Communications: electrical – Land vehicle alarms or indicators – Of relative distance from an obstacle
Reexamination Certificate
2000-02-28
2003-04-15
Wu, Daniel J. (Department: 2632)
Communications: electrical
Land vehicle alarms or indicators
Of relative distance from an obstacle
C340S436000, C340S425500, C340S540000, C340S901000
Reexamination Certificate
active
06549124
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Field of the Invention
The present invention relates to an environment monitoring system, and more particularly to an environment monitoring system for picking up the environment (road image) of one's own vehicle by an image pick-up means such as a camera installed on the vehicle such as a motor car, detecting a vehicle approaching from the environment of one's own running vehicle using the road image picked up and giving a warning to a driver.
2. Description of the Related Art
For example, when a driver of a vehicle running on one-side two lanes of e.g. a speed way intends to change his own vehicle lane, if he changes the lane while he misses a vehicle which catches up with his own vehicle on another lane at a higher speed than his own vehicle from the diagonal-rear direction, there is strong possibility of a serious accident. Therefore, it is desired that the driver surely notices or recognizes other vehicles in the environment.
When the following vehicle on the same lane abruptly approaches his own vehicle from the rear, if the driver of his own vehicle makes abrupt braking, there is possibility of bumping-into-the back.
When another vehicle runs forward on the same lane at a lower speed than that of his own vehicle, if a driver dozes, there is a danger of bumping-into-the back.
A technique for avoiding the danger as described above has been proposed as an environment monitoring system for a vehicle disclosed in JP-A-7-50769. Now referring to
FIGS. 10A-10D
, an explanation will be given of this environment monitoring system.
FIGS. 10A-10C
are views for explaining a change in a rear background image acquired by a video camera
1
.
FIG. 10A
shows a status inclusive of one's own vehicle.
FIG. 10B
shows an image picked up by a video camera
1
at timing t in an environment of one's own vehicle.
FIG. 10C
shows an image picked up at timing t+&Dgr;t.
Now it is assumed that one's own vehicle is running straight on a flat road. The road sign and building residing in the rear of one's own vehicle in
FIG. 10A
are observed as images shown in
FIGS. 10B and 10C
at timings t and t+&Dgr;t, respectively. Coupling the corresponding points in these two images provides speed vectors as shown in FIG.
10
D. The are referred to as “optical flows”. Where a following vehicle approaches, the directions of the vectors in the optical flows in
FIG. 10D
are contrary. Using the optical flows, the conventional environment monitoring system monitors the relationship between one's own vehicle and the following vehicle or another vehicle running on an adjacent lane to detect the other vehicle approaching one's own vehicle, thereby giving a warning to a driver.
In some prior arts, a technique of searching corresponding points using two cameras is adopted. Specifically, an edge point Pa of an object is detected from a luminance difference between the adjacent pixels on the image picked up by a camera. A point Pb of the image picked up by another camera corresponding to the detected edge point is detected. The position of an approaching vehicle is acquired by the pixel coordinates of Pa and Pb. On the basis of the position of the approaching vehicle acquired, the pertinent driver is given a warning of the existence of the vehicle approaching his own vehicle.
However, where it is difficult to recognize the status of the environment using the image picked up by a camera owing to fog or strong rain, the above conventional environment monitoring system cannot detect the approaching vehicle through image processing.
In the environment monitoring system using optical flows, in order to acquire the optical flows, for example, a “correlative technique” of detecting the corresponding points between two frames of images' has been adopted. Referring to
FIGS. 11A and 11B
, an explanation will be given of the correlative technique. First, on an image picked-up at timing t, a window W
1
is set for a pixel Q at issue (FIG.
11
A). Next, on the image picked up at timing t+&Dgr;t, while the window corresponding to the pixel Q is moved on the entire region of the image picked-up, the absolute value in the luminance difference between the corresponding pixels at timings t and t+&Dgr;t is acquired. This operation will be carried out for each of the pixels constituting the image. The point in the window W
2
when the sum of the luminance differences for the respective pixels is minimum is defined as a corresponding point, i.e. corresponding pixel R. The vector QR thus created is obtained as an optical flow (FIG.
11
B).
The correlative technique has the following disadvantage. The optical flow is detected on the basis of the luminance of each of the pixels constituting the window set within each of two frames of images picked up by a camera
1
. Therefore, while a vehicle runs in bad weather such as fog or strong rain, the entire image picked-up will be whitish and hence the luminance of each of the corresponding pixels is approximately equal on the entire image. This makes it difficult to detect correct optical flows, and hence impossible to detect the approaching vehicle.
Also in the environment monitoring system using two cameras, the corresponding Pa and Pb between the two frames of images picked up by the two cameras are detected by means of the correlative technique. Therefore, while a vehicle runs in bad weather such as fog or strong rain, it is difficult to detect the corresponding points Pa and Pb, thereby making it impossible to detect another approaching vehicle.
When the environmental condition cannot be recognized using the images picked up by the cameras, the environment monitoring system cannot detect the approaching vehicle, and cannot give a warning even if there is the approaching vehicle. In this case, where a driver continues to run his own vehicle without knowing this fact, he may change the lane with the realization that there is no approaching vehicle. This may lead to the collision of his own vehicle with the approaching vehicle in the adjacent lane. In this way, it is very dangerous for a driver to run his own vehicle with no realization that the approaching vehicle cannot be detected.
SUMMARY OF THE INVENTION
An object of the present invention is to provide an environment monitoring system which permits one's own vehicle to run safely even if an approaching vehicle cannot be detected.
In order to attain the above object, as shown in
FIG. 1A
, an environment monitoring system for a vehicle according to the invention comprises:
image-pickup means
1
loaded on the vehicle for picking up an environment of the vehicle to acquire an image;
image-processing means
3
a
-
1
for processing the image to detect an approaching vehicle;
danger deciding means
3
a
-
2
for deciding danger for the approaching vehicle;
decision means
3
a
-
3
for deciding whether or not the approaching vehicle can be detected by means of the image processing means
3
a
-
1
; and
warning means
5
for giving warning when it is decided that the approaching vehicle cannot be detected by means of the image processing means.
In this configuration, a driver can notice that the warning means indicates that the approaching vehicle cannot be detected by the image processing means.
Preferably, the decision means decides “NO” if prescribed information is not acquired at any timing from the image picked up by the image pick-up means. Therefore, it is possible to decide directly from the image picked up by the image pick-up means whether or not the approaching vehicle can be detected by the image processing means.
Preferably, as shown in
FIG. 1B
, the prescribed information is a first image of an object at a prescribed position in the image picked up by the pick-up means when the approaching vehicle can be detected by means of the image processing means; and
the deciding means has an image storing means
3
b
-
1
for storing the first image, the deciding means decides “NO” if similarity between the first image stored in the image
Fujinami Kazutomo
Ishikawa Naoto
Okamoto Keiki
Armstrong Westerman & Hattori, LLP
Huang Sihong
Wu Daniel J.
Yazaki -Corporation
LandOfFree
Environment monitoring system for a vehicle with an image... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Environment monitoring system for a vehicle with an image..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Environment monitoring system for a vehicle with an image... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3080764