JP6623657B2 - Information providing apparatus, information providing system, and information providing method - Google Patents

Description

  The present invention relates to an information providing device, an information providing system, and an information providing method.

  Regarding this type of device, a technique is known that acquires an information package such as an e-mail including location information and acquisition information, extracts the location information and acquisition information from the received information package, and registers the acquisition information based on the location information. (Patent Document 1).

JP 2006-290027 A

  However, in the conventional apparatus, since the target is identified based on the position information, a movable target cannot be identified, and there is a problem that it is difficult to share information on the movable target.

  The problem to be solved by the present invention is to be able to share information about movable objects.

  The present invention identifies an object existing around a vehicle using an image captured by a camera, extracts text information about an object existing around the vehicle from audio information collected by a microphone, and identifies the object. The above object is achieved by outputting a target and text information related to the target in association with each other.

  According to the present invention, information on a movable object can be shared by a plurality of users.

It is a block configuration diagram of an information providing system according to the present embodiment. It is a figure showing an example of the dictionary of this embodiment. It is a figure showing an example of object information of this embodiment. It is a figure showing an example of the collection information of this embodiment. It is a figure showing the 1st example of a display of offer information of this embodiment. It is a figure showing the 2nd example of a display of offer information of this embodiment. 5 is a flowchart illustrating a control procedure of the information providing apparatus according to the embodiment. 5 is a flowchart illustrating a control procedure of the server according to the embodiment.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the present embodiment, an example in which the information providing apparatus 100 according to the present invention is applied to the information providing system 1 will be described. The information providing system 1 of the present embodiment is used in a vehicle. That is, it is used by the user who gets on the vehicle.

FIG. 1 is a diagram illustrating a block configuration of an information providing system 1 according to the present embodiment.
The information providing system 1 of the present embodiment collects information on an object that the user encounters while moving, and provides information on an object that the user encounters while moving, via the information providing device 100 of the user.

  The information providing system 1 according to the present embodiment includes one information providing apparatus 100, another information providing apparatus 100N, and a server 200.

  The information providing apparatus 100 according to the present embodiment includes a communication device 120, and exchanges information with another plurality of information providing apparatuses 100N and the server 200. In this specification, from the viewpoint of simplifying the description, the configuration and operation of one information providing apparatus 100 will be described, and the description of the configuration and operation of another information providing apparatus 100N that is common to this will be omitted. The number of the information providing apparatuses 100 and 100N is not limited.

  The server 200 of the present embodiment includes an information acquisition device 210 that acquires target information from each information providing device 100. The information acquisition device 210 includes a communication device 211. The server 200 has a database 220 for storing the acquired target information. The server 200 has an output device 230 that outputs text information to be displayed on the information providing device 100. The output device 230 sends a text information output command to the information acquisition device 210 via the communication device 211.

The information providing device 100 according to the present embodiment will be described.
The information providing apparatus 100 of the present embodiment presents target information on a target in response to a request from a user. The content of the target information is not limited. The information providing device 100 may be configured as an in-vehicle device, or a smartphone or a PDA (Personal Digital
Assistance) or the like.

  As shown in FIG. 1, the information providing apparatuses 100 and 100N of the present embodiment (hereinafter, described by adding 100 as a representative code) include a control device 10, a camera 20, and a microphone 30. The information providing device 100 of the present embodiment further includes a navigation device 110, a communication device 120, and an output device 130. In the information providing apparatus 100 mounted on the vehicle side, the above-described devices are mutually connected by a CAN (Controller Area Network) or other in-vehicle LAN.

  The camera 20 of the present embodiment captures an image around the vehicle. The camera 20 is a camera using an image sensor such as a CCD. The lens may be a telephoto lens with a narrow viewing angle that can capture images in the distance, a fisheye lens with a wide field of view to respond to changes in the curve or gradient of the running path, or a lens for an omnidirectional camera that can capture the entire circumference May be. Although the mounting position of the camera 20 is not limited, in the present embodiment, the camera 20 is installed near the interior mirror of the host vehicle and facing the front of the vehicle. This is for adjusting the imaging direction of the camera to the line of sight of the driver of the own vehicle. Note that imaging characteristic information such as an internal parameter such as a lens distortion of the camera 20 and an external parameter indicating a mounting position with respect to the vehicle are stored in a ROM in advance. The camera 20 outputs the captured image via an output device 130 described below.

The microphone 30 is arranged in the vehicle interior, acquires voice information of a user who gets on the vehicle , and at least temporarily stores the voice information. The mounting position of the microphone 30 is not limited, but is preferably provided near the vehicle seat.

  The navigation device 110 according to the present embodiment includes a position detection device 111, map information 112, and POI information 113. The so-called POI (point of interest) information includes information on stores, restaurants, banks and other facilities, event information, traffic regulation information, and the like. The navigation device 110 guides the driver by indicating a route from the current position of the vehicle to the destination. Further, the navigation device 110 can communicate with the outside, and can acquire POI information, traffic regulation information, and the like of each point via a communication line. The navigation device 110 outputs the obtained information and the calculated information via an output device 130 described later.

  The position detection device 111 includes a GPS (Global Positioning System). The position detection device 111 can also acquire the position information provided by an intelligent transport system (ITS) mounted on the roadside device as the current position of the own vehicle via short-range communication.

  The output device 130 has a display 131 and a speaker 132. The display 131 presents the acquired target information. The speaker 132 reads out text information included in the acquired target information.

  Subsequently, the control device 10 of the present embodiment will be described. The control device 10 included in the information providing apparatus 100 according to the present embodiment executes a ROM (Read Only Memory) 12 storing a program for generating and outputting target information, and a program stored in the ROM. The computer includes a CPU (Central Processing Unit) 11 as an operation circuit functioning as the information providing apparatus 100 and a RAM (Random Access Memory) 13 functioning as an accessible storage device.

  The control device 10 has an identification function, an extraction function, and an output function. The control device 10 executes each function by cooperation of software for realizing the above functions and the above hardware. Hereinafter, each function of the information providing apparatus 100 according to the present embodiment will be described.

  The identification function of the control device 10 will be described. The control device 10 extracts features of the image captured by the camera 20 and identifies an object existing around the vehicle based on the features of the extracted image. The identified “target” is a target of a common topic of a plurality of users. The attribute of the “target” is not limited as long as the mobile user can visually recognize the target. The “target” may be a store or facility near the travel route, a vehicle passing or being overtaken in the travel route, a natural object (Mt. Fuji) or a building (Tokyo) visible in the travel route. Sky Tree).

  The control device 10 extracts features of the captured image. The feature extraction method is not particularly limited. The control device 10 extracts an edge, and extracts a shape obtained from the edge as a target feature. The control device 10 extracts a character or a character string included in the captured image as a target feature. The control device 10 extracts a figure included in the captured image as a target feature.

  When the object is moving, the position cannot be used to identify the object. Therefore, the control device 10 identifies the moving target from the morphological characteristics of the target. Specifically, when the appearance of the target is a special vehicle (an ambulance, a police vehicle, a construction vehicle), the control device 10 determines the appearance (shape, pattern, color) of the vehicle by another vehicle (special). Vehicle). The control device 10 may identify the attributes of the vehicle based on the difference in the appearance of the vehicle. By identifying the attributes of the vehicles, it is not possible to specify them, but the target vehicles can be narrowed down. The attributes of the vehicle are sedan type, land cruiser, sports car, minicar, truck, camper and the like. Even if the target is narrowed down to some extent by the identification such as “sports car”, the target is a common topic of a plurality of users. When the target is a vehicle, the control device 10 extracts a character / symbol string written on the license plate of the vehicle as a feature of the target other vehicle. According to the vehicle number, a specific vehicle can be identified.

  The target is not limited to the mobile object itself, and may be, for example, an event that the mobile object advertises. For example, when the truck is advertising the event using the outer surface of the bed, the control device 10 determines the contents of the event, the subject (artist) of the event, and the venue of the event described on the bed portion of the truck. Is extracted as a feature.

  When the target is a store that does not move, the feature of the shape of the entrance of the store can be extracted as the feature of the target store. Similarly, when the target is a facility, the feature of the shape of the trademark (mark) drawn on the signboard of the facility can be extracted as the feature of the target facility.

  Even if the target does not move, when the host vehicle moves, the appearance (shape in the captured image) of the target differs depending on the position of the host vehicle. In such a case, the position information of each point stored in advance, the characteristics of a captured image when an object (Mt. Fuji, Tokyo Sky Tree) is imaged from each point, and the identification information of the object correspond to each other. Use the attached master image information. The controller 10 can refer to the master image information and identify the target based on the current position of the vehicle and the characteristics of the target extracted from the image captured by the camera 20 mounted on the vehicle. The control device 10 compares the characteristic of the master image information with the characteristic of the image captured by the camera 20 and, on condition that the matching rate of the characteristic is higher than a predetermined value, the target included in the image captured by the camera 20. Perform identification processing. The method of identifying the target using the captured image is not particularly limited, and an image recognition technique known at the time of filing can be appropriately used.

  The control device 10 may use the position and / or time at which the target exists in the target extraction processing. Since the target is visible to the user boarding the own vehicle, the position of the target can be associated with the current position of the own vehicle (user). The current position of the host vehicle (user) can be obtained from the position detection device 111. The control device 10 can narrow down the position where the target exists by using the current position of the own vehicle at the timing when the target is imaged, the imaging direction of the camera 20 and its imaging characteristics.

  When a plurality of target identification results are obtained, the control device 10 presents the plurality of identification results to the user and accepts the user's selection information. Specifically, the control device 10 displays a plurality of identification results as options on a touch-panel display 131 that accepts information input. The control device 10 identifies one identification result touched by the user as a target recognized by the user in the vehicle.

  Next, the extraction function of the control device 10 will be described. The control device 10 extracts text information on an object existing around the vehicle from the voice information. The control device 10 cuts out the utterance of the user collected by the microphone 30 in a predetermined unit such as a word, and calculates the degree of coincidence between each cut-out word and a word recorded in the dictionary. The control device 10 determines a word having a matching degree equal to or more than a predetermined value as a spoken word. The method of recognizing the uttered voice is not particularly limited, and a voice recognition technique known at the time of filing can be appropriately used.

  The target identification processing may be performed in the information providing apparatus 100 or may be performed in the server 200 capable of exchanging information with the information providing apparatus 100.

  The information providing apparatus 100 has an accessible dictionary 14. The control device 10 reads the dictionary 14. The dictionary 14 is a dictionary that associates an object with text information about the object. This dictionary is used when extracting text information on a target from audio information. The dictionary 14 may be stored in the information providing apparatus 100, or may be stored in a server 200 accessible by the information providing apparatus 100.

  FIG. 2 is an example of the mode of the dictionary 14. As shown in FIG. 2, in the dictionary 14, a target identifier, a target attribute, and a plurality of pieces of text information are associated with each other. The text information included in the dictionary 14 may be a sentence or a word constituting the sentence.

  For example, assume that the target W1 shown in FIG. 2 is a restaurant. An attribute (W1) for specifying the target W1 as a facility is associated with an attribute related to the target W1. The attributes defined in this example include the category of the target W1, the name of the target W1, the action performed on the target W1, the impression and experience of the target W1, and the position of the target W1. The definition of the attribute can be appropriately defined for each object.

  The target W1 is associated with text information on the target W1. The text information in the dictionary 14 is defined by predicting a text that may be emitted for the target W1. The text information in the dictionary 14 may be defined by extracting text information having a large number of occurrences from text information actually collected from the user.

  For example, in the example shown in FIG. 2, the text information associated with the name of the target W1 is a name W1N that is the name of the target W1 itself (completely identical), a shortened name W1a, and a name W1b that is familiar as a nickname. , Name W1c. The text information associated with the category of the target W1 includes “Restaurant”, “Italian”, “Lunch”, and “Sweets” which are the contents of the provided service. The text information associated with the action performed in the target W1 includes “meal”, “eat”, and “tea”. Considering the actual utterance, it may have the same meaning as “meal” but may include text information of spoken language such as “rice”. The text information associated with the impression and experience regarding the target W1 includes “taste”, “delicious”, “popular”, and “beautiful”. The text information associated with the position related to the target W1 includes “A”, “near”, “immediately”, and “convenience” of the location (administrative district name). Relative texts such as "close" and "immediately" may be described in the dictionary 14 by replacing them with specific position information obtained from the position information of the location K.

  It is assumed that the target W2 shown in FIG. 2 is a merchandise sales facility. The same attribute as W1 is defined in the identifier (W2) for specifying the facility. Similarly, text information on the target W2 is associated with the target W2. The text information associated with the name of the target W2 includes a name W2N that is the name of the target W2 itself (completely identical), a shortened name W2a, and names W2b and W2c that are familiar as nicknames. The text information associated with the category of the target W2 includes “shop”, “clothes”, “bag”, and “shoes”, which are the contents of the provided service. The text information associated with the action performed on the target W1 includes “buy”, “buy”, “want”, and “go”. The text information associated with the impression and experience regarding the target W2 includes “cute”, “fashionable”, “popular”, and “favorite”. The text information associated with the position related to the target W2 includes “K”, “close”, “immediately”, and “N minutes” of the location (administrative district name). Relative texts such as “close”, “immediately”, and “N minutes” may be described by being replaced with specific position information obtained from the position information of the location K.

  It is assumed that the target W3 shown in FIG. 2 is a road. The same attribute as V1 is defined in the identifier (W3) for specifying the road. Similarly, text information on the target W3 is associated with the target W3. The text information associated with the name of the target W3 includes the name of the target W3, for example, “Tomei Expressway”, a shortened name “Tomei”, and a direction-limited name “Tomei Up” and “Tomei Down”. The text information associated with the action performed in the target W3 includes “run”, “flow”, “go”, “go”. The text information associated with the impression and experience regarding the target W3 includes “crowded”, “traffic jam”, “accident”, and “late”. The text information associated with the position related to the target W2 includes the name “L” of the location, for example, an interchange L1, a “service area L2”, and a “junction L3”.

  Next, the output function will be described. The control device 10 outputs target information in which the identified target is associated with text information on the target. The target information is text information spoken by the user and a target of the topic of the text information. The text information included in the target information is a message regarding the target. The text information included in the target information is preferably a sentence.

  FIG. 3 shows an example of the target information. In the target information shown in FIG. 3, text information is associated with each of the identified targets P1 to P4. The text information W11, W12, and W13 are texts constituting an utterance related to the target P1.

  Further, the target information shown in this example includes text information, position information at which voice information is obtained, and the time at which the audio information was obtained. As shown in the figure, the actually acquired image information may be included in the target information. As described above, the control device 10 outputs target information in which the identified target, the position and / or time at which the target exists, and the text information on the target are associated with each other. A plurality of pieces of text information are associated with one target.

  The control device 10 sends the generated target information to the server 200. The control device 10 may transmit the information to the control device 10 of another nearby vehicle using the inter-vehicle communication.

  Next, the server 200 will be described. The information acquisition device 210 of the server 200 collects target information from the information providing device 100 of each vehicle. The server 200 stores the collected target information in the database 220 for each target.

  FIG. 4 shows an example of the collected information. In the collected target information, the target identifier is associated with the text information. The text information of the collected target information may be a sentence that is the utterance content of the user, or may be a word that constitutes the utterance content.

  The output device 230 of the server 200 distributes the collected text information to the information providing device 100 of another user. When acquiring the request information including the identified target from one information providing device 100, the output device 230 of the present embodiment sends text information on the collected target to the one information providing device 100. The output device 230 sends to the information providing device 100 information including text information and an instruction to indicate the text information. The display 131 of the information providing apparatus 100 displays text information according to the command.

  When the server 200 acquires the request information including the identified target from one information providing apparatus 100, the server 200 allows the user who issued the request information to present the target information regarding the target related to the request information. Can share information about common objects.

  The request information is automatically sent to the server 200 when the target is identified. The request information includes an identifier (ID) of the information providing apparatus 100. It is possible to automatically share utterances (murmurs) about a common target even if a user's request operation is not performed.

FIG. 5 is a diagram illustrating a first display example of target information.
The information providing apparatus 100 of the present embodiment uses the display 131 to display an actual captured image of the camera 20 of the host vehicle, and displays target information in a manner superimposed on the captured image.

  In the example shown in FIG. 5, the current position of the own vehicle is detected, and the own vehicle is traveling before the interchange X and before the service area Y on the expressway. In the example shown in the drawing, it is assumed that other vehicles V2, V3, and V4 traveling around are detected from the captured image of the own vehicle. The other vehicles V2, V3, V4 are identified from the display of the license plate.

  A display area S1 in the upper left of the display image on the display 131 in the figure is a display area for target information generated from voice information spoken by a user of another vehicle.

  It is assumed that the information providing apparatus 100N of the other vehicle V2 (not shown) identifies the other vehicle V3, and the driver of the other vehicle V2 feels that the driving of the other vehicle V3 is violent and utters the other vehicle V3. The content of the utterance is "driving is rough". The information providing apparatus 100N of the other vehicle V2 detects the other vehicle V3 from the captured image, and generates target information by associating the utterance information with the identifier of the other vehicle V3. Since the other vehicles to be discussed are likely to be vehicles that disturb the traffic flow, among the extracted other vehicles, other vehicles whose acceleration / deceleration is equal to or higher than a predetermined value or other vehicles whose speed is equal to or higher than a predetermined value May be identified as a target. Further, when a plurality of other vehicles are identified as targets, the user may be shown a target candidate to be selected.

  In this example, for the target "other vehicle V3", the driver's utterance that the driver of the other vehicle V2 is "rough driving" (so-called tweet) is displayed on the display 131 of the information providing apparatus 100 of the own vehicle V1. The fact that the target of the utterance is the other vehicle V3 may or may not be displayed. Further, in order to specify the target, a number which is an identifier of the other vehicle V3 may be displayed, but a color, a vehicle type, and the like of the other vehicle V3 may be displayed. For example, the other vehicle V3 may be expressed to such an extent that the subject of the topic can be shared. For example, when the feature that the color of the other vehicle V3 is red can be extracted from the captured image, the description may be such as "red sports car, driving is rough". At this time, the other vehicle V3 included in the captured image may be displayed with the mark M1 attached so that the other vehicle V3 can be visually identified. This mark may be displayed based on the collected and accumulated target information. For example, a mark indicating that fact may be added to other vehicles for which the utterance “Driving is violent” is collected.

  Further, according to the current position of the host vehicle V1, the utterance of the driver of another vehicle regarding the vicinity thereof may be displayed. For example, when the current position of the own vehicle is within a predetermined distance of the X interchange (IC), an utterance (murmur) of “congestion near XIC” regarding the area is displayed. Also, when the current position of the vehicle is within a predetermined distance of the Y service area (SA), an utterance (murmur) of “YSA ramen is delicious” for that area is displayed.

  Further, in the displayed captured image, the driving state of the other vehicle V4 may be displayed by a mark G1, and the driving state of the other vehicle V5 may be displayed by a mark G2. The displayed captured image may indicate the intention of the vehicle to change lanes.

FIG. 6 is a diagram illustrating a second display example of the target information.
The information providing apparatus 100 of the present embodiment uses the display 131 to display an actual captured image of the camera 20 of the host vehicle, and displays target information in a manner superimposed on the captured image.

  In the example shown in FIG. 6, the current position of the host vehicle is detected. You can see the mountain from your vehicle (you can take an image). The information providing apparatus 100 extracts the feature of the region R1 corresponding to the mountain from the captured image, and identifies that the mountain seen from the current location is Mt. Fuji from the current position of the vehicle and the features of the master image. The information providing apparatus 100 sends request information including the identifier of Mt. Fuji to the server 200. The server 200 sends another user's utterance (tweet) “Mt. Fuji is beautiful” about the target (Mt. Fuji) to the information providing apparatus 100 and causes the display 131 to display it. Although the mountain does not move, its own vehicle moves, so its relative positional relationship changes. Even in such a case, the information providing apparatus 100 of the present embodiment can specify a target that can be seen by the user, and can share information about the specified target with a user of another vehicle.

  The information providing apparatus 100 may recognize the characters in the region R1 corresponding to the sign included in the captured image, and may identify the destination of the own vehicle or a nearby facility. This is because the destination or facility of the vehicle may be the target of the utterance (murmur).

  As shown in FIG. 6, a past utterance (tweet) may be associated with the position information, and a past utterance associated with the current position of the vehicle may be displayed. For past utterances, speaker identification information (nickname) may be displayed. Further, information S2 of the accident history (seen aside, excessive speeding) occurring at the point and information S3 of the traffic tendency (frequent overtaking) may be displayed together.

  Subsequently, an operation procedure of the information providing apparatus 100 of the present embodiment will be described with reference to a flowchart of FIG. Note that the processing contents shown in FIG. 7 are continuously performed at a predetermined cycle.

  In step S110, control device 10 acquires a captured image around the vehicle captured by camera 20. The control device 10 acquires the voice information of the occupant whose sound is collected by the microphone 30.

  At the same time or before and after, in step S120, the control device 10 acquires the current position detected by the position detection device 111.

  In step S130, control device 10 identifies a target that can be visually recognized by the occupant from the captured image.

  In step S140, when there is an occupant's utterance, control device 10 proceeds to step S150. In step S150, control device 10 cuts out text information from the audio information. In step S160, the control device 10 refers to the dictionary 14. In step S170, the control device 10 extracts text information on the target. In step S180, it is determined whether text information on the target has been extracted. In step S190, the target information associated with the extracted text information on the target is output to server 200. Since there is a possibility that other vehicles existing in the vicinity may share a visible object, the other vehicles may be transmitted to the other vehicles using the inter-vehicle communication network.

FIG. 8 is a flowchart illustrating an operation procedure of the server 200 according to the present embodiment.
In step S210, the target information output in step S190 of FIG. 7 is obtained. The server 200 collects target information from an unspecified number of information providing apparatuses 100. In step S220, server 200 stores the collected information. In step S230, when the server 200 acquires the request information including the target identified on the information providing apparatus 100 side, the process proceeds to step S240. In step S240, server 200 extracts text information (utterance information) corresponding to the request information from the stored database. The extracted text information is an opinion or impression on the same object. In step S250, server 200 causes display 131 of information providing apparatus 100 to display the sent text information.

  Each user can acquire another person's message for the target that he or she recognizes.

  According to the information providing apparatus 100 and the information providing system 1 of the present embodiment, the following effects can be obtained.

  [1] The information providing apparatus 100 of the present embodiment identifies a target existing around the own vehicle, extracts text information on the target from the voice information, and associates the identified target with the text information on the target. Outputs the attached target information. As a result, information on a target that cannot be uniquely identified by position information or the like, such as a mobile object, can be shared with another unspecified user. The objects are automatically identified and textual information about the objects is automatically extracted, so that a driving user can simply speak (mutter) and share opinions and experiences with other users with common objects. Can be shared.

  [2] The information providing apparatus 100 of the present embodiment refers to the dictionary in which the target is associated with the text information, so that the text information on the target can be accurately extracted from the voice information.

  [3] The information providing apparatus 100 of the present embodiment outputs target information in which the position of the identified target and / or the time at which the target is detected and the text information are associated with each other. The subject can be accurately identified.

  [4] The information providing apparatus 100 of the present embodiment presents a plurality of identification results to the user and allows the user to select the result, so that the target can be accurately identified.

  [5] In the information providing system 1 of the present embodiment, the server 200 collects target information, and causes the display 131 of the information providing device 100 to present text information on the target identified in each information providing device 100. Thus, the user of each information providing apparatus 100 can share his or her opinion and experience on the target of interest with other users of the information providing apparatus 100.

  [6] The above-described operation and effect can be obtained also by the information providing method of the present embodiment.

  The embodiments described above are described for facilitating the understanding of the present invention, and are not described for limiting the present invention. Therefore, each element disclosed in the above embodiment is intended to include all design changes and equivalents belonging to the technical scope of the present invention.

  That is, in this specification, an information providing system 1 including an information providing apparatus 100 and a server 200 will be described as an example of an information providing system according to the present invention, but the present invention is not limited to this. is not.

  In the present specification, an information providing apparatus 100 including a control device 10, a camera 20, and a microphone 30 will be described as an example of an information providing apparatus according to the present invention, but the present invention is not limited thereto. .

  In the present specification, as an example of an information providing apparatus according to the present invention including an identification unit, an extraction unit, and an output unit, information including a control device 10 that executes an identification function, an extraction function, and an output function The providing device 100 will be described as an example, but the present invention is not limited to this.

DESCRIPTION OF SYMBOLS 1 ... Information provision system 100, 100N ... Information provision device 10 ... Control device 11 ... CPU
12 ... ROM
13 ... RAM
Reference Signs List 20 camera 30 microphone 110 navigation device 111 position detection device 112 map information 113 POI information 120 communication device 130 output device 130
131 ... display 132 ... speaker 200 ... server 210 ... information acquisition device 211 ... communication device 220 ... database 230 ... output device

Claims (5)

A camera for imaging the surroundings of the vehicle,
A microphone for acquiring voice information of a user boarding the vehicle,
Identification means for identifying an object present around the vehicle based on characteristics of the image captured by the camera;
An extraction unit that refers to a dictionary in which the target and text information related to the target are associated in advance, and extracts text information related to the identified target from the voice information,
Information providing device and an output means for outputting the object information associated with the text information on the target and the target that the identified. The identification means identifies a position and / or time at which the object exists,
And the output means, the identification is the subject was, the position and / or time the target is present, the information providing apparatus according to claim 1 for outputting the object information associated with the text information on the subject. The identification means, if the target identification result is obtained plurality presents a plurality of the identification results to the user, based on the selection information input by the user, according to claim identifies the object 1 Or the information providing device according to 2. An information providing device according to any one of claims 1 to 3 ,
A server that collects target information from a plurality of the information providing devices,
The server comprises:
Storing the collected target information for each of the targets,
The identified request information including the object identifier when acquired from the information providing device, the information providing system for presenting the gathered the text information relating to the target was in the information providing apparatus. A camera for imaging the surroundings of the vehicle,
Using a microphone that obtains voice information of a user boarding the vehicle, using an information providing device,
Based on the characteristics of the captured image of the camera, identify an object that exists around the vehicle,
Referring to a dictionary in which the target and text information related to the target are associated in advance , extracting text information related to the identified target from the audio information,
The identified the object and information providing method of correspondence outputting text information related to the subject.

Images