JPS6166905A - Position of vehicle driver recognizing device - Google Patents

Abstract

PURPOSE:To recognize the position of a vehicle driver precisely by comparing image data which is obtained by detecting an image with infrared light with standard data on a specific position which is stored previously. CONSTITUTION:This device is equipped with a light emitting part 5, image detection part 6, and image processing part 8; and the processing part 8 consists of an image input part 10 which stores an image signal as image data, irradiated signal output part 12, CPU14 which performs position recognition processing for recognizing the position of a driver's nose, etc., by detecting the nose tip, etc., of the driver from the image data, ROM16, RAM18, bus line 20 as a signal path, and electric power circuit 22. Then, when the image data (face) is read in the input part 10 in a step 101, a step 102 is entered and a picture element (nose tip) having higher than brightness is retrieved in the image data and stored. The position in the image where the degree of correlation between the standard pattern of the nose and data is maximum on the basis of the position of the picture element is found in a step 103 and regarded as the position where the nose is present, thereby determining the position of the nose.

Description

[Detailed Description of the Invention] [Industrial Application Field] The present invention relates to a vehicle driver position recognition device that captures the vehicle driver's riding condition as an image and recognizes the vehicle driver's position in the passenger compartment. In particular, the (+7 position) of the vehicle driver is configured to accurately recognize the (
Q: This is related to question J.

[tlY, future technology] With the rapid development of modern electric equipment, vehicle operation↑-1,
Research is progressing on new devices aimed at improving safety, such as layered bamboo and accident avoidance. It recognizes devices and automatically adjusts the position and angle of rearview mirrors, headrests, air-conditioned air outlets, steering wheels, etc., and detects drowsy driving based on periodic changes in the position of the driver's eyes and head. Consideration is being given to providing a warning to the driver. The riding position recognition device that recognizes the riding position of the vehicle driver, which is necessary to execute such control, is capable of recognizing the riding position of the vehicle driver.
liWf&, an image detection unit consisting of a camera, etc. that detects the image, and the detected image is analyzed by so-called image processing, and the driver's eye position, head position, etc. on the image are determined in advance. It is being considered that the driver's position can be determined by detecting the position of the driver and calculating the position of the driver in the middle chamber by using a micro-ampicoter or the like. .

[Problems to be solved by the invention] Automatic adjustment of the positions and angles of the above-mentioned rearview mirror, headrest, air outlet, steering wheel, etc. In order to detect drowsy driving based on periodic changes in the driver's position and give a warning to the driver, it is necessary to accurately detect certain parts of the driver (such as the eyes (O position, It is necessary to recognize the location etc.

The object of the present invention is to accurately recognize the position of a vehicle driver by recognizing a predetermined part of the driver! ! The purpose is to provide the stomach.

[Means for Solving the Problems] As shown in FIG. an image detecting means (2) for detecting at least each image data of the driver's face when light control is received; 1st stage IV of singular point position detection to be carried out, ``--a position in the vicinity of the singular imaginary position 1d of the detected predetermined portion in the arranged image data, and pre-stored data of a standard pattern of the predetermined portion. While changing the position of the data of the standard pattern on the image data, the position recognition means V which has the maximum correlation obtained by comparing (1'/neck) is determined. The gist of this paper is a means for recognizing the position of F11 vehicle drivers, which is characterized by:

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

FIG. 2 is a J perspective view showing the instrument panel and its surroundings of a vehicle on which the passenger position recognition device of this embodiment is mounted, in which 1 is a driver, 2 is a driver's seat, and 3 is an instrument panel. It represents a panel. A light emitting unit 5 that illuminates the upper body of the driver 1 from the left side and a light emitting unit 5 that illuminates the upper body of the driver 1 from the left side are located diagonally forward to the left of the driver's seat = 5-2 of the instrument panel 1 to panel 3, that is, in front of the passenger seat side.
An image detection unit 6 is provided that can generate a two-dimensional image of the upper body of the user from the left direction.

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.
An infrared light emitter 5a, a lens 5b for broadly illuminating the driver with the infrared light emitted by the infrared light emitter 5a, and an infrared filter that transmits infrared light but blocks visible light. 5C, and a case 5d for storing the infrared emitter 5a, lens 5b, and infrared filter 5C and attaching them to a predetermined position on the instrument panel 3.

The image detecting section 6 corresponds to the above-mentioned image detecting means (2), and as shown in FIG. a
For example, the focal length for focusing on the m-plane is 12.5111
11 lens 6b, a liquid crystal aperture element 6C for adjusting the light, and a liquid crystal aperture element -〇- Used to automatically adjust the aperture of the 6C, and detect the light R passing through the liquid crystal aperture line F6c. Phototransistor 6
(1 and -1- A photodiode array and a switching system that take out the image formed on the IM plane after passing through the infrared filter a, the lens 6h, and the σ liquid crystal aperture element 6C as an electrical signal by switching scanning. MO consisting of circuit
A solid-state camera is used, which is composed of an S-shaped solid-state image sensor 6e and a case 6t for storing the above-mentioned parts and attaching them to the instrument panel 3.

Next, the overall configuration of the head position recognition device for riding while riding according to this embodiment will be explained based on the block diagram shown in FIG. 5.

As shown in the figure, this recognition device processes an image of the driver 1 captured by the image detection section 6 in addition to the second light emitting section 5 and the image detection section 6, and processes the driver's position (main position). In the embodiment, an image processing section 8 for recognizing the position of the nose is provided. 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 uses the converted digital 4:5 as image data. An image input section 10 that can be used for one-click memory; an irradiation signal output section 12 that outputs an illumination signal for causing the light emitting section 5 to emit light;
The singular point position of a predetermined part of the face of the driver 1 (in this example, the position of the nose) is detected from the image data converted and stored, and from this singular point position, the position of the nose of the driver 1 is detected. There is a central processing unit (CPU) 1 that executes a series of position recognition processes such as recognizing the position i, and an I that executes position recognition processes in the CPLJ1
, II Ill A read memory (ROM) 16 in which programs and data are stored in advance, and a read memory (ROM) 16 in which data used for arithmetic processing 1j are temporarily read.
a rung access memory (RAM) 18 to be
- It is composed of a pass line 20 that connects each of the above sections and serves as a path for image signals and other signals, and a power supply circuit 22 that supplies a Ti source to each of the above sections. The image input section 10 also includes a synchronization signal generation circuit 10a that generates a vertical synchronization signal and a vertical synchronization signal 8 to the image detection section 6, and an image signal obtained by the image detection section 6, for example, for one frame 11. Hit horizontal 25
6. A Δ/D conversion circuit 101) that converts the brightness of the pixel of 12'IO into an image f-even consisting of digital 4M numbers,
It is comprised of an image data storage circuit 10c capable of storing the converted two-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. Note that this process is executed when a request for driver 1's position *a is inputted by a signal of a certain period or a signal from a switch, etc., and as described above, in this embodiment, the 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. Image data reading in which the detected image is stored in the image input unit 10 as image data G consisting of digital signals! l! 1 Execute immediately.

−〇 − Here, the image input unit 10 outputs the synchronized 8 shots t[circuit IQa1
Δ/D conversion circuit 10;) and image data storage circuit 10C
The image detecting section 6 is operated in accordance with the vertical synchronizing signal and the horizontal synchronizing signal outputted from the eight synchronizing signal generating circuit 10a.
111w, the image signals output from the image detection unit 6 are sequentially taken in and converted into digital signals via the Δ/D conversion circuit 101), and the image signals can be stored as image data G in the storage circuit 10C. Therefore, as the main image data reading process, the image input unit 104! : operate,
This can be easily carried out by causing the light emitting unit 5 to emit light in synchronization with ν output from the synchronization signal generating circuit 10a. In other words, as shown in FIG. 7, after a predetermined time Δt has elapsed since the rising edge of the vertical synchronizing signal J-, the irradiation unit 5 is outputted with irradiation No. 18 S, thereby emitting light in coincidence with the vertical retrace Δt1. A process is executed in which the unit 5 emits light and the image 11 produced by the light emission is read as image data G.

Note that the image is A/D converted and stored in the image input section 10! As mentioned above, the %gator G represents the brightness of the pixels that are divided into 256 horizontally and 240 vertically the image obtained by the image detection unit 6, and each pixel is divided into 1 mm as shown in FIG. That light 1! IG (x, v) is stored.

In this way, in step 101, the light emitting section 5, the image detecting section 6
When the image input unit 10 is braked and the image data G is read in the image input unit 10, the subsequent step 102 is executed, and the area 30 shown in FIG. is defined as the area where the nose exists, and a bright spot search process is performed in which a pixel with a brightness of a certain level or higher that exists on the 0th side of this area is searched and its position is memorized.This process is as follows. When detecting the position of the driver 1 in step 103, the driver 1's nose is
! ! ! This is a process for limiting one range, and the determined pixel position is used as the base point for searching for the nose. In addition, in the tree score search process, etc., the pixel at the H-to end in nose existence 1jJ30 in FIG. This can be done by memorizing the position of the pixel.

When the bright point 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 brightness of a certain level or more to the right is found, in step 103, which follows from -, this (f /1ilt is used as a base point to search for the nose and determine the position of the nose. The degree of correlation between the standard pattern and the image data is examined, and the image with the maximum correlation w1 is regarded as the position where Kotobuki exists, and the position of the nose is determined.

In other words, centering on the pixel position G (x, y) determined in step 102 above, as shown in FIG. Kotobuki's l1tl shown in! The correlation value between the image data and the standard pattern is set as the center position j1m (0, O) on the pattern. ? The pixel position whose value increases by m is recognized as the nose position G (hx, hy). Here, number 4 on the nose in Figure 10! The center position @+a (0, O) in the quasi-pattern is set in advance as a part corresponding to the nose, and the correlation value can be obtained from the following formula. As for the above i and j, Kotobuki's standard pattern is configured as data with a spread of 16 above, 7 below, 1 at t, and 6 to the right with respect to the center m (0, O). Therefore, it is sufficient to use an integer value between (-1) and <-+-6) for i and between (-16> and (+7)) for j.

Also, the correlation value is the central position vIJ in the standard pattern of the nose.
II (0,0), as shown in Fig. 11, apply a total of 121 pixels, 5 each to the top, bottom, left and right of the image data 10 pixel G (X, V) as the center, 3 Since it is controlled, the numbers of X1Y that can be used in the above formula are as follows: X is an integer value between ×±5 and Y is an integer value between y±5, and in the end, the combination of X and Y has a maximum of 121 scales. Correlation 111I
pixel G
(X, Y) is detected as the nose position - 13 = G (hx, hy).

As explained above, the vehicle driver position recognition device of the present embodiment is configured to use the standard pattern of the predetermined region when performing J on the predetermined region. It becomes possible to more accurately recognize the riding position without erroneously recognizing '/ill.

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

In this embodiment, based on the position of the nose of the vehicle driver 1 recognized in the first embodiment, a singular point (in this embodiment, the center of the eye) of a predetermined part of the vehicle driver 1 other than the nose is detected. The position and the position of a predetermined part (in this example, the eyes) are recognized.

Regarding the operation of the position recognition device executed in this example,
This will be explained in detail with reference to 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 102 and step 103, so the explanation will be omitted.

= 14 − Nose position G(hx, hy) by sequentially executing steps 201, 202, and 203
is required, the process moves to the following step 204 and
Based on this nose position G (hx, hy>), the eyes (
◇They yelled when they asked for a place. To find the 10 positions of the eyes, first find the position of the nose Q (hx).

by) 12 pixels to the right and 13 pixels above ff1G (hX+ 12, hl/ -13)
The degree of correlation between the image data and the standard pattern of the eyes shown in Fig. 13, which is set in advance near the position of
) can be determined. Note that this determination method may be carried out in the same manner as the position determination of the nose of the stub 103 in the first embodiment, so the explanation thereof will be omitted.

In the following step 205, the eye position (3(a+x,
my), and assuming that the driver 1 does not move in the left-right direction, a process is carried out that uses the three-dimensional (On) of the driver's eyes in the middle room.In other words, the driver 1 shown in FIG. Assuming that there is no movement in the left/right (Z) direction of 1, drive while considering a coordinate system based on the standard <i position iff I) of the driver's eye (left eye) on the hill, which was determined by experiment. The coordinates (X
, Y, O), but since the image detection unit 5 is fixed, the position W of the standard point P on the image data is
IG (px, py) is memorized in advance, and the eye position G (IIX
, mV).

As explained above, in this embodiment! The position recognition device for the 11-vehicle driver is configured to recognize a predetermined part using a standard pattern of the predetermined part, so there is no chance of erroneously recognizing the position of the west predetermined part. This makes it possible to more accurately recognize the riding position.

Furthermore, in this embodiment, instead of directly determining the position of the driver's mouth from the image data, we first determine the position of the face-16 part J, which is the most easily detected part on the image data, and the position of the protruding nose. The position of the nose is detected by setting the center of the eye as a singular point of a predetermined part and the nose as a predetermined part, and then detecting the position of the nose obtained earlier by setting the center of the eye as a singular point of a predetermined part and setting the eye as a predetermined part. Since the eye position is detected based on the position, the riding width position i (left eye position If) can be easily recognized.

Further, in this embodiment, the position of the eyes of the driver 1 (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 of the driver, and the process after recognizing the position of the vehicle driver, such as automatically adjusting the rearview mirror or automatically adjusting the steering angle, may be performed. The configuration may be configured to recognize the most appropriate riding position according to the driver's position.Incidentally, in this embodiment, when the driver's 10th position is recognized, the angle of the rearview mirror is automatically adjusted or drowsy driving is detected. It can be used for lifting platforms, etc.

Furthermore, in the first embodiment and the second embodiment, the above-mentioned light emitting means (2) includes a light emitting section 5, the image detecting means (2) includes an image detecting section 6, and the singular point position detecting means (2) and the position recognizing means V each include a light emitting section 5. The image processing unit 1ff18 corresponds to the image processing unit 1ff18, respectively.In addition to the image detection unit 6 consisting of a MOS type solid-state IM image element as in the 11th embodiment, the image detection unit 6 also includes, for example, a CC
It is also possible to use an Ii image tube as long as it is made of a line image element used in DM, a so-called solid-state camera.

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 viewed from one direction is used to recognize the riding position of the driver. Although the movement of the person in the left and right direction is not taken into account, two image detection units are installed at different positions, which is the origin of so-called triangulation. If the vehicle is configured to recognize the driver's riding position using ll, it will be possible to detect the driver's movement in the left and right directions, making it possible to more accurately recognize the driver's three-dimensional position. .

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

Furthermore, in the first example and the second example, in the bright point search process, the search is performed sequentially in the vertical direction starting from the upper left corner, but the search class (O) is applied to all pixels in the nose region. Two (''
Even if I try to search according to that ranking, it is still not possible.

Further, in the first and second embodiments, the nose region is rectangular, but it may be circular or triangular, for example. In this case, a more efficient search can be achieved by combining the above-described method of ranking pixels in a search order.

In addition, the image data obtained by the image detection means
I) Regarding image data subjected to lateral differential processing, when the position is recognized (1m), the feature h(tl) of the image data is determined, so more accurate position recognition is possible.

[Effect of the invention] 1. As described above, in the vehicle driver position recognition device of the present invention, data in the vicinity of a singular point of a predetermined part of image data obtained by the image detection means and a pre-stored standard (standard) of a predetermined part are used. The system is configured to recognize the vehicle driver's device by comparing the and. Therefore, it is possible to accurately recognize a predetermined part of the driver.
It automatically adjusts the position and angle of rearview mirrors, headrests, air-conditioned air outlets, steering wheels, etc., and detects drowsy driving from changes in the position of the driver's eyes and head. This is useful for issuing a warning to the driver.

[Brief explanation of the drawing]

Fig. 1 is a block diagram showing the configuration of the present invention, Figs. 2 to 14 show embodiments of the invention, and Fig. 2 shows an instrument panel of a vehicle to which the embodiment of the invention is applied. 3 is an explanatory diagram of the light emitting section 5, FIG. 4 is an explanatory diagram of the image detecting section 6, and FIG. 5 is a perspective view showing the riding position li.
l! 6 is a flowchart showing the operation of the image processing unit 8 of the first embodiment, FIG. 7 is a time chart 1 to 1 explaining the reading process of image data G, and FIG. 8 is an image input FIG. 9 is an explanatory diagram showing the irradiation image data G stored in the unit 10. FIG. 9 is an image diagram of the image data G.
11 is an explanatory diagram of the nose position detection process, FIG. 12 is a flowchart showing the operation of the image processing unit 8 of the second embodiment, and FIG. 13 is a data diagram showing the standard pattern of the nose. FIG. 14 is an explanatory diagram illustrating the three-dimensional position of the eyes, in which (a) is a plan view of the driver 1, and (b) is a side view of the driver 1. ■...Light emitting means ■...Image detection means IV...Singular point position detection means ■...Position Wg* means 5...Light emitting unit 6...Image detection unit 8...Image processing unit 10... Image input section 14... CPU

Claims (1)

[Scope of Claims] 1. A light emitting means for illuminating a vehicle driver; and an image detecting means for receiving reflected light from the driver caused by the illumination of the light emitting means and detecting at least the face of the driver as image data. , a singular point position detecting means for detecting a singular point position of the predetermined part of the driver in the detected image data; data in the vicinity of the singular point position of the detected predetermined part in the image data; position recognition means for determining the position of the predetermined region at a position with the maximum correlation obtained by comparing the data of the standard pattern of the predetermined region with the data of the standard pattern while changing the position of the data of the standard pattern on the image data; A vehicle driver position recognition device comprising: . 2. The vehicle driver position recognition device according to claim 1, wherein the predetermined portion is the driver's nose, and the singular point of the predetermined portion is the tip of the driver's nose. 3. Claim 1, wherein the light emitting means emits infrared light and the image detection means receives infrared light.
2. The vehicle driver position recognition device according to item 1 or 2. 4. The position of the vehicle driver according to any one of claims 1 to 3, wherein the image detection means is arranged on the passenger seat side of the vehicle so as to detect the riding state of the vehicle driver as a side image. recognition device. 5. A vehicle driver position recognition device according to any one of claims 1 to 4, wherein the image detection means comprises a two-dimensional solid-state image sensor.