JP2000090393A - On-vehicle-type travel route environment recognition device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To recognize a travel vehicle and a travel lane, to precisely recognize a sign and to avoid the rise of cost by changing the image pickup range of an image pickup means which successively obtains an image, processing the obtained image and recognizing the environment of the travel route of the vehicle. SOLUTION: A camera 12 installed in a vehicle 10 can three-dimensionally swing in the range of a prescribed angle αwith a travel route direction 18 as a center. Namely, the eye direction of the camera 12 can be controlled. Thus, the eye direction of the camera 12 can be turned to a sign direction 16 if need except for the travel route 18. A zoom mechanism is given to the camera 12 itself and an object is enraged, is photographed and an image processing can be executed even if the area of the object is comparatively small like the road sign 14. The precision of image recognition on the road sign 14 improves. The obtained image is processed and the environment of the travel route of the vehicle 10 is recognized.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an apparatus for recognizing a traveling road environment mounted on a vehicle such as an automobile, and more particularly to an apparatus for recognizing a traveling road environment by image recognition and transmitting information necessary for image recognition. The present invention relates to an on-vehicle traveling road environment recognition device that can be acquired with simple hardware.

[0002]

2. Description of the Related Art In recent years, with the aim of realizing a safe, comfortable and efficient next-generation road traffic system, governments, academia and citizens have been working on a national project, ITS (Intel), from their respective positions.
ligent Transport Systems)
Is promoting R & D. One field of the ITS is a field called an autonomous driving road system. This system is a system whose ultimate goal is fully automatic driving of a vehicle on a highway, and includes various element technologies.

[0003] In parallel with the development of a full-scale automatic driving system, the development of a safe driving system aimed at assisting the driver's driving by applying the elemental technology which is considered to be able to be commercialized as early as possible has been developed. Is underway. These include magnetic sensors, laser radars, and CCDs (Cha).
rge-Coupled Device: information acquired by a vehicle-mounted sensor such as a camera;
Based on information provided from a fixed facility (hereinafter, referred to as "infrastructure") by road-to-vehicle communication, a danger warning is issued to a driver or driving assistance is provided.

[0004] One example of this safe driving system is "AHS".
Development of Safe Driving System "(Satoshi Terakubo et al., SEI Technical Review No. 151, September 1997, pp. 47
-52). In this system,
LCX (Leacy Coaxial) as infrastructure
Cables will be laid along roads, and road information and accident information will be provided to vehicles through dedicated communication devices mounted on the vehicle. On the other hand, information such as a running position and a state of the vehicle can be collected on the infrastructure side through the dedicated communication device on the vehicle side.

[0005] A laser radar for measuring an inter-vehicle distance to a preceding vehicle and a CCD camera for photographing a road boundary such as a white line are provided on the front side of the cabin of the vehicle. Image processing is performed on an image captured by the CCD camera to extract a lane mark such as a white line and recognize a preceding vehicle. There are various algorithms for this recognition, and an appropriate one is selected according to the recognition target.

[0006]

In the above-mentioned prior art, the vehicle interior camera can relatively accurately recognize the preceding vehicle and the road boundary. However, these are not the only information that affect the driving control of the automobile. For example, road signs can be effectively used for such travel control. However, in the method used in the related art, it has been difficult to efficiently recognize a road sign in addition to a preceding vehicle and a road boundary line.

The first reason is that the camera used in the prior art cannot capture a clear image of a road sign. In prior art cameras, the magnification is pre-selected as suitable for recognizing the preceding vehicle and the lane of travel. Therefore, an image size sufficient for recognition of a road sign cannot be obtained. Further, since the line of sight of the camera is in the direction of the preceding vehicle, the image of the road sign is often at the end of the image, and it is difficult to recognize the image.

Further, it is necessary to always perform image processing on an image area in which a road sign is likely to appear in addition to the preceding vehicle and the traveling lane, and the processing cycle of the entire image processing becomes longer. Therefore, the cycle in which information can be obtained is lengthened, which causes a problem in security. In order to ensure safety, a high-speed CPU (Central ProcessingUn
(it: central processing unit), and there is a problem that the cost increases.

In order to solve this problem, a system for recognizing only a road sign may be provided separately from a system for recognizing a preceding vehicle and a traveling lane. Since it rises, it is not preferable as a consumer device.

[0010] Such a problem occurs not only for road signs but also for signs such as road marks written on roads.
In the specification of the present application, the term "sign" refers to a road sign, a road surface mark indicating a pedestrian crossing or a maximum speed, a display of a road sign or traffic information on an electronic bulletin board, and the like, particularly for a traveling road environment that can be acquired by image recognition. It shall contain relevant information.

Therefore, a main object of the present invention is to provide an on-vehicle type traveling environment recognizing apparatus capable of accurately recognizing a sign in addition to recognizing a preceding vehicle or a traveling lane and avoiding an increase in cost. That is.

Another object of the present invention is to provide an on-vehicle traveling environment recognizing device that can recognize a sign in addition to a preceding vehicle or a traveling lane with a single imaging device. .

Still another object of the present invention is to enable a single image pickup device to accurately recognize a sign in addition to the recognition of a preceding vehicle or a traveling lane, and to adversely affect the recognition processing of the preceding vehicle or the traveling lane. An object of the present invention is to provide an in-vehicle type traveling environment recognition device that does not affect.

Another object of the present invention is to use a single imaging device to accurately recognize a sign in addition to the recognition of a preceding vehicle or a traveling lane. It is an object of the present invention to provide an in-vehicle type traveling environment recognition device capable of performing the following.

[0015]

According to a first aspect of the present invention, there is provided an on-vehicle traveling road environment recognizing device, comprising: an imaging unit for sequentially acquiring images; and an imaging range changing unit for changing an imaging range of the imaging unit. And an image recognition unit for processing an image acquired by the imaging unit to recognize an environment of a traveling path of the vehicle.

By changing the imaging range of one imaging means, an image to be recognized by the image recognition means can be brought into an appropriate state according to the position of the recognition object. Compared with a case where two or more imaging units are used to recognize different objects, respectively, it is possible to efficiently recognize objects in the same range at a lower cost.

According to a second aspect of the present invention, in the vehicle-mounted traveling road environment recognizing device, in addition to the configuration of the first aspect, the imaging range changing means changes a line of sight of the imaging means. A gaze direction changing unit is included.

By changing the direction of the line of sight of the imaging means, it is possible to reliably capture an image of a specific recognition target.

According to a third aspect of the present invention, in the vehicle-mounted traveling road environment recognizing device, in addition to the configuration of the second aspect, the imaging range changing means further changes the magnification of the imaging by the imaging means. For changing the imaging magnification.

By changing the magnification of imaging, for example, a small (distant) recognition target can be photographed large, or a large (near) recognition target can be photographed at an appropriate size suitable for high-speed recognition. Can be. Therefore, it is possible to more reliably and efficiently recognize the traveling road environment.

According to a fourth aspect of the present invention, in the vehicle-mounted traveling road environment recognizing device, in addition to the configuration of the first aspect, the imaging means includes a CCD camera, and the imaging range changing means includes a CCD camera. Means for changing the size of the imaging area of the image.

To change the size of the imaging region, no mechanical means is required, and only electrical processing may be performed. Therefore, it is expected that the number of failures is reduced as compared with the case where mechanical means is used.

According to a fifth aspect of the present invention, in the vehicle-mounted traveling road environment recognizing device, in addition to the configuration of the fourth aspect of the invention, the CCD camera is configured to calculate the number of pixels used for image processing by the image processing means. Also includes many imaging pixels, and the on-vehicle traveling road environment recognition device further includes resolution changing means for changing the resolution of the CCD camera at the time of shooting according to the size of the imaging area.

By changing the resolution of the CCD camera, the magnification of imaging is substantially changed. This allows you to take a large image of a small (distant) recognition target,
For example, a large (nearby) recognition target can be photographed with an appropriate size suitable for high-speed recognition. Therefore, it is possible to more reliably and efficiently recognize the traveling road environment.

According to a sixth aspect of the present invention, in addition to the configuration of the first aspect of the present invention, a vehicle-mounted traveling road environment recognizing device stores position information of a sign provided around the traveling road. Sign position storage means, a position detection means for detecting a vehicle position, and a change in the imaging range by the imaging direction changing means based on the output of the position detection means and the position information of the sign stored in the sign position storage means. And an imaging range control unit for controlling.

With this configuration, it is also possible to recognize a marker. In addition, by changing the imaging range for photographing the sign, it is possible to photograph the sign and the recognition target other than the sign using the common imaging means. Therefore, there is no possibility that the cost will be unduly increased in adding the sign to the recognition target.

According to a seventh aspect of the present invention, in the vehicle-mounted traveling road environment recognizing device, in addition to the configuration of the sixth aspect, the imaging range control means includes an output of the position detection means and a sign position storage means. Determining means for determining whether or not a sign is present in a predetermined range from the vehicle position based on the position information of the sign stored in the storage unit, and determining that the sign is present in a predetermined range from the vehicle position by the determining means In response to this, the means for temporarily changing the imaging range by the imaging range changing means to a range in which the sign can be photographed, and the judging means have determined that the sign exists within a predetermined range from the vehicle position. Means for temporarily changing the contents of the image recognition processing by the image recognition means so as to recognize the sign photographed by the image pickup means in response to the request.

In recognizing a sign, a process for recognizing a sign is temporarily performed only when a sign exists within a predetermined range from the own vehicle. In other cases, a process for recognizing a sign is not performed. Therefore, there is no problem in performing the processing other than the sign recognition at predetermined intervals, and it is possible to efficiently recognize the traveling road environment without using a high-speed CPU. In addition, since the sign recognition process is performed when necessary, it is possible to always appropriately recognize the traveling road environment according to the position and situation of the host vehicle.

According to an eighth aspect of the present invention, there is provided an on-vehicle type traveling road environment recognizing device, wherein the traveling road recognized by the image recognizing means is added to the configuration of the first aspect of the invention. Means for performing a driving assistance operation of the vehicle according to the environment.

[0030] Not only the traveling route and the situation of the preceding vehicle, but also
Further, it is possible to reliably and efficiently perform an appropriate driving assistance operation according to the position and situation of the vehicle based on the display content of the sign. Moreover, at that time, there is no need to provide a plurality of image pickup means and image recognition processing, and it is possible to prevent an increase in cost.

[0031]

DESCRIPTION OF THE PREFERRED EMBODIMENTS [First Embodiment] An on-vehicle traveling road environment recognizing device according to a first embodiment of the present invention will be described below with reference to FIGS.

Referring to FIGS. 1 and 2, the on-vehicle type traveling road environment recognizing device includes a camera 12 provided in a room of a vehicle 10 which is positioned within a range of a certain angle α around a traveling road direction 16. The first feature is that it can be dimensionally swung, that is, the line of sight of the camera 12 can be controlled. In this way, by allowing the camera 12 to swing, the line of sight of the camera 12 can be directed to the sign direction 18 as necessary in addition to the traveling path direction 16.
As a result, as compared to the case where the camera 12 is fixed, the road sign
4 can be accurately recognized.
Although the camera 12 can swing three-dimensionally in this embodiment, a camera that can swing only two-dimensionally in a plane parallel to the ground may be used. May be swingable in a plane at a predetermined angle (for example, 90 degrees) with respect to. When only a two-dimensional swing is possible, there is an effect that the mechanism for the swing is simplified. On the other hand, if the camera can be swung three-dimensionally, there is an effect that the possibility of obtaining an optimal image according to the target is increased.

Further, in the apparatus of this embodiment, the camera 12 itself is provided with a zoom mechanism, and even if the area of the subject is relatively small, such as a road sign 14, the subject is enlarged and photographed to perform image processing. You can do it.
Therefore, the accuracy of the image recognition of the road sign is further improved. Hereinafter, the configuration and operation of the vehicle-mounted traveling road environment recognition device according to the first embodiment will be described. In the present embodiment, a zoom mechanism capable of continuously changing the imaging magnification is used. However, for example, a mechanism capable of switching the magnification to an arbitrary one of a plurality of magnifications fixed in advance may be used. Good.

Referring to FIG. 3, this on-vehicle traveling road environment recognizing device has a zoom lens 30 for changing the magnification of the front image, and an imaging surface for receiving the front image condensed by zoom lens 30. Then, a CCD camera 32 for sequentially acquiring a forward image and an image signal corresponding to the forward image output from the CCD camera 32 are received, and image processing for recognizing a preceding vehicle, a traveling lane, and a sign such as a road sign is performed. Processing device 34 and a recognition result of a preceding vehicle, a driving lane, a sign, etc. output from the image processing device 34, and generates a signal necessary for driving assistance of the vehicle 10 according to the recognition result. And a determination / control CPU 40 for executing a program to be output.

The on-board traveling road environment recognition device further includes a GP
S (Global Positioning System)
em) A so-called car navigation system which stores a position detecting device 46 for detecting the position of the own vehicle using a sensor, a vehicle speed sensor, a direction sensor, an acceleration sensor, road-to-vehicle communication, and information on a sign position together with map information. CD-ROM 50 (Compact-Disc Rea)
CD-RO to which d-Only Memory can be attached
M drive 48, these position detecting device 46 and CD
An in-vehicle information terminal 42 for providing information about the position of a sign, a pedestrian crossing, and the like, and information about the position, traveling speed, and traveling direction of the vehicle to the determination / control CPU 40 based on the output of the ROM drive 48; including. The determination / control CPU 40 responds to the information about the position of the sign and the pedestrian crossing, etc., and the information about the position, the traveling speed and the traveling direction of the own vehicle, and the line-of-sight direction of the CCD CCD at a predetermined timing so that
A function of outputting a signal for changing the line of sight of the camera 32 and a signal for adjusting the focal length of the zoom lens 30 so that the size of the image of the sign captured by the CCD camera 32 are also appropriate. Output function.

The on-vehicle type roadway environment recognizing device further includes a zoom driving device 36 for changing the magnification of an image by changing the focal length of the zoom lens 30 in response to a signal from the determination / control CPU 40. Similarly, the CCD camera 32 responds to a signal from the determination / control CPU 40.
And an actuator 38 for swinging the line of sight three-dimensionally toward the sign direction.

The in-vehicle type roadway environment recognizing device further performs a predetermined warning or a driving assistance operation in response to a signal output from the determination / control CPU 40 and necessary for the driving assistance of the vehicle 10. Warning and driving assistance device 4
4 inclusive. As the warning / drive assist device 44, a device that issues a warning to the driver by voice, image, light, or the like,
Alternatively, a device that automatically performs braking or shifts down the automatic transmission as necessary can be considered. Instead of issuing a warning unconditionally, a warning may be issued depending on the situation. For example, if the driver recognizes a sign indicating that the vehicle is in a no-passing section, it issues a warning when the driver performs an operation that is interpreted as preparation for overtaking (for example, acceleration, starting blinking of a right turn signal, or steering). Therefore, it is preferable that not only an appropriate driving assistance can be provided in accordance with the condition but also that an unnecessary warning is not issued to the driver.

The determination / control CPU 40 constantly performs a process of determining whether or not the vehicle is near a sign based on information provided from the on-board information terminal 42. When the own vehicle is not near the sign, the focal length of the zoom lens 30 and the line of sight of the CCD camera 32 are set to predetermined magnifications and directions for recognizing the preceding vehicle or the traveling lane, respectively. Only when it is determined that the own vehicle is near the sign, the zoom driving device 36 and the actuator 38 are temporarily driven, and when it is determined that the own vehicle has passed the sign, the focal length of the zoom lens 30 and CC
The line of sight of the D camera 32 is promptly reset to a predetermined magnification and direction for recognizing the preceding vehicle or the traveling lane, respectively.

Referring to FIG. 4, the CPU for determination and control of the vehicle-mounted traveling road environment recognition apparatus according to the first embodiment is described.
The processing executed at 40 will be described. This processing is realized in the form of a program executed by the determination / control CPU 40. The program is stored in a storage device not shown in a machine-readable and machine-executable format, for example, a ROM.
(Read-Only Memory) and the like, and the following processing is realized by the determination / control CPU 40 sequentially executing the instructions in the program. As a device for storing a program, in addition to a ROM, an SRAM, a combination of a hard disk and a DRAM or an SDRAM,
There are various types of removable card-type memories.

The processing shown in FIG. 4 is executed by the CPU 40 for repetition determination and control. First, step 60
Based on the image acquired by the CCD camera 32,
The traveling lane recognition process is executed by the image processing device 34. For this processing, for example, a technique similar to that described in the above-described conventional technique can be used, but other techniques may be used.

Further, at step 62, a preceding vehicle recognition process is executed. This processing is also executed by the image processing device 34 based on the image acquired by the CCD camera 32.
In this case, the same technology as that described in the above-described conventional technology can be used, but other technologies may be used. It is not necessary to perform the processing of step 60 and the processing of step 62 in this order, and they may be performed in the reverse order or at remote positions.

Next, an inquiry is made to the in-vehicle information terminal 42 as to whether or not there is a sign near the own vehicle (step 6).
4). In response, the in-vehicle information terminal 42 returns information indicating whether or not there is a sign near the own vehicle. This determination is made based on the position of the vehicle obtained by the on-board information terminal 42 from the position detecting device 46 and the CD-ROM via the CD-ROM drive 48.
-The position of the sign obtained from the ROM 50 (in which information indicating the position of the sign is stored together with the map data and the like) is collated with the sign.

If the result of determination in step 66 is that there is no sign to be recognized, processing proceeds to step 80. The processing after step 80 will be described later.

If it is determined in step 66 that there is a marker to be recognized, the process proceeds to step 68.
Proceed to. In step 68, information such as the current position of the vehicle, the position of a nearby sign, and the type of sign is obtained from the on-board information terminal 42. Note that the content of the sign itself can be stored in the CD-ROM 50 as information on the type of sign, but since there are signs whose contents dynamically change depending on time, weather, season, traffic conditions, and the like. It is more practical to save the information on the contents of the sign in the CD-ROM 50 and obtain the actual display contents of the sign by image recognition.

Subsequently, in step 70, step 68
On the basis of the information obtained in step (1), the actuator 38 is operated as necessary to turn the CCD camera 32 toward the sign. Next, in step 72, only the area where the sign is shown is selected and image processing is performed to confirm the position of the sign itself. Then, in step 74, the zoom driving device 36 is operated to increase the focal length of the zoom lens 30 to enlarge the sign to shoot. Based on the image of the sign thus obtained, the display contents of the sign are recognized by the image processing device 34 through image processing in step 76.

The order of the processing of steps 70 to 74 is not limited to that shown in FIG. 4, but is arbitrary. Further, if the image recognition of the sign can be performed only by directing the line of sight of the CCD camera 32 to the sign, the zoom lens 30 may not be used, but in general, it is better to use the zoom lens 30 in this way. This is preferable because the accuracy of image processing is increased.

Subsequently, at step 78, the CCD camera 3
A process of restoring the line-of-sight direction and the focal length of the zoom lens 30 is performed. This process is a preparation for the next traveling lane recognition process and the preceding vehicle recognition process. When the process in step 78 ends, the control proceeds to step 80. In step 80, the own vehicle position, own vehicle state, and the environment recognition results performed in steps 60, 62, and 76 are evaluated. Then, as a result of this evaluation, it is determined whether or not a warning and / or driving assistance for the driver is necessary (step 82). If necessary, a warning or driving assistance is provided to the driver in step 84 using the warning / driving assistance device 44. Driving assistance or both processes are performed. When this process ends, the control returns to the step 60 again. If it is determined in step 82 that the warning or the driving assistance is unnecessary, the control returns to step 60. Hereinafter, a series of processes described above are repeatedly executed.

In the above-described embodiment, only when it is determined in step 66 that a sign or the like to be recognized exists near the own vehicle, a series of processing in steps 68 to 78 is executed temporarily to recognize the sign. Done. If no sign or the like to be recognized exists nearby, only the lane recognition and the preceding vehicle recognition are performed. Therefore, there is no possibility that each cycle of the recognition processing is always unduly lengthened, and the travel path recognition is performed at appropriate time intervals. In addition, a high-speed CPU is not necessarily required for that purpose. Therefore, there is no possibility that the cost of the vehicle-mounted traveling road environment recognition device will be unduly increased. Further, when a sign is present near the own vehicle, the sign is recognized, so that the traveling road environment can be determined in consideration of not only the traveling lane and the state of the preceding vehicle but also the display contents of the sign. . Therefore, there is an effect that warning and driving assistance can be more appropriately performed.

In this embodiment, the camera is C
Although the CD camera 32 is used, another type of camera may be used. Further, the camera is preferably of a color system in order to perform image recognition including colors, but a black and white camera may be used.

[Second Embodiment] With reference to FIGS. 5 to 7, a vehicle-mounted traveling road environment recognition apparatus according to a second embodiment of the present invention will be described. As shown in FIG. 5, the on-board type roadway environment recognizing device of the second embodiment differs from the device of the first embodiment in that a CCD camera is used instead of the actuator 38 of the device of FIG. At the time of shooting of the image 32, an image from only a part of the imaging surface of the CCD camera 32 is selected according to the control of the determination / control CPU 40, and the resolution for changing the resolution of the image at the time of shooting of the CCD camera 32 is also selected. The resolution changing unit 1 includes a changing unit 100.
The point that the image selected by 00 is given to the image processing device 34. 5, the same or corresponding parts or blocks as those shown in FIG. 3 are denoted by the same reference numerals. Their functions and names are also the same. Therefore, detailed description thereof will not be repeated here.

As a premise of the device according to the second embodiment, it is necessary that the number of pixels on the imaging surface of the CCD used in the CCD camera 32 is sufficiently large. Normally, the output of almost the entire surface of these pixels is used, and in order to speed up image processing, the pixels are appropriately thinned out, and the output of the entire imaging surface is used for traveling lane recognition and preceding vehicle recognition processing. Alternatively, only the image near the center of the imaging surface is used for the traveling lane recognition and the preceding vehicle recognition processing. When performing the sign recognition process, as shown in FIG. 6, an image of only the CCD partial imaging region where the image of the sign is considered to be formed in the CCD imaging region is obtained, and the sign is recognized. Used for processing. In this case, the resolution of the imaging by the CCD is increased (that is, the pixel is not thinned out),
Only the image signal from this limited area is used for the sign recognition process. As a result, the resulting image is substantially enlarged.

FIG. 7 shows a processing flowchart of a program executed by the determination / control CPU 40 of the vehicle-mounted traveling road environment recognizing device according to the second embodiment. FIG. 7 corresponds to FIG. 4 shown in connection with the first embodiment. In FIG. 7, the same or corresponding blocks (steps) as the respective blocks (steps) shown in FIG. 4 are denoted by the same reference numerals. The processing performed by them is the same. Therefore, detailed description of those blocks will not be repeated here.

The flowchart of FIG. 7 differs from the flowchart of FIG. 4 in that step 110 is included in place of steps 70 to 74 in FIG. 4 and step 112 is included in place of step 78 in FIG.

In step 110, of the image pickup areas of the CCD camera 32, only the area where the sign is considered to be picked is selected, and the image of the sign is acquired with an increased resolution (ie, enlarged). At this time, the zoom lens 30
It is more preferable to increase the focal length of the lens. In step 76, the sign is recognized based on the image thus obtained. After obtaining an image necessary for recognition, a process of selecting an imaging area of the CCD camera 32, and returning the resolution and the focal length of the zoom lens 30 to the original state is performed in step 112.

As described above, in the apparatus according to the second embodiment, a mechanism for changing the line of sight of the CCD camera 32 is not required, and as a result, the mechanism is simplified. Therefore, it is expected that the failure frequency of the device will also be reduced.

In the apparatus of the second embodiment, the photographing magnification is further increased by using the zoom lens 30. However, if the resolution of the CCD camera 32 is sufficiently high, the zoom lens 30 may not be used. .

As described above, according to the present invention, by changing the line of sight of the camera mechanically or by electrically changing the image pickup area of the image pickup device, it is different from the traveling road or the preceding vehicle. An image of another recognition target such as a sign can be acquired.
At that time, it is not necessary to newly increase the number of cameras and image processing devices. Therefore, an unreasonable increase in cost can be avoided. In addition, only when it is determined based on the own vehicle position and the sign position that there is a sign near the own vehicle, the sign recognition process is temporarily performed. Normally, only the travel path recognition and the preceding vehicle recognition are performed, and even if the recognition of the sign is added, the cycle of the recognition processing does not become long over the whole. Therefore, the traveling path recognition and the preceding vehicle recognition can be performed in an appropriate cycle time. In order to keep the cycle time within a predetermined length, it is not necessary to employ a particularly high-speed CPU, and an increase in cost can be avoided.

In addition, by making the signs even objects of recognition, it is possible to perform appropriate driving assistance or warning processing in accordance with not only the conditions of the traveling road and the preceding vehicle but also a wider range of traveling road environment. , A safer driving environment can be provided.

The embodiments disclosed this time are to be considered in all respects as illustrative and not restrictive. The scope of the present invention is defined by the terms of the claims, rather than the description above, and is intended to include any modifications within the scope and meaning equivalent to the terms of the claims.

[Brief description of the drawings]

FIG. 1 is a perspective view for explaining a first embodiment of the present invention.

FIG. 2 is a plan view for explaining the first embodiment.

FIG. 3 is a functional block diagram of the vehicle-mounted traveling road environment recognition device according to the first embodiment;

FIG. 4 is a flowchart of a process performed by the vehicle-mounted traveling road environment recognition device according to the first embodiment;

FIG. 5 is a functional block diagram of a vehicle-mounted traveling road environment recognition device according to a second embodiment;

FIG. 6 is a diagram schematically illustrating an imaging surface of a CCD according to a second embodiment.

FIG. 7 is a flowchart of a process performed by the vehicle-mounted traveling road environment recognition device according to the second embodiment;

[Explanation of symbols]

 Reference Signs List 12 Camera 14 Road sign 30 Zoom lens 32 CCD camera 34 Image processing device 36 Zoom drive device 38 Actuator 40 Judgment / control CPU 42 In-vehicle information terminal 44 Warning / driving assistance device 46 Position detection device 48 CD-ROM drive 50 CD- ROM 52 Resolution change unit 102 CCD imaging area 104 CCD partial imaging area

Continued on the front page F-term (reference)

Claims (8)

[Claims] An imaging unit for sequentially acquiring images; an imaging range changing unit for changing an imaging range of the imaging unit; and an image acquired by the imaging unit. An on-vehicle type roadway environment recognizing device including an image recognizing means for recognizing the environment of the vehicle. 2. The on-vehicle traveling road environment recognizing device according to claim 1, wherein the imaging range changing means includes a gaze direction changing means for changing a gaze direction of the imaging means. 3. The on-vehicle traveling road environment recognizing device according to claim 2, wherein said imaging range changing means further includes an imaging magnification changing means for changing a magnification of imaging by said imaging means. 4. The on-vehicle traveling road environment according to claim 1, wherein said imaging means includes a CCD camera, and said imaging range changing means includes means for changing a size of an imaging area of said CCD camera. Recognition device. 5. The CCD camera includes more imaging pixels than the number of pixels used for image processing by the image processing means, and furthermore, the resolution of the CCD camera at the time of photographing depends on the size of the imaging area. 5. The on-vehicle traveling road environment recognition device according to claim 4, further comprising a resolution changing unit for changing the driving road environment. 6. A sign position storing means for storing position information of a sign provided around a traveling road; a position detecting means for detecting a vehicle position; an output of the position detecting means and the sign position The on-vehicle traveling road environment recognition device according to claim 1, further comprising: an imaging range control unit configured to control a change in an imaging range by the imaging direction changing unit based on the position information of the sign stored in the storage unit. . 7. The image pickup range control means determines whether or not a sign exists in a predetermined range from a vehicle position based on an output of the position detection means and position information of the sign stored in the sign position storage means. Determining means for determining, in response to the determination means determining that the sign is present in a predetermined range from the vehicle position, the imaging range by the imaging range change means to the range in which the sign can be photographed Means for temporarily changing, and the image recognition means for recognizing the sign photographed by the image pickup means in response to the judgment means judging that the sign exists within a predetermined range from the vehicle position. Means for temporarily changing the contents of the image recognition processing by the means. 8. The on-vehicle type vehicle according to claim 1, further comprising: means for performing a driving assistance operation of the vehicle according to an environment of a traveling path recognized by said image recognition means. Roadway environment recognition device.