose.

In this bright spot search process, starting from the upper left pixel in the nose existing area 30 in FIG. It can be executed by writing 1a.

When the bright spot search is executed in this way and the position of the pixel that exists on the leftmost side of the nose region and has a constant brightness equal to or higher than Hell is determined, in the subsequent step 103 as described above,
Processing is performed to search for the nose using this position as a base point and determine this process. The degree of correlation between the standard pattern and the image data is examined, and the position in the image where the correlation is maximum is regarded as the position where Zen exists, and the position of the nose is determined.

In other words, as shown in FIG. 11, centering on the pixel position G (x, y) found in step +02 of
- 5 pixels each on the bottom, left and right, Mll 21 pixels,
Nasal mark Y1-pattern c shown in FIG. 9: Calculate the correlation value between the image data and the mark Cp-pattern as the center position im (0, 0>), and calculate the pixel position where the value becomes the largest. is recognized as the nose position G (hx, hy). Here, the center position m (0, 0) in the standard nose pattern shown in Fig. 10 is preset as the part corresponding to the nose, and The correlation value can be obtained from the following formula % formula % ().Then, the values of ``-2i and j are 16 above and 7 below the standard pattern of the nose with respect to the center m (0, O). , is configured as data with a spread of 1 on the left and 6 on the right, so if we use a rectified value between (-1) and (+6) for i and between (-16) and (+7) for j, we get ,L.

Also, the correlation value is the center position m in the standard pattern
It is calculated by applying to (0, 0) a total of 121 pixels, 5 each on the top, bottom, left and right, centering on the pixel G (x, y>) on the image data as shown in Figure 11. Therefore, the values of X and Y in the above formula are
±5, Y becomes an integer value between y±5, and in the end, a maximum of 12] types of correlation values are calculated by the combination of X and Y, and the pixel G (X, Y) on the image data that has the maximum value is It is detected as the nose position G (hX, hy).

As explained above, the position recognition of the vehicle driver in this embodiment is
In the W position, when recognizing a predetermined part, it is configured to use the standard pattern of the predetermined part, so the riding position can be recognized more accurately without erroneously recognizing the position of the predetermined part. You will be able to do this.

Next, a second embodiment of the present invention will be described with reference to the drawings.

In this embodiment, 6i? ) Based on the recognized position of the nose of the vehicle driver 1, the position of the singular point (the center of the eye in this embodiment) of a predetermined region of the vehicle driver 1 other than the nose and the specific region (the center of the eye in this embodiment) are determined. ) position.

Regarding the operation of the position recognition process executed in this embodiment,
This will be explained in detail along the flowchart shown in FIG. Note that steps 201, 202, and 203 in this embodiment are the same as step 101 in the first embodiment.
．． Step! 02 and Ste Nobu IO3, so the explanation will be omitted.

Step 201. By sequentially executing steps 202 and 203, the nose position l c (hx, hY)
Once obtained, the process moves to the next step 204, where this nose position IG (h x ) is obtained.

The position of the eyes is determined based on hy). To find the position of the eyes here, first, the starting position G (h
The pixel position G (IIX + 12.hy-1) is 12 pixels to the right and 13 pixels rows above from x, rIy)
3), and find the first preset position near this position.
The degree of correlation between the eye standard pattern shown in Figure 2 and the image data was examined, and the eye position G (mx) was determined.

my). Note that this determination method may be performed in the same manner as the nose position determination in step IO in the first embodiment, so a description thereof will be omitted.

In the following step 205, the process is performed.

The position of the pixel data G-)- obtained in 204; 6
Based on G (mx, my), the three-dimensional (i
Execute the process to output 1γ from the 7th position. In other words, assuming that there is no movement in the left/right (Z) direction of the driving shown in FIG. 13, the driver's eyes (
left eye) mark? Considering a coordinate system in which the ili position iηP is J and IIX, the three-dimensional position M of the eye (left eye) of the driver 1 is determined as the coordinate (X, Y, 0) and the position of the eye is recognized. However, since the image detection unit 5 is fixed, this process requires
1 (Memorize the position G (px, r'y) of point P, and then calculate p, ((11!
This can be easily carried out by calculating the deviation of the eye device (mx, my) with respect to x, p y).

As explained above, the vehicle driver position recognition device of this embodiment is configured to recognize a predetermined region using a standard pattern of the predetermined region. It becomes possible to more accurately recognize the riding position without erroneously recognizing or recognizing the position of the body part.

Furthermore, in this embodiment, instead of directly determining the Q position of the driver's eyes from the image data, we first calculate the position of the tip of the nose that protrudes from the facial area, which is the part that is easiest to detect, in the image data at a predetermined location. As a singularity and the nose as a designated part ☆
Then, using the center of the eye as a singular point of a predetermined part and the eye as a predetermined part, the position of the eye is detected based on the previously determined nose position. Therefore, the riding position (left eye position) can be easily recognized.

In this embodiment, the position of the driver's 10th eye (more precisely, the position of the left eye) is recognized as the riding position of the vehicle driver. The three-dimensional position may be recognized as the position, and the process after recognizing the position of the driver in the vehicle, such as automatically adjusting the pack mirror or automatically adjusting the steering angle, may be performed. The vehicle may be configured to recognize the most appropriate riding position. However, when the position of the eyes of the driver 1 is recognized as in this embodiment, it can be used to automatically adjust the angle of the hack mirror or to detect drowsy driving.

Furthermore, in the first embodiment and the second embodiment, the above-mentioned light emitting means includes a light emitting section 5, and the imaging means includes an image detecting section 6.
As for the imaging means, as in the above embodiment, the image detecting section 6 is composed of a MOS type solid-state imaging device.
In addition, it may be made of an image sensor T used in a so-called solid-state camera, such as a CCD, and it is also possible to use an image pickup tube.

In addition, in the first embodiment and the second embodiment, the number of image detection units 6 is one, and image data of the driver captured from one direction is used to determine the position of the driver; Although the driver's movement in the left and right horn directions is not taken into account, two image detection units are installed at the stomach position.
If the configuration is configured to recognize the driver's riding position using the so-called l-truth of bigonal measurement, it is possible to detect the driver's movement in the left and right directions, and the three-dimensional position of the driver can be recognized more accurately. You will be able to do this.

In the first and second embodiments, an infrared strobe is used as the light emitting means (2), but continuous light such as an incandescent light may also be used.

Furthermore, in the first and second embodiments, in the bright spot search processing, the search is performed sequentially in the downward direction starting from the upper left corner, but all pixels in the nose existing area are ranked in search order. The search may be performed according to the ranking.

Further, in the first and second embodiments, the nose region is rectangular, but it may be circular or triangular, for example. In this case, if the search rank is assigned to the above pixel, i
Searching can be done more effectively by using this method in combination.

Furthermore, instead of directly processing the image data obtained by the imaging means to recognize the position, recognizing the position of the image data that has been subjected to edge detection processing or lateral differentiation processing can reveal the characteristics of the image data. This makes it clearer, allowing for more accurate position recognition.

[Brief explanation of the drawing]

Figures 1 to 13 [m show embodiments of the present invention;
The figures are perspective views showing the instrument panel and its surroundings of a vehicle to which an embodiment of the present invention is applied, FIG. 2 is an explanatory view of the light emitting unit 5, FIG. FIG. 4 is an overall configuration diagram of the riding position recognition device, FIG. 5 is a flowchart showing the operation of the image processing unit 8 of the first embodiment, and FIG.
7 is an explanatory diagram showing the irradiation image data G stored in the image input unit 10, FIG. 8 is an image diagram of the image data G, and FIG. The figure is a data diagram representing the signpost pattern of the residence, No. 1.
Figure 0 is an explanatory diagram of the (-7 position detection process), Figure 11 is the second
Fig. 12 shows the mouth mark (1c pattern); Fig. 13 shows the three-dimensional position of 1; In the explanatory diagram of Explanation-4, C1 (a) is a side view of the driver 1, and (1) is a side view of the driver 1. 5... Light emitting unit, 6... Image detection Section, 8... Image processing section, 10... Image input section, 14... c P LJ
. Agent B1 Riju Takashi Okabe Figure 13

Claims (1)

[Scope of Claims] A device for optically-electrically recognizing an area where at least the face of a vehicle driver is normally located as a recognition area, the device comprising A light-emitting means is arranged at a position having a predetermined first angle and irradiates light to the recognized region; A vehicle driver position recognition device comprising: an imaging means arranged at two angle positions and configured to receive reflected light from the recognition target area caused by irradiation of light from the light emitting means and convert it into an electrical signal.