JP2003329463A - Object guide apparatus and method - Google Patents

Abstract

(57) [Summary] [Problem] There is a demand to know on the spot the name of a mountain or the like that can be seen outside a vehicle when driving. When a driver switches to an object guidance mode by an operation of a remote controller, a CPU obtains a current position and a traveling direction of an own vehicle, and captures an image of a driver's face with a video camera. When the driver inputs a voice from the microphone 15 with his / her face directed toward the mountain, for example, "What is that mountain?", The voice recognition processing unit 14 recognizes the content of the question. The object detecting means 24c of the CPU 24 reads the name of the queried mountain in the direction of the driver's face from the map data based on the current position and the traveling direction of the vehicle, and outputs the read name to the speaker 18 or the liquid crystal display 7.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an object guide device and method capable of displaying the name of a recognition object such as a mountain or a building visible on the outside of a traveling vehicle.

[0002]

2. Description of the Related Art Conventionally, as an object guide device of this type,
For example, Japanese Unexamined Patent Publication No. 9-42987 discloses a vehicle-mounted map display device that reads out the corresponding map information by voice recognition processing and displays the name of a corresponding facility when a skiing area, a golf course, or the like is voice-input while the vehicle is traveling. It is disclosed. Further, Japanese Patent Application Laid-Open No. 8-327375 discloses a landscape display system that reads out three-dimensionally the topographical information relating to the landscape in the traveling direction when the vehicle is traveling from the storage device.

[0003]

However, in the object guide device described in the above-mentioned JP-A-9-42987,
By limiting the recognition target words in voice recognition to the vehicle travel route or the place name of the vehicle travel area, it is possible to prevent a decrease in processing speed and increase the voice recognition rate while performing map operation and information retrieval of areas not displayed on the screen. It was made possible and could not be displayed if the names of mountains and buildings visible on the outside of the vehicle were unknown. In addition, JP-A-8
According to the publication No. 327375, the image of the scenery seen by the observer can be displayed three-dimensionally on the screen of the display device, but the name of the object cannot be displayed.

The present invention solves such a conventional problem, and even if the names of mountains, buildings, etc. visible on the outside of the vehicle are not known, the object guide device can display the names immediately. And to provide a method thereof.

In order to achieve the above object, the object guiding apparatus of the present invention comprises an input means for inputting a vocabulary relating to a recognition object, and a map data storage means for storing the name and position data of the recognition object. Current position detection means for detecting the current position of the vehicle, face detection means for detecting the direction of the driver's face at the current position, and the above-described vocabulary based on the recognition target object in the driver's face direction. An object detection means for detecting the name of the recognition object from the map data and an output means for outputting the detected name of the recognition object are provided. With this configuration, the driver turns his / her face toward the recognition target object, for example, "what is that?"
By simply inputting, it is possible to immediately search for and output a proper name such as a mountain visible on the outside of the vehicle or a general name such as a building.

Further, the object guiding apparatus of the present invention comprises a traveling direction detecting means for detecting the traveling direction of the own vehicle, and detects the direction of the driver's face with reference to the traveling direction at the present position of the own vehicle. It is characterized by doing. With this configuration, the direction of the driver's face can be specified as the number of directions from the direction in which the vehicle is currently traveling.

Further, the object guiding apparatus of the present invention comprises absolute azimuth detecting means for detecting an absolute azimuth, and detects the direction of the driver's face based on the absolute azimuth detected by the absolute azimuth detecting means. It is characterized by that. With this configuration, the direction of the driver's face can be specified based on the absolute azimuth obtained by the driver from the geomagnetometer or the like worn on the helmet or hair band of the head.

Further, the object guiding apparatus of the present invention comprises a video camera for photographing the driver's face and image processing means for detecting the direction of the face from the photographed driver's face image. It is characterized by. With this configuration, it is possible to easily detect the direction of the driver's face.

Further, the object guiding apparatus of the present invention comprises a video camera for photographing the driver's face and image processing means for detecting the direction of the eyeball from the photographed driver's face image. It is characterized by. With this configuration, it is possible to easily detect the direction of the line of sight of the driver.

Further, the object guiding apparatus of the present invention is characterized in that the video camera is an infrared camera. With this configuration, it is possible to easily detect the direction of the driver's face or line of sight even in a dark environment such as at night.

Further, in the object guiding apparatus of the present invention, the input means recognizes the inputted voice by voice input means for inputting a vocabulary about the recognition object by voice, and identifies the name of the recognition object. And a voice recognition means for extracting. With this configuration, the driver can inquire about the recognition target object while operating the steering wheel by speaking while pointing the face toward the recognition target object.

Further, the object guiding apparatus of the present invention is characterized in that the input means is a push button switch. With this configuration, the driver pushes the push button switch while facing the face to the recognition target,
It is possible to ask a question about the recognition target object without speaking.

Further, the object guiding apparatus of the present invention is characterized in that the object detecting means outputs only one name of the object to be recognized in the direction of the driver's face. With this configuration, for example, when mountains are connected, only the unique name of the most characteristic mountain can be output. Further, when a building exists in the mountain, only one more characteristic name can be output.

Further, the object guiding apparatus of the present invention is characterized in that the object detecting means outputs a plurality of names of recognition objects in the direction of the driver's face. With this configuration, for example, when mountains are connected,
It is possible to output the unique names of the characteristic mountains. When a building exists in a mountain, the mountain unique name and the building unique name or general name can be output.

Further, the object guiding apparatus of the present invention is characterized in that the object detecting means outputs the name of the recognition object corresponding to the type of the inputted recognition object. With this configuration, for example, when the question "What is that mountain?" Is input, only the proper name of the mountain can be output even if there is a building in the mountain.

Further, the object guiding apparatus of the present invention is characterized in that the object detecting means outputs the name of the recognition object corresponding to the input attribute of the recognition object. With this configuration, for example, when a question "what is that round and big?" Is input, a general name such as a gas tank can be output.

Further, in the object guiding apparatus of the present invention, the output means is a speaker for outputting the detected name of the recognition object by voice. With this configuration, the driver can auditorily know the name of the recognition target object while keeping the line of sight forward.

Further, the object guiding apparatus of the present invention is characterized in that the output means is a display device for displaying the detected name of the recognition object by characters or pictures. With this configuration, the name of the recognition object can be visually known by looking at the display.

Further, the object guiding apparatus of the present invention is characterized in that the display device highlights the recognition object to be displayed. With this configuration, for example, the recognition target object can be clearly distinguished from the others by flashing characters, pictures, backgrounds, and the like of the visual recognition target object, displaying in bold characters, or enlarged display.

Further, the object guiding method of the present invention includes the steps of inputting a vocabulary relating to the recognition object, detecting the current position of the vehicle, and detecting the direction of the driver's face at the current position. And a step of detecting from the map data a name of the recognition target object based on a vocabulary about the recognition target object in the direction of the driver's face, and a step of outputting the detected name of the recognition target object. It is a thing. With this method, the driver turns his / her face toward the recognition target object and, for example, simply inputs "What is that?", And the unique name such as a mountain visible on the outside of the vehicle or the unique name or general name of a building etc. You can search and output immediately.

Further, the object guiding method of the present invention comprises a step of inputting a vocabulary related to the recognition object by voice and a step of recognizing the content of the vocabulary input by voice. With this method, the driver can ask a question about the recognition target object by speaking while facing the recognition target object.

Further, the object guiding method of the present invention comprises the step of photographing the driver's face with a video camera and detecting the driver's face direction or eyeball direction. With this configuration, it is possible to easily detect the direction of the line of sight of the driver.

Further, the object guiding method of the present invention comprises a step of outputting the detected name of the recognition object as a voice, a character, an image or a combination thereof. With this configuration, the driver can easily know the name of the recognition target object.

The object guide device of the present invention is an in-vehicle navigation device equipped with any one of the above object guide devices, and the function as the navigation device can be expanded to increase the added value.

[0025]

BEST MODE FOR CARRYING OUT THE INVENTION Embodiments of the present invention will be described below with reference to the drawings. FIG. 1 shows the configuration of a vehicle-mounted navigation device equipped with the object guide device of the present invention. In FIG. 1, the azimuth sensor 1 is a means for detecting the traveling azimuth of the own vehicle using a three-dimensional gyro. The vehicle speed sensor 2 generates a vehicle speed pulse according to the number of rotations of the wheels of the vehicle equipped with this device. The various sensors 3 are a reverse switch, a parking switch, a light switch, etc., and detect the running state of the vehicle. The DVD-ROM drive 4 reads map data, voice data, voice recognition dictionary data, etc. from the DVD-ROM. The wireless transceiver 5 is for exchanging data with an information center or the like, and may be of a type for exchanging data with the information center or the like by connecting a mobile phone. The GPS receiver 6 obtains the current position (latitude / longitude) and azimuth of the vehicle by calculating radio waves from a plurality of satellites received by a GPS antenna. The liquid crystal display 7 displays a map and the current vehicle position, direction, operation menu, etc., and has a touch panel on the front surface of its display screen. The remote controller 8 has operation buttons for the user to instruct various requests and commands. The remote control light receiving section 9 is provided on a part of the front panel of the liquid crystal display 7, and receives an infrared signal from the remote control 8. The DVD-ROM drive 4, the wireless transmitter / receiver 5, the GPS receiver 6, the liquid crystal display 7 and the like are integrated and arranged on the dashboard of the vehicle.
Communication interface 22 of the apparatus main body 11 through 10
It is connected to the. The device main body 11 is installed in a trunk room of a vehicle or a center console in the vehicle.

In the apparatus main body 11, the image signal processing unit 1
2 performs image processing on the road sign captured by the video camera 13 and outputs it as road sign image data. The video camera 13 is attached in the vicinity of the rear-view mirror in the front upper part of the driver's seat in the vehicle to photograph the face of the driver, and may be equipped with illumination for illuminating the driver's face.
The voice recognition processing unit 14 recognizes the voice input from the microphone 15. The microphone 15 is arranged near the video camera 13. Sensor signal processing unit 1
6 calculates the traveling direction of the vehicle based on the signal from the azimuth sensor 1, calculates the traveling distance from the vehicle speed signal from the vehicle speed sensor 2, and further calculates the traveling state of the vehicle based on the signals from the various sensors 3. It detects and produces the signals required for control. The voice processor 17 converts a voice recognition result into a voice signal, and outputs a voice signal indicating a search result, voice guidance on a traveling route, and operation content of a remote controller to the speaker 18. The speaker 18 is used when a search result, a voice recognition result, voice guidance such as intersection guidance on a travel route, branch guidance, tollgate guidance, and exit guidance, and voice instructions for operation contents on the remote controller. The image processor 19
Menu data, map data, current position data of your vehicle,
A display image is generated based on building data and the like. The storage unit 20 includes a ROM storing a program, a RAM temporarily storing work data, and a VR storing image data.
It is composed of AM, etc. The display control unit 21 reads necessary image data from the image processor 19 to create drawing data, and also performs image deformation (simplification) processing, scale change processing, and the like. The communication interface 22 controls communication between an external device such as the DVD-ROM drive 4 and the device body 11. The data storage unit 23
If the hard disk drive is not a DVD-ROM storing road map data, a large amount of data such as road map data and word dictionary data for voice recognition is downloaded from the information center via the wireless transceiver 5. Accumulate. A CPU (Central Processing Unit) 24 controls the entire device and controls the current position / direction detecting means 24a, route searching means 24b, and object detecting means 24c.

Next, regarding the operation of this embodiment, the basic operation of the navigation device will be described first. In FIG. 1, when the vehicle engine is started, the power of the device is turned on, a menu screen is displayed on the liquid crystal display 7, and the CPU 24 causes the current position / orientation detecting means 2 to operate.
The program of 4a is started, the position and direction information from the GPS receiver 6, the direction sensor 1 and the vehicle speed sensor 2
Based on the data obtained by processing the signal from the sensor signal processing unit 16, the accurate current position and traveling direction of the own vehicle are calculated. Based on this vehicle position information, the CPU 24
-Corresponding map data is read from the DVD-ROM through the ROM drive 4, converted into image data by the image processor 19 and temporarily stored in the VRAM of the storage unit 20, and then converted into color signals, and then the liquid crystal display 7 through the communication interface 22. Is displayed together with the vehicle position mark on the screen. When an address name such as a destination is input through the microphone 15, the voice recognition function of the voice recognition processing unit 14 recognizes the address name and sets the destination. When the destination is set, the CPU 24 activates the program of the route searching means 24b, calculates an optimum guide route from the current position of the vehicle to the set destination, and displays the map displayed on the liquid crystal display 7. Display on top. When the user advances the vehicle along the guide route displayed on the liquid crystal display 7, the CPU 24 sets the map displayed on the liquid crystal display 7 to the traveling direction side based on the current position information and the road network data on the map data. While scrolling sequentially, the position of the vehicle position mark is updated sequentially.
When the vehicle approaches a branch point or the like in the guide route, the voice guidance added to the map data is created as synthesized voice by the voice processor 17 and output from the speaker 18.

Next, the operation of the object guide device according to this embodiment will be described with reference to FIG. When the driver presses the object guidance mode switching button from the remote control 8, CP
U24 switches from the navigation mode to the object guidance mode (step S1). Next, the CPU 24
The current position and running direction of the vehicle detected by the current position / direction detecting means 24a are acquired, and the video camera 13 starts photographing the driver's face (step S2). Next, if the driver is an object to be recognized, for example, a mountain, turn his or her face in the direction of the mountain, and a vocabulary about the object to be recognized such as "what is that?" Or "what is that mountain?" When inputting and asking a question (step S3), the voice recognition processing unit 1
Reference numeral 4 compares the voice data of the word input from the microphone 15 with the voice data of the word dictionary read by the DVD-ROM drive 4, and outputs one or a plurality of highly similar words to the CPU 24 as a voice recognition result. Yes (step S4). On the other hand, the image signal processing unit 12 performs image processing on the face image signal obtained by photographing the driver's face to detect the driver's line of sight (step S5).

FIG. 3 shows the processing in the image signal processing section 12. In FIG. 3, when a face image signal is input from the video camera 13 (step S11), unnecessary noise and the like are removed, and then the image signal is converted from an analog signal to a digital signal (step S12). Next, only the image of the eyeball portion in the face is extracted by the background difference processing (step S13). Since the eyeball part in the face is circular and is clearly distinguished from other parts, the background difference processing unit 27 sets the part other than the eyeball as the background.
By removing only the background part from the captured image,
Extract only the eyeball part. The extracted eyeball image data is binarized (step S14), and then the feature amount of the eyeball image data is calculated (step S15). When viewed from the front, the eyeball is almost a perfect circle, but when the face is tilted, the eyeball changes to an elliptical shape according to the degree, so that the gaze direction can be detected from the amount of change. That is, the driver's line-of-sight direction is detected by comparing the calculated area of the eyeball image data with the reference feature amount data stored in the storage unit 20 (step S16), and the line-of-sight direction signal is output ( Step S17).

In FIG. 2, when a line-of-sight direction signal is received from the video signal processing unit 1, the object detecting means 24 of the CPU 24.
From the output line-of-sight direction signal, c extracts one or more names of mountains or buildings existing in the line-of-sight direction with reference to the current position from the map data of the storage unit 20 (step S6), and extracts the name. The name of the mountain is output by voice from the speaker 18 (step S7).

As described above, according to the present embodiment, when the mode is switched to the object guide mode by the operation from the remote controller 8, the CPU 24 acquires the current position and the traveling direction of the own vehicle and the face of the driver. Is photographed by the video camera 13, and the driver inputs voice from the microphone 15 with his face facing the mountain, for example, "What is that mountain?", The voice recognition processing unit 14 recognizes the content of the question, and the target of the CPU 24. The object detecting means 24c reads out the name of the mountain in the direction of the driver's face from the map data based on the current position and traveling direction of the own vehicle and outputs it to the speaker 18 or the liquid crystal display 7, so that the outside of the vehicle. It is possible to immediately search for and output the names of mountains and the like that look like. In addition, since the object guide device of the present invention is incorporated in the vehicle-mounted navigation device, it is possible to share each part to simplify the configuration and expand the function of the vehicle-mounted navigation device.

In the above embodiment, the CPU 24 acquires the current position and traveling direction of the own vehicle after switching to the object guide mode, and the video camera 1
Although the driver's face is photographed by 3 and the input voice is recognized by voice, the CPU 24 constantly detects and stores the current position and traveling direction of the own vehicle, and the face of the driver by the video camera 13 is stored. The image data is stored by always taking the image, and the data is updated sequentially after the predetermined time set by the timer. When the object guidance mode is switched, the input voice is recognized and the face image data is image processed. Then, the line-of-sight direction of the driver may be detected.

In the above embodiment, the eyeball image is extracted from the driver's face image to detect the driver's line-of-sight direction. However, the driver's face should be oriented so that the driver faces the recognition target. By previously determining the method of using the device, the face direction can be set as the line-of-sight direction without extracting the eyeball image. Further, in the above embodiment,
The direction of the driver's face or line of sight was detected based on the driving direction at the current position of the vehicle, but an electronic geomagnetometer, which is an absolute direction detecting means, was attached to the helmet or hairband worn by the driver on the head. However, by obtaining the absolute azimuth signal from this geomagnetometer, the direction of the driver's face or line of sight can be detected with the absolute azimuth as a reference.

In the above embodiment, the driver's face is photographed by the video camera. However, the photographed image can be displayed on the liquid crystal display 7 so that it can be monitored.
The position of the eyeball can be taken as a shooting target. Further, by using the infrared camera as the video camera, it is possible to detect the direction of the driver's face or line of sight even in a dark environment such as at night.

Further, as the input means, the vocabulary concerning the recognition target object is inputted by voice from the microphone 15. However, the push button switch of the remote controller 8 or the touch switch arranged on the front surface of the liquid crystal display 7 is pushed,
When switching from the navigation mode to the object guidance mode, the device can be designed in advance assuming that the signal inputs a vocabulary equivalent to “what is that?” As a question. Also, by attaching a "name notification button" for setting such a silent mode to the handle and pressing the button, it is possible to ask a question about the recognition target object without uttering.

Further, the object detecting means 24c outputs the word of the type when the question including the type of the object to be recognized is received by the voice recognition processing section 14, so that the object to be recognized according to the type is recognized. The name of an item can be output.
For example, when the question "What is that mountain?" Is input, the unique name of only the mountain is output even if there is a building in the mountain. Further, when there is a question including the attribute of the recognition target object, the name of the recognition target object according to the attribute can be output. For example, when a question "What is that round and big one?" Is input, a general name such as gas tank is output. In order to make these possible, it is necessary to store the name of the recognition target object and the words related to its type and attribute in association with each other in the word dictionary for voice recognition.

As the output means, the name of the recognition target object is output by voice from the speaker 18. However, the name of the recognition target object may be displayed on the screen of the liquid crystal display 7 by a character or a deformed image. Good. At that time, by flashing the characters and images of the visual target, the background, etc., displaying in bold type, or enlarging the display,
The recognition target can be displayed distinctly from the others.

Further, the voice data or characters and the image data of the name of the detected object are stored in the storage unit 20 or the data storage unit 23 together with the position data, and later,
When traveling on the same route, the name of the mountain or the building may be automatically output when the vehicle arrives at that position.

In the above description, the driver of the vehicle has been described, but it goes without saying that the same object guidance can be performed for other occupants by using the same device.

[0040]

As described above, the object guiding apparatus of the present invention includes the input means for inputting the vocabulary relating to the recognition object, the map data storage means for storing the name and position data of the recognition object, and Current position detection means for detecting the current position of the vehicle, face detection means for detecting the direction of the driver's face at the current position, and name of the recognition target object based on the vocabulary of the recognition target object in the driver's face direction Is provided from the map data and output means for outputting the name of the detected recognition target object, so that the driver simply asks his / her face toward the recognition target object and the outside of the vehicle It is possible to immediately search for and output the names of mountains, buildings, and the like that can be seen, which can be useful for grasping the current position and confirming the target.

Further, the object guiding method of the present invention includes the steps of inputting a vocabulary relating to the recognition object, detecting the current position of the vehicle, and detecting the direction of the driver's face at the current position. , The step of detecting from the map data the name of the recognition target object based on the vocabulary relating to the recognition target object in the direction of the driver's face, and the step of outputting the name of the detected recognition target object Can immediately search and output the names of mountains, structures, etc. that are visible on the outside of the vehicle by simply asking their faces to the recognition target, which can be useful for grasping the current position and confirming the target. it can.

[Brief description of drawings]

FIG. 1 is a block diagram showing a configuration of an in-vehicle navigation device including an object guide device according to an embodiment of the present invention.

FIG. 2 is a flowchart showing an object guidance process in the embodiment of the present invention.

FIG. 3 is a flowchart showing a driver gaze direction detection process in the embodiment of the present invention.

[Explanation of symbols]

1 Direction sensor 2 vehicle speed sensor 3 Various sensors 4 DVD-ROM drive 5 wireless receiver 6 GPS receiver 7 LCD display 8 remote control 9 Remote receiver 10 Car LAN 11 Device body 12 Image signal processor 13 video camera 14 Speech recognition processing unit 15 microphone 16 Sensor signal processor 17 Voice Processor 18 speakers 19 Image processor 20 memory 21 Display control unit 22 Communication interface 23 Data storage unit 24 CPU 24a Current position / direction detecting means 24b Route search means 24c Object guide means

Front page continuation (51) Int.Cl. ⁷ Identification code FI theme code (reference) G10L 15/22 G10L 3/00 R 5H180 15/24 571G 15/28 571T H04N 5/225 F term (reference) 2F029 AA02 AB01 AC03 AC04 AC14 AC16 5B057 AA16 BA02 CE12 DA08 DB02 DB05 DB09 DC08 DC22 DC33 5C022 AA01 AA15 5D015 KK01 KK02 KK04 5D045 AB21 5H180 AA01 CC04 EE02 FF04 FF14 FF22 FF27 FF32 FF38 FF40

Claims (20)

[Claims] 1. Input means for inputting a vocabulary relating to a recognition target object, map data storage means for storing the name and position data of the recognition target object, current position detection means for detecting the current position of the vehicle, and Face detecting means for detecting the direction of the driver's face at the current position, and object detection for detecting the name of the recognition object based on the vocabulary of the recognition object in the direction of the driver's face from the map data. An object guide device comprising means and output means for outputting the detected name of the recognition object. 2. A driving direction detecting means for detecting a traveling direction of the own vehicle is provided, and the direction of the driver's face is detected with reference to the traveling direction at the present position of the own vehicle. The described object guidance device. 3. The absolute azimuth detecting means for detecting an absolute azimuth is provided, and the direction of the driver's face is detected based on the absolute azimuth detected by the absolute azimuth detecting means. Object guide device. 4. A video camera for photographing the driver's face, and image processing means for detecting the direction of the face from the photographed driver's face image. The object guide device according to any one of 1. 5. A video camera for photographing the driver's face, and image processing means for detecting the direction of the eyeball from the photographed driver's face image. The object guide device according to any one of 1. 6. The object guide device according to claim 4, wherein the video camera is an infrared camera. 7. The input means comprises voice input means for inputting a vocabulary related to a recognition target object by voice, and voice recognition means for recognizing the input voice and extracting the name of the recognition target object. Claims 1 to 6 characterized in that
The object guide device according to any one of 1. 8. The object guide device according to claim 1, wherein the input unit is a push button switch. 9. The object according to claim 1, wherein the object detecting unit outputs only one name of a recognition object in a direction of the driver's face. Object guidance device. 10. The object guide according to claim 1, wherein the object detection unit outputs a plurality of names of recognition objects in a direction of the driver's face. apparatus. 11. The object detecting means outputs the name of a recognition object corresponding to the type of the input recognition object, according to any one of claims 1 to 10. Object guidance device. 12. The object detecting means outputs a name of a recognition target object corresponding to an attribute of the input recognition target object, according to any one of claims 1 to 11. Object guidance device. 13. The object guide apparatus according to claim 1, wherein the output unit is a speaker that outputs the name of the detected recognition object by voice. 14. The object according to claim 1, wherein the output unit is a display device that displays the name of the detected object to be recognized by characters or pictures. Guidance device. 15. The display device highlights the recognition target object to be displayed.
4. The object guide device described in 4. 16. A step of inputting a vocabulary relating to a recognition target object, a step of detecting a current position of the vehicle, a step of detecting a direction of a driver's face at the current position, and a direction of the driver's face. In the object guidance method, the step of detecting the name of the recognition object based on the vocabulary relating to the recognition object from the map data and the step of outputting the detected name of the recognition object. 17. The object guiding method according to claim 16, further comprising: a step of inputting a vocabulary related to the recognition target object by voice, and a step of recognizing the content of the vocabulary input by the voice. 18. The object guiding method according to claim 16, further comprising the step of photographing the driver's face with a video camera to detect the driver's face direction or eyeball direction. 19. The object guiding method according to claim 16, further comprising the step of outputting the detected name of the recognition object by voice, characters, an image, or a combination thereof. 20. An in-vehicle navigation device comprising the object guide device according to claim 1.