JP2611325B2 - Road recognition device for vehicles - Google Patents

Description

Description: Object of the Invention [Industrial application field] The present invention relates to a vehicle road recognition device that recognizes a road from an image outside the vehicle around the vehicle.

2. Description of the Related Art There have been proposed some devices that capture an image of a field of view in the front-rear direction of a vehicle using an image capturing unit such as a TV camera mounted on a vehicle, and extract and use various information included in the image. For example, JP-A-59-127200 discloses an "in-vehicle traffic sign notification device" that recognizes a road sign from an image.
Further, as a military vehicle, an unmanned tank that detects a flat area and automatically travels has been developed.

[Problems to be Solved by the Invention] However, since a road sign or the like does not always have a fixed positional relationship with a running vehicle, it is extremely difficult to directly recognize a road sign. Therefore, in order to realize such a technology, a device that specifies an object having a substantially constant positional relationship with a running vehicle and that reliably recognizes the object is indispensable. As such an object, a road is considered to be suitable, but a device for accurately recognizing the road has not been proposed.

Further, in the automatic driving of a general vehicle, for example, in the automatic driving of tracking a running vehicle, it is not sufficient to determine whether or not the road is a flat road, and it is necessary to correctly recognize a driving road and a driving lane. There is. From this point of view, a device that accurately recognizes roads is necessary, but roads have differences in road width, the presence or absence of intersections, straight roads / curves, and heights.
Furthermore, there are dark portions such as a white crossing portion and a shadow of an overpass such as a pedestrian crossing, and it has been extremely difficult to recognize this by image processing.

An object of the present invention is to solve the above problems and to appropriately recognize a road by extracting a region from an image outside a vehicle.

Configuration of the Invention The configuration of the present invention that achieves the above object will be described below.

[Means for Solving the Problems] As shown in FIG. 1, the vehicle road recognizing device of the present invention has an image pickup means M2 for picking up an image outside the vehicle M1 and an image picked up by the image pickup means M2. A region extracting unit M3 for extracting one or more regions present in the image; and a road region determining unit M4 for determining a region corresponding to a road based on at least the form of the region from among the extracted regions. Attribute storage means M5 for storing attributes such as color and shape of the determined road area; and, among the areas extracted by the area extraction means, the attribute of the area is stored in the attribute storage means. An area that can be regarded as having the same or a continuity is connected to the road area determined by the road area determining means, and an area correcting means M6 for correcting the road area is provided. .

Here, the means M3 for extracting a region performs, for example, a differentiation process or a skeleton extraction process on a captured image to detect an edge, and extracts a range surrounded by the edge as a region. It can be configured to realize various methods of region extraction, such as a configuration in which each part that falls within the respective ranges of color and brightness set in stages is extracted as a region.

Means M4 for determining a road area includes, for example, an area extracted from an image outside the vehicle that is equal to or larger than a predetermined size as a road, and a substantially trapezoidal area located at the lower center of the image as a road. This can be realized by a configuration or a configuration in which an area having a small shape change over time is determined to be a road.

Further, the means M5 for storing the attribute of the road area is configured to store, for example, one or a combination of the color, brightness, texture, their distribution, or the characteristic of the shape or the like of the area determined as the road as the attribute. be able to.

For example, when the attribute storage unit M5 stores the color of the region as the attribute of the road region, the region correction unit M6 stores the color of the region in the region extracted by the region extraction unit M3 in the attribute storage unit M5. In the case where the area that can be regarded as being the same as the attribute (color) stored in the area is continuous to the road area, and when the attribute storage means M4 stores the shape of the area as the attribute of the road area, the area is extracted by the area extraction means M3 It can be configured such that, in the set area, an edge of the area is connected to the road area in such a manner that an edge of the area matches a line extending from the edge of the road area.

[Operation] The vehicle road recognizing device of the present invention having the above configuration is configured to extract one or more regions existing in the image from the image outside the vehicle M1 around the vehicle M1 captured by the imaging unit M2.
Extract with M3. From the area thus extracted,
At least based on the form of the area, the road area determination means M4
Accordingly, the area corresponding to the road is determined, and the attributes such as the color and shape of the road area are stored in the attribute storage unit M5. Further, in the vehicle road recognizing device of the present invention, the area correcting means M6
Among the regions extracted by the region extracting unit M3, a region whose attributes are considered to be the same as or have continuity with the attributes stored in the attribute storing unit M5 is determined by the road region determining unit M4. The road area is corrected by connecting to the determined area corresponding to the road.

Embodiment In order to further clarify the configuration and operation of the present invention described above, a preferred embodiment of the vehicle road recognition device of the present invention will be described below. FIG. 2 is a schematic configuration diagram of a vehicle road recognizing device as a first embodiment of the present invention, and FIG. 3 is a block diagram showing a schematic configuration mainly of an image processing device.

As shown in FIG.
A full-color television camera 3 using a CCD for imaging the front of the vehicle, an image processing device 5 for processing an image captured by the television camera 3, and a color monitor 7 for displaying the processed image so that an occupant can view it. It is composed of The image processing device 5 is configured as an arithmetic and logic operation circuit including a well-known CPU 11, a ROM 12, a RAM 13, an image memory (hereinafter, referred to as a VRAM) 15, and the like. The image processing apparatus 5 includes, in addition to the CPU 11 and the like, an image signal input port 18, an input circuit 19, and a CRTC 20 connected to each other via a bus 17, and further, an RGB signal from the television camera 3 for each color. And an A / D converter 22 for converting into a digital signal.

A confirmation switch 25 is connected to the input circuit 19. The switch 25 is used when a final determination by the occupant is required in the road recognition processing to be described later.
The CPU 11 can read through the input circuit 19 at any time whether or not the switch 25 has been operated. The image signal input port 18 is connected to the A / D converter 22 and sequentially reads the image signal from the television camera 3 and develops the image signal in a predetermined area of the VRAM 15. Therefore, the CPU 11 can freely process the image outside the vehicle by accessing the predetermined address of the VRAM 15. CRTC20 is a color monitor 7
Connected to the VRAM 15 upon receiving an instruction from the CPU 11.
The image data after the image processing developed in the predetermined area is read out and displayed on the color monitor 7.

Road recognition processing in the vehicle road recognition device of the present embodiment having the above configuration will be described. The apparatus of this embodiment executes a road recognition processing routine shown in FIG. After the power is turned on, first, a process of inputting an image outside the vehicle captured by the television camera 3 through the image signal input port 18 is performed (step 100). The input image data is developed in a predetermined area of the VRAM 15 as described above. An example of the captured image is shown in FIG. Subsequently, the captured image data is binarized by applying a well-known spatial filter such as a Laplacian operator, and a process of extracting an edge from the captured image is performed (step 11).
0). By edge extraction, the image is binarized into edges and other parts. After edge extraction, edge enlargement / reduction processing is performed to connect portions where edges that should have occurred are missing in the process of capturing images (step 12).
0). FIG. 5B shows an example of the result of such edge extraction and processing.

After the edge is repaired, a process of extracting a portion surrounded by the edge as one region is performed (step 13).
0). The extraction of the area surrounded by the edge is performed in order from the area existing at the bottom of the screen in consideration of the probability of the existence of the road, and by tracing the edge clockwise, the area of the area is extracted. The calculation is also performed. Subsequently, it is determined whether or not the extracted region corresponds to a road. In the present embodiment, with respect to the extracted region, the area calculated in step 130 is one area of the entire screen.
When it is determined that the value is equal to or more than / 10 (step 140) and the position where the region exists is a position corresponding to the road (step 150), the region is determined to be a region corresponding to the road. The area occupied by the road with respect to the entire screen depends on which part of the vehicle 1 is provided with the television camera 3,
Further, the ratio varies depending on the angle of depression, the magnification, the change in the gradient of the road, and the like, and the ratio serving as a criterion for determination is experimentally determined. In this embodiment, the determination of the position of the region is made based on whether or not the region exists from the bottom to the center of the screen. This is because when the television camera 3 is provided in the front part of the vehicle 1, the road is usually imaged at this position.

If the extracted area does not correspond to a road, it is determined whether all the areas existing on the screen have been extracted and determined (step
160) If the determination of all the areas has not been completed, the process returns to step 130 to continue the determination of the next area. On the other hand, when the determination for all the regions is completed (step 160), the process returns to step 100 to execute again from input of a new image.

When it is determined that the extracted area is a road by the processing of steps 130 to 150, processing for displaying this on the color monitor 7 is performed (step 170). In this case, if the area extracted as a road is subjected to a process of high visibility (for example, yellow color or blinking of the area) and displayed over the captured original image, it can be recognized at a glance. Is preferred. This example is shown in FIG. 5 (C).
In the figure, the hatched area is the color monitor 7
Above, it is colored yellow.

In this manner, it is determined whether the area shown on the color monitor 7 can be finally determined as the road area by operating the confirmation switch 25 (step 180). If the confirmation switch 25 is operated within a certain period, the color monitor 7
Assuming that the area displayed above may be determined to be a road, the attributes of this area, in this embodiment, the road width L and its color, are stored in RAM1.
It is stored in a predetermined area of step 3 (step 190).

With the above processing, it is determined that the initial recognition of the road has been completed, and the recognition of the road using the attributes of the road area is continued from step 200 onward. First, the steps in the initial recognition process
As in the case of 100, 110, and 120, input of an image captured by the television camera 3 (step 200), extraction of edges (step 210),
The edge is repaired (step 220), and subsequently, a detection point is set using the road width L which is one of the attributes stored in the RAM 13 (step 230). The detection point SP is set as a half point of the road width L as shown in FIGS. 6 (A) and 6 (B). The road changes its shape when approaching a curve, but focuses on the fact that there is no significant change in the width occupying the bottom of the screen. The extraction of the area is started from the area to be processed. If the extracted area cannot be recognized as a road, the detected point SP is successively moved to an upper area and a new area is extracted. If the detected point SP reaches the top of the screen, ( Step 240), and repeat the above-described processing from the input of the image (Step 200).

If the detection point SP does not reach the upper part of the screen, an area where the detection point SP exists is extracted (step 250), and it is determined whether or not the area of the area is 1/10 or more of the entire screen. (Step 260). If the area is equal to or smaller than the size corresponding to the road, the above-described processing is repeated from the setting of the detection point SP (step 230).

If the area of the extracted area occupies less than 1/10 of the screen, the color which is one of the attributes of the area is determined (step 270). If the color of the area can be regarded as the same as the color of the road stored in the RAM 13 in step 190, it is determined that the area is a road, and it is determined whether or not this area is continuous to the center of the screen (continuous). Sex determination) (step 280). If it continues to the center of the screen, it is regarded as a road, and the area is displayed as a road on the color monitor 7 (step 290). An example of this is shown in FIG.

When imaging on a real road, the road area is divided by the shadow of an overpass, building, telephone pole, etc. reflected on the road, or the edge is generated by a white line such as a pedestrian crossing or center line. Sometimes the area is divided. Such an example is shown in FIG.

When the road area is divided, even the area determined to have the area and the color corresponding to the road may not be continuous to the center of the screen. Therefore, when it is determined that there is no continuity (step 280), the detection point SP is moved to the upper or lower part of the divided area to extract the area (step 300), and the area and the road ahead are extracted. To compare the color with the area determined to be
310). If the colors of the two areas can be regarded as the same, the two areas are combined (step 320), and the continuity is determined again (step 280). If the area is not continuous to the center of the screen even after combining, it is further determined whether the area above and below the area cannot be regarded as the same color. Repeat until the sex determination is satisfied (steps 280, 300, 310, 320). If the continuity is satisfied, or if there is no longer a region of the same color, the region that has been recognized as a road is output to the color monitor 7 as a result of the previous determination (step 29).
0), the above-described processing (steps 200 to 320) is repeated from the image input processing (step 200) again.

According to the vehicle road recognition device of the present embodiment configured as described above, after extracting an area corresponding to a road based on an image captured by the television camera 3 provided in the front of the vehicle 1, By storing attributes such as the width and color of this region and then combining a region having the same attribute as the stored attribute with a region previously extracted as corresponding to a road, the road region is corrected. Do. Therefore, the road recognition device of this embodiment can recognize roads very accurately and continuously, and can display the recognized roads on the color monitor 7. Therefore, the vehicle occupant can visually recognize the road pattern displayed on the color monitor 7 in addition to visually recognizing guardrails, telephone poles, billboards, and other contaminants, thereby contributing to improved driving safety. can do.

Furthermore, if the road recognition device of the present embodiment is used, a road sign recognition device such as a traffic signal based on road recognition, an automatic tracking travel device that tracks a preceding vehicle, or a key plane travel device that keeps running in a lane Etc. can be applied.

Next, a description will be given of a vehicle road recognition device according to a second embodiment of the present invention and a road overhead view display device to which the device is applied. This road overhead view display device has the same hardware configuration (see FIG. 3) as the vehicle road recognition device of the first embodiment, and differs only in the processing. That is, as shown in the flowchart of the overhead view display processing routine of FIG. 7, the road overhead view display device of the present embodiment first executes an initial recognition process corresponding to steps 100 to 180 of the first embodiment. (See FIG. 4). Then, in addition to the color, the roughness of the area is stored as attributes of the area finally determined to be a road (step 390). What is the roughness of the area?
This is a so-called texture in image processing. In the present embodiment, the density of a region is defined as a ratio of black pixels when expressing the density of a region by binarized pixel analysis (dither method).

After the initial recognition of the area corresponding to the road and the storage of its attributes are performed, an image is further input (step 40).
0), as in the first embodiment, extraction of edges from the input image and restoration thereof are performed (step 415). As in the first embodiment (steps 230 to 320 in FIG. 4), the areas obtained in this way are corrected based on the attributes of the road area and the areas are combined (step 425). However, in the present embodiment, unlike the first embodiment, correction and combination are performed based on the roughness of the area instead of the color of the image. As a result, in this embodiment, it is not necessary to use a color television camera or the like, and image processing can be simplified.

After such correction and combination, as in the first embodiment, a road area is extracted (step 435), and based on the obtained shape of the road area, it is determined whether or not the recognized road is a straight road. Perform (step 445). The determination as to whether or not the road is a straight road can be easily made based on whether or not the left and right ends of the recognized road area can be regarded as straight lines. If the road is not a straight road, the following equations (1), (2) and (3) are used. On the other hand, if the road is a straight road, the following equations (1), (4) and (5) are used.
The coordinates of each of the recognized road area coordinates are converted (steps 455 and 465).

The image in which the road area is recognized is obtained by developing a three-dimensional space existing in the visual field of the television camera 3 into a two-dimensional plane. This plane is hereinafter referred to as an image plane, and its coordinates are represented by (x, y), and the coordinates of the real space are represented by (X, Y, Z)
It is assumed that At this time, as shown in FIG. 8, assuming that the height of the television camera 3 from the road surface is H and the distance from the television camera 3 to the image plane is f, as shown in FIG. A relationship exists.

Therefore, the coordinates of the road, that is, the coordinates (X, Y, Z) of the left end and the right end of the road can be obtained by performing coordinate conversion from the image plane to the real space according to the equation (1). However, such a conversion is correctly established when it is assumed that the road captured by the television camera 3 is a two-dimensional plane that does not include a gradient change or the like.

Based on the road coordinates (X, Y, Z) thus obtained, the relative position of the vehicle with respect to the road and the equations at the left and right ends of the road are calculated. When the road has the curvatures R1 and R2 (see FIG. 9), or when the road is a straight road making an angle θ with respect to the vehicle 1 (see FIG. 10), the left end and the right end are represented in real space. The equations are given by the following equations (2), (3) and (4),
(5). The expressions W1 and W2 indicate the distance of the vehicle 1 to the left and right ends of the road, respectively.

Leftmost case-road curve road ^{Z 2 + (X + R1 +} W1) 2 = R1 2 H 2 x 2 + 2xyH (R1 + W1) - (2R1W1-W1 2) y 2 = -f 2 H 2 ...
(2) the right end of the road ^{Z 2 + (X + R2 +} W2) 2 = R2 2 H 2 x 2 -2xyH (R2 + W2) - (2R2W2 + W2 2) y 2 = -f 2 H 2 ...
(3) For straight roads ・ Left end of road ・ The left end of the road The equation of the left and right ends of the road thus obtained is compared with the coordinates of the left and right ends of the road area extracted from the captured image (step 475), and if they do not match, the position is corrected (step 485). The two do not match: (A) when the road includes an uphill or downhill with a gradient change and plane approximation cannot be performed; (B) when an error occurs due to noise included in the image signal; C) When an intersection or a branch point is included, etc. In such a case, it is conceivable that an accurate road position cannot be recognized. Therefore, in this case, the road position is corrected using the condition that the road width is constant and the road position information on the screen processed up to that time. For example, in the case of the above (A), since the value of y on the image plane changes, the coordinates in the real space shift. In this case, using the condition that the road width W is constant, the coordinate y is corrected so that the following equation (6) is satisfied.

W = X2−X1 = x1 · H / y1−x2 · H / y2 (6) Since the road width is parallel to the normal screen, in this case, y1 = y2. In the case (B), the left and right ends of the road are smoothed using an approximation of being a smooth straight line or curve. Further, in the case of (C) above, it is determined whether or not an intersection or a branch point is included from the shape of the road area obtained by the recognition of the road area. The correction can be performed by superimposing the stored information on the shape of the intersection and the like.

After the position is corrected in this way, or in step 47
If the expression and the image data match in the judgment of step 5, an overhead view of the road and the position of the vehicle are obtained based on the coordinates of the road in the real space obtained by the above processing (step 49).
0), which is displayed on the color monitor 7 (step 49).
Five). An example of a bird's-eye view is shown in FIG.

As described above, according to the vehicle road recognition device of the present embodiment, the road can be recognized from the image captured by the monochrome television camera 3. Further, based on the recognized road, the overhead view display device to which the vehicle road recognition device is applied can accurately obtain the shape of the road in the real space by correcting a gradient change or the like. Further, in the present embodiment, the vehicle 1
Can be displayed together with the position of. Therefore, the vehicle occupant can use this information, and can further improve the safety in driving the vehicle. Further, the three-dimensional shape of the road and the positional relationship of the vehicle with respect to the road thus obtained can be used in various devices such as a key plane traveling device (not shown). When used in such an apparatus, it is also possible to realize automatic or semi-automated driving, accident prevention such as rear-end collision, and the like.

Next, a traffic light recognition device using a vehicle road recognition device as a third embodiment of the present invention will be described. FIG. 12 is a block diagram showing a schematic configuration of the signal recognition device. As shown in the figure, the device of the present embodiment detects the vehicle speed in addition to the configuration of the TV camera 503, the image processing device 505, and the color monitor 507, which have substantially the same configuration as the vehicle road recognition device of the first embodiment. A vehicle speed sensor 508, a brake sensor 509 for detecting a brake operation amount, and an alarm device 510.
Further, the inside of the image processing apparatus 505 has substantially the same configuration as that of the first embodiment, and in addition to the CPU 511, the ROM 512, the RAM 513, the VRAM 515, the input circuit 519, the CRTC 520, the A / D converter 522, the output circuit 525 Is provided. The vehicle speed sensor 508 and the brake sensor 509 are connected to the input circuit 519 of the image processing device 505, and
0 is connected to the output circuit 525.

The processing of the traffic light recognition device having such a configuration will be described. FIG. 13 is a flowchart showing a signal recognition / alarm processing routine executed by the image processing apparatus 505 of this embodiment. When this routine is started, first, an initial recognition process corresponding to steps 100 to 180 of the first embodiment is executed (see FIG. 4). Then, the shape of the area is stored together with the color as the attribute of the area finally determined as the road (step 590). In this embodiment, the shape data of the region is data defined as an equation of the left and right edges of the region.

After the initial recognition of the area corresponding to the road and the storage of its attributes are performed, an image is further input (step 60).
0), as in the first embodiment, extraction of edges from the input image and restoration thereof are performed (step 615). As in the first embodiment (steps 230 to 320 in FIG. 4), the areas obtained in this way are corrected based on the attributes of the road area and the areas are combined (step 425). However, in the present embodiment, unlike the first embodiment, correction and combination based on the shape of the area are performed together with the combination based on the color of the image. That is, even when the color of the region is different from the color as the attribute stored in advance to some extent, the right and left edges of the adjacent region are well matched to the line obtained by extending the left and right edges of the basic region according to the equation. In the case of, both regions are combined. As a result, in this embodiment, the road area can be correctly corrected even when a road surface having a different color is encountered due to repair work or the like.

After such correction and combination, as in the first embodiment, a road area is extracted (step 635). Based on the shape of the obtained road area, it is determined whether or not the recognized road includes an intersection. A decision is made (step 645). 14th
As shown in FIG. (A), when an intersection is included, the road area GR does not have a monotonous shape as illustrated in FIGS. Shows a unique shape with overhanging areas. Therefore, the intersection is determined by focusing on this shape, and when the intersection is included,
A process of recognizing a traffic signal is performed based on the position of the intersection (step 655). Since the traffic signal has a very high probability of being located at a specific position with respect to the intersection, as shown in FIG. 14 (B), it searches for a search area GS set diagonally above the intersection and The object having the shape and color is specified. Since the search area GS is set for the intersection and recognition is performed, false recognition with the tail lamp or neon sign of the preceding vehicle does not occur, and the accuracy of traffic signal recognition can be improved and the recognition time can be shortened.

After thus recognizing the traffic light, it is determined whether or not the traffic light is a red light (step 665). When it is determined that the color of the lit lamp among the three lamps of the traffic light is red, the signals from the vehicle speed sensor 508 and the brake sensor 509 are read via the input circuit 519, and the vehicle speed brake operation amount and Is input (step 675). Based on the vehicle speed and the brake operation amount thus input, it is determined whether or not an alarm is necessary (step 685). Even if the traffic signal is a red light, the vehicle speed is equal to or higher than a predetermined value and the brake operation is performed. If not, the alarm device 510 is activated via the output circuit 525, assuming that the driver may not be aware of the traffic signal (step 695). Alarm device 510
May be a simple alarm buzzer or the like, but a voice synthesizing device may be incorporated and a warning such as "Red light. Please reduce the speed." If the vehicle speed still does not decrease, it can be considered to perform vehicle speed reduction control such as reducing the output of the internal combustion engine or automatically applying a brake. After activating the alarm device 510, or when the vehicle is not at an intersection (step 645) or the signal is not a red light (step 665) or when no alarm is required (step 685), the process returns to step 590 to repeat the above processing. .

According to the vehicle road recognition device of the present embodiment configured as described above, the road region can be accurately recognized from the color and shape of the region determined as the road by the initial processing. Therefore, according to the signal recognition device of the present embodiment using the vehicle road recognition device, an intersection included in the recognized road region is detected, and an area set for the intersection is searched for, thereby extremely The traffic light can be quickly, easily and accurately recognized. As a result, an alarm can be output from the alarm device 525 using the recognized traffic light,
The safety in driving the vehicle can be further enhanced.

Although several embodiments of the present invention have been described above,
The present invention is not limited to such embodiments at all. For example, a configuration applied to tracking of a preceding vehicle or a key plane traveling device, processing of an image of the rear of the vehicle to recognize a road, and when traveling backward, based on the road, is recognized. The present invention can be implemented in various modes, such as a device for improving the safety of the vehicle, a device for rear-end collision, foreseeing / warning, or a device using other characteristics obtained by image processing as a road attribute, without departing from the gist of the present invention. Obviously you can get it.

Effects of the Invention As described in detail above, according to the vehicle road recognition device of the present invention, there is an excellent effect that a road area can be recognized very accurately. As a result, the recognized road can be displayed and the like, and road information and the like can be provided to the occupant to contribute to safe driving. Further, since it is not necessary to lay an identification device or the like on the road side, it becomes easy to actually mount the road recognition device on a vehicle. Therefore, other control devices mounted on the vehicle, such as a device for displaying a bird's-eye view of the recognized road and the vehicle, a device for recognizing a traffic signal and used for safe driving, and a reference for processing in an automatic tracking travel device or a key plane travel device. The road recognized by the vehicle road recognition device of the present invention can be used. For this reason, the processing of these devices can be facilitated and highly accurate. The realization of such a device can contribute to the improvement of driving safety of a vehicle and is extremely useful.

BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a block diagram illustrating a basic configuration of the present invention, FIG. 2 is a schematic configuration diagram of a vehicle road recognizing device as a first embodiment of the present invention, and FIG. FIG. 4 is a flowchart showing a road recognition processing routine executed by the image processing apparatus of the first embodiment, and FIGS. 5 (A), (B),
(C), (D), and (E) are explanatory diagrams each illustrating an image processed by the road recognition process. FIGS. 6A and 6B are explanatory diagrams illustrating a state of setting a detection point SP. FIG. 7 shows the second embodiment of the present invention.
FIG. 8 is a flowchart showing the processing of the overhead view display device using the vehicle road recognition device as an embodiment, FIG. 8 is a conceptual diagram showing the relationship between an image plane and real space, and FIG. FIG. 10 is an explanatory diagram showing a method of coordinate transformation on a straight road, FIG. 11 is an explanatory diagram showing an example of a bird's-eye view obtained in this embodiment, and FIG. 12 is a third embodiment. FIG. 13 is a schematic configuration diagram of a traffic light recognition device using a vehicle road recognition device as an example, FIG. 13 is a flowchart showing a traffic light recognition / warning processing routine executed by the image processing device in the third embodiment, and FIG. 14 (A). (B) is an explanatory diagram showing a state of recognition of an intersection and setting of a search area GS. DESCRIPTION OF SYMBOLS 1 ... Vehicle 3 ... TV camera 5 ... Image processing device 7 ... Color monitor 15 ... VRAM 505 ... Image processing device 508 ... Vehicle speed sensor 509 ... Brake sensor 510 ... Alarm device SP ... Detection point GS: Search area

Claims (1)

(57) [Claims] 1. An image pickup means for picking up an image of the outside of a vehicle around a vehicle, an area extracting means for extracting one or more areas present in an image picked up by the image pickup means, and at least one of the extracted areas Road area determination means for determining an area corresponding to a road based on the form of the area; attribute storage means for storing attributes such as color and shape of the determined road area; extracted by the area extraction means In the area, an area in which the attribute of the area is the same as or has continuity with the attribute stored in the attribute storage means is connected to the road area determined by the road area determination means. A vehicle road recognizing device, comprising: a region correcting unit that corrects the road region.