JP2940118B2 - Tunnel detection device - Google Patents

Description

Description: TECHNICAL FIELD The present invention relates to a tunnel detection device. This device is
The present invention can be applied to an automatic light control device, an external air automatic switching device of a car air conditioner, a car phone interrupt warning device, and the like.

[Prior Art] A conventional vehicle auto light control device operates due to a change in illuminance, and therefore cannot distinguish between a tunnel and a bridge girder, and has a problem in that it is lit when passing through the bridge girder.

To solve this drawback, JP-A-60-151521 and JP-B-63-7797 are based on sound waves (noise), and JP-A-54-158962 is based on self-emitting ultrasonic waves.
JP-A-240545 detects a tunnel using a two-dimensional image sensor.

[Problem to be Solved by the Invention] A method of detecting a tunnel using a two-dimensional video signal is as follows.
There is an advantage that earlier detection is possible compared to the sound wave method, but there are various patterns in the two-dimensional shape of the tunnel, and a large-scale image processing device is required for its distinction,
The time required for image processing cannot be ignored.

For example, the upper part of the tunnel is empty, a vertical surface of concrete, a tree surface or a rock surface, and it is not easy to set only the tunnel portion to the black level of the binarized video signal and noise is inevitable. Is mixed. Further, it is not easy to accurately determine tunnel portions having various cross-sectional shapes from the binarized two-dimensional video signal.

The present invention has been made in view of such problems,
It is an object of the present invention to provide a tunnel detection device capable of high-speed discrimination and obtaining high discrimination accuracy despite a simple device configuration.

Means for Solving the Problems A tunnel detecting device according to the present invention is mounted on a vehicle in a vehicle traveling direction and captures a lateral image, and a one-dimensional image output from the one-dimensional image capturing device. A binarizing unit for binarizing the signal; and a tunnel judging unit for judging a tunnel by processing the binarized video signal output from the binarizing unit. When the continuous black level region where the black level signal of the structured video signal is continuous exists at a predetermined width at the center of the imaging region of the one-dimensional imaging device, and at the center of the imaging region of the one-dimensional imaging device. A feature is that a tunnel detection signal is output when there is a pair with a predetermined width on both sides of a predetermined fine width.

The one-dimensional imaging device that captures images in the horizontal direction may be any device that can obtain one row of video signals in a substantially horizontal direction, and may use one pixel row of an area image sensor.

[Operation] When a one-dimensional video signal obtained by imaging a tunnel with a one-dimensional imaging device in which pixel rows are arranged in a horizontal direction is binarized by binarization means, a continuous black level region of the binarized video signal is obtained. Exists at a predetermined width at the center of the imaging region of the one-dimensional imaging device, or exists in a pair with a predetermined width on both sides of a predetermined minute width at the center of the imaging region of the one-dimensional imaging device.

Therefore, when these two one-dimensional image patterns occur, it can be determined that the tunnel is a tunnel.

[Example] [First example] Fig. 1 shows a tunnel detection device according to a first example.

This device includes a one-dimensional imaging device 1, a comparator 2 as a binarization processing unit, a microcomputer 3 as a tunnel determination unit, and an auto light control device 4 driven by the microcomputer 3.

The one-dimensional imaging device 1 is mounted on a dashboard of a vehicle as shown in FIG.
A CD linear image sensor 1b and a lens system 1a are provided. The optical axis of the lens system 1a extends substantially horizontally in the vehicle traveling direction, and the pixel rows of the CCD linear image sensor 1b are arranged substantially horizontally in the vehicle signal direction.

Light entering through the windshield is reflected by the lens system 1a
An image is formed on a pixel row of the CCD linear image sensor 1b, and the CCD linear image sensor 1b outputs a one-dimensional video signal Vs to the comparator 2. By the way, CCD linear image sensor 1
The scanning cycle of b is 64.5 μsec. The comparator 2 compares the one-dimensional video signal Vs with a predetermined threshold voltage Vref, and outputs a binary one-dimensional video signal (hereinafter, simply referred to as a binary signal) Vd. The microcomputer 3 processes the binarized signal Vd to determine a tunnel, and outputs a lighting signal to the automatic light control device 4 when the tunnel is determined.

Here, the threshold voltage Vref is set to a level at which an output signal voltage of a pixel for imaging the inside of the tunnel is set to 0.

Next, the operation of the microcomputer 3 will be described with reference to the flowchart of FIG.

First, a binary signal Vd for one pixel row is received from the comparator 2 during the odd scanning period, and is temporarily stored in a built-in storage area (S10).

During the next even scanning period, the above-mentioned binarized signal temporarily stored
By processing Vd, all continuous black level regions Rb are extracted, and the start point and end point thereof are stored (S12). Note that the start point coordinates of the continuous black level region Rb are the coordinates of the pixel whose left adjacent pixel is at the white level and the black level itself, and the end point coordinates of the continuous black level region Rb are that the left adjacent pixel is at the black level. And the coordinates of a pixel that is itself a white level, and
The continuous black level region Rb means a pixel region from the start point to the end point.

Next, it is determined whether or not at least one of the center coordinates (intermediate coordinates between the start point and the end point) of each continuous black level region Rb exists in the center of all the pixel regions (linear) (S14). , It is checked whether the width of the continuous black level region Rb is equal to or greater than a predetermined value (here, equal to or greater than half the width of the entire pixel region). If the width is equal to or more than half of the width of the entire pixel area, it is determined that the tunnel is a tunnel, and the auto light control device is turned on in S22. Also, if the center coordinates of all the continuous black level regions Rb are not at the center of all the pixel regions in S14, it is checked whether a pair of continuous black level regions Rb exists with a small width at the center of the entire pixel region. , If it exists
Proceed to S20; if not, proceed to S28. Here, the central portion of the entire pixel area means a range near the central pixel of the entire pixel area,
The fine width means a relatively small width (here, the number of pixels is 10% or less of the total number of pixels). Obviously, the pixel having this small width is at the white level.

In S20, it is checked whether or not the pair of continuous black level regions Rb has a predetermined width (here, the number of pixels is 20% or less in each case). move on.

After the lighting (S22), it is checked whether or not all the pixel areas are almost at the white level (S24). Here, almost white level means
It is assumed that a continuous black level region Rb of several consecutive pixels or less is included. If all the pixel areas are almost at the white level, a turn-off command is issued to the auto light control device to turn off the light, and if not, the process proceeds to S28.

In S28, the process stands by until the above-described even-number scanning period ends (start of the next odd-number scanning period), and then returns to S10.

FIG. 2 shows an imaging state of the tunnel 5 and an imaging state of the bridge girder 6 of FIG.

As can be seen from FIG. 2, when the tunnel 5 is imaged by the linear image sensor 1b in which pixels are arranged in the horizontal direction,
The continuous black level region Rb exists in the central region of the pixel region 1c of the linear image sensor 1b with a width equal to or larger than a predetermined width, or
A single continuous black level region Rb is present across a small width of a predetermined width or less located at the center of all pixel regions. Here, this small width is a white level area where the tunnel exit is imaged. On the other hand, when passing through a bridge girder that should not be lit (or at the time of passing through a short tunnel), a pair of continuous black level regions Rb are present across a white level region Rw having a predetermined width or more located at the center of all pixel regions. The tunnel detecting apparatus according to the present embodiment focuses on the difference between the image signals when the tunnel 5 and the bridge girder 6 are imaged by the linear image sensor 1b.

FIG. 6 shows an example of an integrated chip suitable for this embodiment.

On this chip, a linear image sensor 11, a microcomputer (or image processing area) 12 including a buffer memory for one pixel row, and an input / output interface 13 are integrated.
The linear image sensor 11 is suitable for manufacturing process consistency.
The MOS shift register driving type is preferable.

The apparatus of this embodiment can also detect raindrops attached to the windshield and the operation of the wiper blade.
For example, as shown in FIG. 7, the light that has passed through the raindrops 8 attached to the windshield 7 and formed an image on the linear image sensor 1b forms a pair of white level regions Rb that are close to each other. This is because light is condensed by refraction at the left and right inclined portions of the raindrop 8, and the amount of light incident on the linear image sensor 1b increases. On the other hand, the wiper blade 9 is an image in which the continuous black level region Rb having a small width reciprocates on the pixel region 1c.

Therefore, according to this device, it is possible to detect the operation of the raindrops and the wiper blade.

Second Embodiment A second embodiment of the present invention will be described.

The device of this embodiment is the same as the device of FIG. 1, except for the operation of the microcomputer 3.

The operation of the microcomputer 3 of this embodiment is shown in the flowchart of FIG.

That is, when the continuous black level region Rb in the stationary or relatively moving state is detected in S16 or S20, whether the detected continuous black level region Rb is expanding (that is, whether the distance between the vehicle and the tunnel is reduced). Find out. More specifically, the width of the continuous black level region Rb extracted this time is obtained, and then compared with the width (stored in the memory) of the continuous black level region Rb extracted last time. If the width has increased by a predetermined width or more, it is understood that the continuous black level region Rb is being expanded.

Then, if the width of the continuous black level region Rb increases,
Lights up (S22), otherwise proceeds to S28.

In this way, it is possible to prevent the case where the vehicle is stopped immediately before the tunnel or the case where the vehicle is illuminated by the black preceding vehicle.

In each of the above embodiments, the threshold voltage Vt of the comparator 2 is fixed.
Vref may be changed.

[Effects of the Invention] As described above, in the tunnel detection device of the present invention, the continuous black level region of the binarized video signal of the one-dimensional imaging device in which the pixel rows are arranged in the horizontal direction is the imaging region of the one-dimensional imaging device. When there is a predetermined width at the center of the one-dimensional imaging device, and when there is a pair with a predetermined width on both sides of a predetermined fine width in the center of the imaging region of the one-dimensional imaging device, a tunnel determination unit that determines that it is a tunnel. Have.

Therefore, according to the present invention, it is possible to perform high-speed discrimination with a much simpler device configuration than in a method of detecting a tunnel using a two-dimensional video signal, and to obtain high discrimination accuracy.

In other words, according to the present invention, when the tunnel is sliced into a small width in the horizontal direction, a pattern in which the continuous black level region exists at a predetermined width at the center of the imaging region, or a predetermined fine width at the center of the imaging region (corresponding to the tunnel exit). ) Can be grouped into patterns that exist in pairs with a predetermined width on both sides of), and if these two characteristic patterns are identified as tunnels, they can be identified with high speed and high accuracy using a simple device configuration. It is.

Further, according to the present invention, since image processing is not performed on a road surface below the tunnel or various wall surfaces (or sky) above the tunnel, it is possible to prevent erroneous determination by these surfaces having various image patterns. it can.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a first embodiment of the present invention, FIG. 2 is an explanatory view showing a tunnel imaging state, FIG. 3 is an explanatory view showing a bridge girder imaging state, and FIG. 4 is an operation of the first embodiment. FIG. 5 is a schematic side view showing the arrangement of the tunnel detection device, FIG. 6 is a schematic plan view of the integrated chip, FIG. 7 is an explanatory diagram showing a raindrop imaging state, and FIG. 8 is a wiper blade imaging FIG. 9 is a partial flowchart for explaining the operation of the apparatus of the second embodiment. 1 ... one-dimensional imaging device 2 ... comparator (binarization means) 3 ... microcomputer (tunnel discrimination means)

Continuation of the front page (51) Int.Cl. ⁶ identification code FI H04N 7/18 H04N 7/18 W (58) Field surveyed (Int.Cl. ⁶ , DB name) G06T 1/00 G06T 7/00-7 / 60 B60T 1/00-1/34 B60Q 1/00-1/56 G08G 1/00-1/16 H04N 7/18

Claims (1)

(57) [Claims] 1. A one-dimensional imaging device mounted on a vehicle in a vehicle traveling direction and taking an image in a lateral direction; a binarizing means for binarizing a one-dimensional video signal output from the one-dimensional imaging device; A tunnel discriminating unit that processes a binarized video signal output from the binarizing unit to discriminate a tunnel, wherein the tunnel discriminating unit includes a continuous black in which a black level signal of the binarized video signal is continuous. When the level region is present at a predetermined width at the center of the imaging region of the one-dimensional imaging device, and at a predetermined width on both sides of the predetermined minute width at the center of the imaging region of the one-dimensional imaging device. A tunnel detection signal, which outputs a tunnel detection signal.