JP5971619B2 - Route guidance device and route guidance program - Google Patents

Description

  The present invention relates to a route guidance device and a route guidance program, and relates to travel route guidance performed using a mark present on the travel route.

2. Description of the Related Art Navigation devices that guide the current position of a vehicle or a terminal device or a route to a destination are widely used. In this navigation apparatus, a travel route to a destination searched using map data is acquired, and guidance of the travel route is performed by voice output or image display.
When voice guidance is used for driving routes, for example, it is common to guide the distance and the direction of travel, for example, “It is approximately XXm ahead”, but it is difficult to accurately grasp the distance. Also, when there are a plurality of intersections ahead, there is a problem that it is difficult to recognize either one.

Therefore, in order to guide the intersection to be changed more easily, Patent Document 1 proposes a technique for guiding using a mark present at the intersection.
FIG. 9 is an explanatory diagram for explaining guidance using a mark present at an intersection.
As illustrated in FIG. 9, guidance is performed in the following order (1) to (4).
(1) When reaching a predetermined distance from the guidance intersection, the mark information (for example, shell oil) linked to the guidance intersection is read out.
(2) Image recognition of a mark (signboard or the like) corresponding to the mark information is performed from a captured image in front of the vehicle imaged by the image pickup device, and it is confirmed whether the mark can be recognized.
(3) Voice guidance of the guidance intersection according to the recognition result of the mark is performed.
(A) If the landmark can be recognized, utter an intersection guide using the landmark.
Example: “Soon to the right. Seashell oil is a landmark.” “Shell oil will soon be to the right.”
(B) When the landmark cannot be recognized (unrecognized), utter distance guidance.
Example: “Soon right.” “Soon 300m ahead, right.”
(4) If the mark can be recognized, the fact that the mark exists at the corresponding intersection is saved, and if the mark is not recognized, the data relating to the mark is deleted.

As a general characteristic when performing image recognition, it is necessary to minimize misrecognition (recognizing a mark other than the mark to be recognized as a mark) as much as possible. ing. This makes it possible to suppress misrecognition, but on the other hand, there is a demerit that the success rate of correct recognition (when recognizing a mark that is a recognition target) is reduced. This is conspicuous in in-vehicle devices that have resource (CPU, memory, etc.) restrictions.
For this reason, in the case of recognizing the mark at the guidance intersection, since the rate of correct recognition is low, unrecognition that cannot be recognized despite the presence of the mark at the guidance intersection occurs.
In such an unrecognized case, it is (a) “unrecognized because the landmark has been removed” or (b) “unrecognized from the performance of the recognition process despite the presence of the landmark. Cannot be correctly determined.

  However, conventionally, when the mark is not recognized, the data of the mark is deleted uniformly, and thus the mark may be deleted even though the mark exists.

Japanese Patent No. 3399506

  It is an object of the present invention to delete the information of the landmark after more accurately determining that the landmark corresponding to the guidance intersection does not exist.

(1) In the first aspect of the present invention, the route learned from the landmark learning data storage means for storing the landmark learning data relating to the landmark of the facility existing at the intersection and the captured image in front of the vehicle captured by the imaging device. An image recognition result acquisition means for acquiring an image recognition result of an image recognition process of a landmark for recognizing a landmark existing at a guidance intersection on the route, and a facility corresponding to the landmark are set as an initial destination of the route search, In the vicinity of the destination, when another destination of the same genre as the initial destination is newly set, an estimation result of the landmark disappearance estimation process that estimates that the landmark corresponding to the initial destination has disappeared is acquired. and mark erasure estimation result acquisition unit, the image recognition result of the image recognition processing of the mark is unrecognized landmark, and when the estimated result of the mark disappeared estimation process is landmark loss estimate Providing route guidance device characterized by comprising an erasing means for erasing the mark learning data corresponding to the mark, the.
( 2 ) In the invention according to claim 2 , in the mark disappearance estimation process, the current position of the vehicle is in a position where it is difficult to enter the initial destination, or the parking lot at the initial destination is full. If there or other vehicle is parked, is not determined that a mark corresponding to the initial destination is lost, it provides a route guidance device according to claim 1, characterized in that.
(3) In the invention described in claim 3, the image recognition process and the mark disappearance estimation process are performed in the other process in the travel before the travel in which one of the processes is performed. A route guidance device according to claim 1 or claim 2 is provided.
( 4 ) In the invention according to claim 4 , the image recognition means for performing the image recognition processing of the mark, and the mark disappearance estimation means for performing the mark disappearance estimation processing, the image recognition result acquisition means, obtain the result of the image recognition processing of the mark by the image recognition unit, the mark disappeared estimation result acquisition unit acquires the result of the mark disappeared estimation processing by the mark disappeared estimating means, according to claim 1, characterized in that, according A route guidance device according to item 2 or claim 3 is provided.
( 5 ) In the invention according to claim 5 , the image recognition process of the mark and the mark disappearance estimation process are performed by a navigation device mounted on a vehicle, and the image recognition result acquisition unit and the mark disappearance estimation result are performed. The route guidance device according to claim 1 , wherein the acquisition unit acquires a result of the landmark image recognition process and a result of the landmark disappearance estimation process from the navigation device. I will provide a.
( 6 ) In the invention described in claim 6 , there is provided a route guidance program for a route guidance device provided with landmark learning data storage means for storing landmark learning data relating to landmarks of facilities existing at intersections. An image recognition result acquisition function for acquiring an image recognition result of an image recognition process of a mark for recognizing a mark existing at a guidance intersection on a travel route searched for a route from a captured image in front of the vehicle, and a facility corresponding to the mark Is set as the initial destination of the route search, and when another destination of the same genre as the initial destination is newly set around the initial destination, the landmark corresponding to the initial destination disappears and estimating the mark disappeared estimation result acquisition function of acquiring the result of estimation of mark erasure estimation process, the image recognition result of the image recognition processing of the mark is unrecognized landmarks, and the eye If loss estimation process estimation result is landmark loss estimation, it provides a route guidance program for realizing the erase function of erasing the mark learning data corresponding to the mark, to the computer.

  According to the present invention, when the image recognition result of the mark image recognition process is the unrecognized mark, and the estimation result of the mark disappearance estimation process is the mark disappearance estimation, the landmark learning data corresponding to the mark Since it is erased, it is possible to delete the information of the mark after more accurately determining that the mark corresponding to the guidance intersection does not exist.

It is explanatory drawing showing the matrix which determines continuation and deletion of the mark learning data of a mark. 1 is a system configuration diagram of a navigation device to which the present embodiment is applied. It is explanatory drawing showing the content of landmark learning DB. This shows a functional configuration when performing guidance processing and data management by the information processing device in the navigation device. It is explanatory drawing which represented the operation | movement at the time of passing along the guidance intersection which exists in the middle of a driving | running route and where landmark learning data exist with time passage. It is explanatory drawing which represented operation | movement when the facility of the landmark learning data which exists corresponding to a difference point is set as a destination with progress of time. It is a flowchart showing the content of the image recognition process of the mark in this embodiment. It is a flowchart showing the content of the mark disappearance estimation process from a vehicle behavior in this embodiment. It is explanatory drawing for demonstrating the guidance using the mark which exists in the intersection in the past.

DESCRIPTION OF EXEMPLARY EMBODIMENTS Hereinafter, preferred embodiments of a route guidance device and a route guidance program according to the present invention will be described in detail with reference to FIGS. 1 to 8, taking a navigation device as an example.
(1) Outline of Embodiments Mark data that exists corresponding to an intersection may be used for guidance of a guidance intersection existing in the middle of a travel route, or may be used as a destination of a travel route.
When used for guidance of a guidance intersection, the landmark image is recognized from the captured image of the guidance intersection captured by the imaging device. If the landmark is recognized, voice guidance using the landmark is performed and the landmark is recognized. Turn on the recognition flag indicating that it has been completed. On the other hand, when the mark is not recognized, the unrecognized flag is turned ON.

In addition, when the landmark is used as the destination of the travel route, a mechanism is provided for estimating that there is no facility corresponding to the landmark from the traveling state (behavior) of the vehicle in the vicinity of the landmark.
That is, when the facility corresponding to the guide intersection mark is set as the destination, the flag with the mark is set to ON if the facility is stopped. On the other hand, if there is an act such as setting another store as a new destination without stopping at the destination despite traveling to the vicinity of the destination, the landmark (and its facilities) will be removed, etc. The mark disappearance estimation flag is set to ON by estimating that the mark has disappeared, that is, the mark has disappeared.

FIG. 1 shows a matrix for determining the continuation and erasure of landmark learning data for landmarks.
As shown in FIG. 1, when both the unrecognized flag and the mark disappearance estimation flag are ON, that is, the result of the image recognition of the mark is unrecognized, and the mark is lost from the vehicle behavior. If estimated, the mark data (marking learning data) is deleted.
On the other hand, when at least one of the recognition flag and the flag with mark is ON, the mark learning data is continued.

As described above, it is possible to more accurately determine the disappearance of the mark by determining not only the image recognition result of the mark but also the behavior of the vehicle with respect to the set destination.
That is, even if the mark is not recognized as a result of the image recognition, the mark learning data is not immediately deleted by itself. Thereby, based on the performance of the image recognition processing, even when the mark actually exists, it is possible to cope with the case where the mark is erroneously unrecognized.
Further, even if the store disappearance is estimated from the vehicle behavior at the set destination, the landmark learning data is not immediately deleted. Thereby, for example, it is possible to cope with the case where the facility and the mark are present but are not visited because they are not on business days or business hours, and as a result, the disappearance of the mark is estimated.

(2) Details of Embodiment FIG. 2 is a system configuration diagram of a navigation apparatus to which this embodiment is applied.
The navigation device is mounted on a vehicle and includes a current position detection device 10, an information processing device 20, an input / output device 40, an information storage device 50, and a communication control unit 60, as shown in FIG.

The current position detection device 10 is configured as follows.
The azimuth sensor 12 is a means for detecting an angle that has changed relative to a reference angle (absolute azimuth). In this embodiment, a gyro sensor that detects a change in angle using an angular velocity is used. Yes. Note that an optical rotation sensor attached to the rotating part of the handle, a rotary resistance volume, or an angle sensor attached to the wheel part may be used. Further, the direction sensor 12 may be, for example, a geomagnetic sensor that detects in which direction the vehicle is located from detection in the N direction based on a magnet, and may be a means for detecting an absolute direction.

The distance sensor 13 is a means that can measure the moving distance of the vehicle, and for example, a sensor that detects and counts the rotation of a wheel or a sensor that detects acceleration and integrates it twice.
The GPS (Global Positioning System) receiver 14 is a device that receives a signal from an artificial satellite, and includes various signals such as signal transmission time, position information of the receiver, moving speed of the receiver, and traveling direction of the receiver. Information can be obtained.

  The information processing device 20 performs calculation and control based on information input from the current position detection device 10 and the input / output device 40 and information stored in the information storage device 50, and displays the calculation result on the display 42, the speaker 44, and the like. It is a means to control to output to the output means.

The information processing apparatus 20 is configured as follows.
The central processing unit (CPU) 21 performs overall calculation and control of the entire navigation device.
The ROM 22 searches for a travel route to the destination, intersection (branch point) guidance processing using the landmark according to the present embodiment, image recognition processing of the landmark, and landmark disappearance estimation processing set at the destination from the vehicle behavior. , Etc., various navigation-related programs and other various programs are stored. The ROM 22 may be divided into a first ROM and a second ROM, and a navigation program related to voice guidance may be stored in the second ROM, and other programs may be stored in the first ROM. These programs may be stored in the information storage device 50 instead of the ROM 22.
The sensor input interface 23 is a means for receiving information from the current position detection device 10.

  The RAM 24 stores information input by the user such as destination information and passage point information input by the input device 41, and results calculated by the CPU 21 based on the user input information and route search It is a storage means for storing the map result read or the map information read from the information storage device 50. The RAM 24 stores a landmark template image and a captured image as a work area in the landmark image recognition process.

The communication interface 25 is means for inputting / outputting various information via the transmission path 45. Specifically, the GPS receiver 14, the input device 41, the imaging device 43, and the information storage device 50 are connected via the transmission path 45.
The timepiece 28 is configured by using, for example, a crystal resonator, and clocks time or provides operation timing of each part of the navigation device by oscillation.
In addition, an image processor dedicated to image processing for processing vector information processed by the CPU 21 into image information, an image memory for storing image information processed by the image processor, and audio information read from the information storage device 50 are processed. However, a voice processor dedicated to voice processing to be output to the speaker 44 may be provided.

The input / output device 40 includes an input device 41 for inputting data such as a destination, a passage point, and a search condition by a user, a display 42 for displaying an image, an imaging device 43, and a speaker 44 for outputting sound.
The input device 41 includes, for example, a touch panel, a touch switch, a joystick, a key switch, and the like.
The display 42 displays a map around the current location and a travel route to the destination.

The imaging device 43 is a device that captures an image in front of the vehicle. The imaging device 43 starts imaging in front of the vehicle from a predetermined distance (for example, 300 m) from the guidance intersection existing on the travel route, and is sequentially captured until the mark can be recognized. The
The captured image in front of the vehicle imaged by the imaging device 43 is a target image for recognizing the mark.
The speaker 44 outputs driving route guidance by voice and outputs voices of various operation explanations.

The information storage device 50 is connected to the information processing device 20 via the transmission path 45.
The information storage device 50 stores map data 51, a landmark standard template 52, a landmark learning DB 53, audio data 54, and other data 55.
The information storage device 50 is generally composed of an optical storage medium such as a DVD-ROM, a CD-ROM, or a magnetic storage medium such as a hard disk, but various types such as a magneto-optical disk and various semiconductor memories. You may comprise with an information storage medium.
Information that needs to be rewritten may be constituted by a rewritable hard disk or flash memory, and other fixed information may be a ROM such as a CD-ROM or DVD-ROM.

The map data 51 stores map data, road data, intersection data, destination data, guidance point data, detailed destination data, and other data as various data necessary for map display, route search, and route guidance in navigation. Has been.
As map data, a national road map, a road map of each region, a house map, or the like is stored. The road map is composed of roads such as main arterial roads, expressways, narrow streets, and ground targets (facility etc.). A house map is a city map in which a figure representing an outer shape of a ground building, a road name, and the like are displayed. The narrow street is, for example, a relatively narrow road having a road width equal to or less than a predetermined value below a national road or prefectural road.
As for the map data, a map of a predetermined range including a current vehicle position and a point designated by the user is displayed on the display 42 at a predetermined scale. On this map, the current position of the vehicle and the designated point are displayed.

The road data is data regarding roads such as the position and type of each road, the number of lanes, and the connection relationship between the roads, and is composed of node data and link data. The road data is used for route search and map matching, and is also used when the searched travel route is displayed over the map data.
The node data is data representing geographic coordinate data of each node used for route search on a map.
For example, a road connection point such as an intersection is represented by a node, and a road between the connection points (that is, an unbranched region of the road) is represented by a link. In this way, it functions as route data representing the connection relation of the node data route.
In addition, for those where travel is restricted due to traffic restrictions, such as entry prohibition and one-way traffic, attributes indicating this are given to each link, but these attributes should be given to intersection nodes. Also good.
Node data is supplementary to characteristic points between intersections (for example, points at the start, middle and end of a curve, and points where the altitude changes), along with intersection nodes that are always set for each intersection. There is an auxiliary node that may be set to The intersection node includes information related to the intersection such as the geographical position coordinates and name of the intersection.

The intersection data stores intersection-related data such as intersection numbers, intersection geographical location coordinates and names, and link data connected to each intersection.
The destination data is data such as the locations and names of places and facilities that are likely to be destinations such as major tourist spots, buildings, and companies / businesses described in the telephone directory. The destination data is classified into various genres such as family restaurants, udon / soba, convenience stores, department stores, gas stations, stations, libraries, ski resorts, golf courses, shrines, and the like. Further, the specific destination data is associated with landmark learning data to be described later. When the facility of the associated destination data is set as the destination, the destination from the vehicle behavior in this embodiment is The set mark disappearance estimation process is executed.

Guidance point data is guidance data of a point where guidance is required, such as the content of a guidance display board installed on a road and guidance of a branch point.
Detailed destination data is detailed data related to each facility, etc. stored in the destination data, for example, each tenant's data in a general building, facility parking lots, entrance / exit information, etc. are associated with each destination data. Stored separately. Note that the detailed destination data may be stored together in the destination data.

The mark standard template 52 is a reference image used when recognizing a mark, and is stored together with a mark type (identification number) for each mark.
This mark standard template 52 is used when image recognition is performed with a predetermined matching rate P (for example, 80%).

The landmark learning DB 53 stores information on whether or not there is a landmark at each intersection, and landmark learning data regarding the landmark when the landmark is present.
FIG. 3 shows the contents of the landmark learning DB 53.
As shown in FIG. 3, the landmark learning DB 53 includes, for each landmark learning data, the intersection number of the intersection where the landmark exists, the landmark type, the recognition flag indicating the image recognition result, the unrecognized flag, and the vehicle behavior. A mark presence flag and a mark disappearance estimation flag indicating the mark disappearance estimation result are stored.
As the intersection number, the same number as the intersection data of the map data 51 (intersection numbers K001, K002,... In the example of FIG. 3) is stored. Since the travel route data searched for the route includes an intersection number, landmark learning data for the intersection to be guided is specified from the intersection number.

As the mark type, an identification number (M001, M002,... In the example of FIG. 3) of the mark standard template 52 corresponding to the mark existing at each intersection is stored. A mark standard template 52 for recognizing the mark image is specified from the identification number of the mark learning data specified from the intersection number on the travel route.
In FIG. 3, it is indicated that there is no mark at the intersection of the intersection number K003 for which the mark type is not stored. If the landmark type is not saved, the landmark learning data (other than the intersection number) will be deleted because the facility corresponding to the landmark that has existed has been removed due to the removal of the landmark. There is a case.
When a new mark is set at an intersection where no mark exists, the mark type is stored as the mark learning data at the corresponding intersection number. The new landmark learning data (marker type) is stored by accessing the information center server (hereinafter simply referred to as the information center) via the communication control unit 60 at a predetermined timing to obtain update information of the landmark learning DB. by. Note that each recognition flag at this time is in an OFF state.

One of the recognition flag indicating the image recognition result and the unrecognized flag is turned ON depending on the result of the image recognition of the mark. Therefore, for example, when the mark cannot be recognized by image recognition of the mark when it passes through the guidance intersection with the recognition flag turned on again, the unrecognized flag is turned on and the recognition flag is turned off. In FIG. 3, the flag ON is indicated by 1, and the flag OFF is indicated by no mark.
On the other hand, either the flag with a mark indicating the estimated mark disappearance result from the vehicle behavior or the mark disappearance estimated flag is turned ON depending on the result of the estimated mark disappearance estimation. Similarly, in this case, when one of the flags is changed from the OFF state to the ON state, the flag is changed to the OFF state if the other flag is ON.

Returning to FIG. 2, the case where the mark standard template 52 and the mark learning DB 53 are stored in the information storage device 50 has been described. However, when acquiring these data from the information processing center, either one or both are stored in the RAM 24. You may make it save to.
In this embodiment, as shown in FIG. 2, the case where both the mark standard template 52 and the mark learning DB 53 are stored in the information storage device 50 will be described. However, the mark standard template 52 and the mark learning DB 53 are all received from the information processing center. In order to acquire or update, it may be stored in the RAM 24 every time a travel route to the destination is acquired.
The travel route may be acquired either by route search by the own device or by acquiring the travel route searched at the information center by transmitting the destination to the information center.

The voice data 54 stores various voice data such as voice data for operation assistance, as well as voice data for voice guidance (including intersection guidance using distance and landmarks) based on the navigation function.
The other data 55 includes, for example, image data of photographs showing places where visual indications such as various facilities and sightseeing spots or major intersections are required, and voice when guiding a set travel route by voice. Data etc. are stored.

The communication control unit 60 transmits / receives data to / from an external device.
For example, in this embodiment, update information of the landmark learning DB 53 is acquired from the information processing center. Further, the full vehicle information of the facility set as the destination, the parking information of other vehicles, and the like are acquired via the communication control unit 60. The full vehicle information and the like are used in the mark disappearance determination from the vehicle behavior in the present embodiment.

FIG. 4 shows a functional configuration when performing guidance processing and data management by the information processing device 20 in the navigation device.
The CPU 21 of the information processing apparatus 20 executes a program for navigation stored in the ROM 22 (intersection guidance using the landmark, image recognition of the landmark, estimation of the disappearance of the landmark set at the destination from the vehicle behavior, etc.) By doing so, it functions as the travel route acquisition unit 210, the vehicle position specifying unit 211, the image recognition unit 212, the mark disappearance estimation unit 213, the guide unit 214, and the mark learning DB update unit 215.

The travel route acquisition unit 210 acquires a travel route to the destination. The travel route is acquired by searching for the travel route to the destination set using the map data 51 in the navigation device by providing the route search function (program) in the navigation device. It is also possible to transmit the set destination from the communication control unit 60 to the information center and acquire the travel route to the destination searched for by the information center.
The own vehicle position specifying unit 211 is based on the travel route to the destination acquired by the travel route acquisition unit 210, various data detected by the current position detection device 10, and the map data 51 of the information storage device 50. The vehicle position of the vehicle and the vehicle position on the map data are specified. In addition, the own vehicle position specifying unit 211 specifies the vehicle behavior near the destination from the change in the specified own vehicle position.

Based on the recognition request from the guide unit 214, the image recognition unit 212 recognizes the guide intersection mark using the captured image captured by the imaging device 43 as a target image.
The image recognizing unit 212 recognizes the mark if the matching rate between the target image (captured image) and the mark standard template 52 is P (for example, 80%) or more, and unmarks the mark if it is less.

The mark disappearance estimation unit 213 performs mark disappearance estimation processing based on vehicle behavior.
In this estimation process, the mark disappearance estimation unit 213 acquires full vehicle information of the store (facility of the destination), parking information of other vehicles at the store, and the like via the communication control unit 60 when the vehicle reaches the vicinity of the destination. At the same time, the behavior of the vehicle or the like in the vicinity of the destination is acquired from the own vehicle position specifying unit 211, and the estimation result (marked flag, mark disappearance estimation flag) is supplied to the mark learning DB update unit 215.
For example, if there is a behavior such as setting another destination of the same genre without stopping at the set destination as the behavior of the vehicle or the like, it is estimated that the mark has disappeared.

The guide unit 214 outputs a guidance voice of the travel route from the speaker 44 based on the travel route acquired by the travel route acquisition unit 210 and the own vehicle position specified by the own vehicle position specifying unit 211, and from the information storage device 50. The travel route guidance is performed by displaying on the display 42 the map, travel route, and vehicle current location corresponding to the current vehicle position to be acquired.
When the guide unit 214 approaches a guidance intersection on the travel route (for example, 300 m before the guidance intersection), the guidance unit 214 requests the image recognition unit 212 to recognize an image of a mark present at the guidance intersection.
Then, the guide unit 214 performs voice guidance for the guidance intersection using the voice data 54 of the information storage device 50. That is, if a landmark present at a guidance intersection can be recognized based on a request for image recognition, voice guidance using the landmark for the guidance intersection, for example, “Soon, shell oil is in the right direction.” As described above, voice guidance based on the landmark and the direction of travel is performed. On the other hand, when the recognition result is unrecognized, voice guidance using the distance, for example, voice guidance such as “Soon, right direction” is performed.

The landmark learning DB update unit 215 performs the guidance based on the image recognition result (recognized or unrecognized) of the landmark in the image recognition unit 212 and the estimation result (estimated or missing landmark) of the landmark disappearance estimation unit 213. The landmark learning data in the landmark learning DB 53 corresponding to the intersection is updated.
That is, the landmark learning DB update unit 215 turns on the recognition flag and turns off the unrecognized flag according to the image recognition result, or turns on the unrecognized flag and turns off the recognition flag.
Also, the landmark learning DB update unit 215 turns on the marker presence flag and turns off the marker disappearance estimation flag, or turns on the marker disappearance estimation flag and sets the marker presence flag according to the result of the marker disappearance estimation. Turn off.
Furthermore, if the unrecognized flag is already turned on when the unrecognized flag is turned on based on the image recognition result, the landmark learning DB update unit 215 erases the landmark learned data for the guidance intersection. . In addition, when the landmark learning DB update unit 215 turns on the landmark disappearance estimation flag based on the result of the landmark disappearance estimation, even if the unrecognized flag is already on, the landmark learning DB update unit 215 obtains the landmark learning data for the guidance intersection. to erase. The deletion of the landmark learning data is performed by deleting the marker type DB3 53 corresponding to the intersection number of the guidance intersection and deleting the flag indicating the landmark disappearance estimation result from the vehicle behavior.

In the navigation device configured as described above, route guidance is performed as follows.
The navigation device detects the current position with the current position detection device 10, reads the map information around the current position from the map data 51 of the information storage device 50, and displays it on the display 42.
When the destination is input from the input device 41, the information processing device 20 searches for (calculates) a plurality of travel route candidates from the current position to the destination, and displays them on the map displayed on the display 42. When the driver selects any travel route, the travel route is acquired by storing the selected travel route in the RAM 24 (travel route acquisition means).

The information processing apparatus 20 transmits the current vehicle position (or input departure point) and destination to the information processing center (server), and receives a travel route to the destination searched for in the information processing center. You may make it acquire a travel route by. In this case, communication of the destination and the travel route is performed by wireless communication via the communication interface 25.
Further, a travel route from the departure place to the destination is searched using an information processing device such as a personal computer at home, etc., stored in a storage medium such as a USB memory, and acquired through the storage medium reader. You may do it. In this case, the storage medium reading device is connected to the information processing device 20 via the transmission path 45.

When the vehicle travels, route guidance is performed by tracking the current position detected by the current position detection device 10.
In the route guidance, the vehicle position on the map is specified by map matching between the road data corresponding to the acquired travel route and the current position detected by the current position detection device 10, and a map around the vehicle current position is displayed on the display 42. Then, the searched travel route is displayed on the map, and a current position mark indicating the current position of the vehicle is displayed on the map.
Also, based on the relationship between the searched travel route and the current position, the necessity of guidance is determined, that is, whether or not guidance for a travel route such as a predetermined route change point or intersection guidance is necessary when straight traveling continues for a predetermined distance or more. If necessary, display on the display 42 and voice guidance are executed.

Next, guidance using the landmark and processing of the landmark learning DB 53 in this embodiment will be described along the moving state of the vehicle.
FIG. 5 shows the operation of the navigation apparatus over time when passing through a guidance intersection that exists in the middle of the travel route and has landmark learning data.
As shown in FIG. 5, while traveling on the travel route searched to the destination, the navigation device performs the following processing around the guidance intersection.

As shown in (1) of FIG. 5, first, a mark (shell oil) linked to the guidance intersection is read out. Here, the landmark learning data in the landmark learning DB is read out.
Then, as shown in (2), from the captured image in front of the vehicle, the mark standard template of the corresponding mark is used from the mark type of the mark learning data, and the mark is image-recognized.
Next, as shown in (3), the guidance intersection is guided by voice according to the recognition result of the mark.
That is, when the landmark can be recognized, for example, the direction of travel at the guidance intersection is voice-guided using the landmark such as “Soon to the right. Seashell oil is the landmark”. This is an example of conventional voice guidance using both distance (soon) and landmarks and directions.
On the other hand, if the recognition result is an unrecognized mark, for example, voice guidance is performed using a distance and a direction such as “coming to the right soon”.

Next, as shown in (4), the landmark recognition result is stored in the landmark learning DB 53. That is, when the mark can be recognized, the recognition flag is turned ON. At this time, if the unrecognized flag is ON, it is changed to OFF.
On the other hand, if the mark is unrecognized, the unrecognized flag is turned ON. At this time, if the recognition flag is ON, it is changed to OFF.

And as shown in (5), when the image recognition result of the current mark is unrecognized, if the mark disappearance estimation flag corresponding to the mark is set to ON, the mark learning corresponding to the mark is learned. Erase the data.
In this way, if the result of the image recognition of the landmark is simply unrecognized, it may be unrecognized due to the recognition accuracy, and it is unclear whether the landmark (and its facility) really disappeared. The landmark learning data is not deleted immediately. Then, in the state where the disappearance of the mark is estimated from the behavior of the vehicle or the like in the previous driving (the mark erasure estimation flag is ON), the mark learning is performed when the mark image recognition is unrecognized by the current driving. By erasing the data, it can be determined more accurately that there is no mark corresponding to the guidance intersection.

FIG. 6 shows the operation when the facility of the landmark learning data existing corresponding to the difference point is set as the destination with the passage of time.
As shown in FIG. 6, when the route corresponding to the landmark learning data is searched for as a destination, the navigation apparatus performs the following processing around the destination.
As shown in (1) of FIG. 6, it is assumed that the vehicle travels around the destination by using the shell oil present at the guidance intersection as the destination.

Next, as shown in (2), the disappearance of the mark is estimated from the behavior of the vehicle.
In other words, whether or not an action that is presumed to have disappeared, such as whether or not a new petrol station of the same genre was set around the destination without stopping at the set destination, was taken If this is the case, the mark disappearance estimation flag of the mark learning DB 53 is turned ON. At this time, if the flag with mark is ON, it is changed to OFF.
When the vehicle stops at a set destination, the flag with a mark is turned ON. At this time, if the mark disappearance estimation flag is ON, it is changed to OFF.

Then, as shown in (3), when the disappearance of the mark is estimated as a result of the mark disappearance estimation due to the behavior of the vehicle or the like, the unrecognized flag is set to ON as a result of the image recognition corresponding to the mark. For example, the landmark learning data corresponding to the destination is deleted.
Thus, even if it is estimated that the landmark has disappeared, the landmark learning data is not immediately deleted because the facility set as the destination may not have stopped by for a holiday and set another destination. If the landmark recognition is unrecognized in the previous travel (when the unrecognized flag is ON) and the disappearance of the landmark is estimated by the current travel, the landmark learning data is deleted. , It can be determined more accurately that there is no mark corresponding to the guidance intersection.

FIG. 7 is a flowchart showing the contents of the mark image recognition process in this embodiment.
The information processing apparatus 20 acquires the current position on the travel route by map matching, and monitors whether the distance from the current vehicle position to the guidance intersection is within a predetermined distance (for example, 300 m) (step 701).
If it is within the predetermined distance (step; 701Y), the information processing apparatus 20 reads the corresponding landmark learning data from the landmark learning DB 53 using the intersection number of the guidance intersection as a search key (step 702).
Then, the information processing apparatus 20 determines whether or not there is landmark learning data at the guidance intersection according to whether or not there is a landmark type at the corresponding intersection number in the landmark learning DB 53 (step 703).

When the landmark type does not exist, that is, when the landmark learning data does not exist at the guidance intersection (Step 703; N), the information processing apparatus 20 utters the normal guidance for the intersection (Step 704), and processes the guidance intersection. If there is a next guidance intersection, the next guidance intersection is monitored.
In the normal guidance utterance, the information processing apparatus 20 performs voice guidance based on the distance and the direction of the route, for example, “300m ahead, right direction” or “shortly right direction”.

On the other hand, when the mark type exists, that is, when the mark learning data exists at the guidance intersection (step 703; Y), the information processing apparatus 20 performs captured image recognition (step 705).
In this captured image recognition, the information processing apparatus 20 reads a mark standard template for recognizing a mark existing at the intersection from the mark standard template 52 using the mark type corresponding to the guidance intersection as a search key.
Then, the information processing device 20 compares each captured image in front of the vehicle sequentially captured by the image capturing device 43 with the mark standard template, and determines whether or not the mark is higher than a predetermined matching rate (for example, 80%). It is determined whether or not it has been recognized (step 706).

When the mark present at the guidance intersection can be recognized (step 706; Y), the information processing apparatus 20 utters the mark guide (step 707).
In the utterance of the guide, the information processing apparatus 20 provides the name of the facility corresponding to the landmark in addition to the above-described normal guidance as the voice guidance using the landmark, or instead of the distance portion of the normal guidance (or In some cases, a facility name corresponding to a landmark is inserted for guidance.
An example of the former is “300m ahead, right direction. Shell oil is a landmark”, and the latter is “soon, shell oil is right”.

Next, the information processing apparatus 20 turns on the recognition flag of the landmark learning data corresponding to the intersection number of the guidance intersection in the landmark learning DB 53 (step 708). At this time, the information processing apparatus 20 changes it to OFF if the unrecognized flag is ON. And the process with respect to the said intersection is complete | finished, and if the next guidance intersection exists, the next guidance intersection will be monitored.
The process for turning on the recognition flag (step 708) may be performed before the utterance of the landmark guidance (707) or may be performed in parallel. This relationship is the same in step 709 and step 710 described later.

When the mark present at the guidance intersection cannot be recognized, that is, when the matching rate between the captured image and the mark standard template is less than the predetermined matching rate (step 706; N), the information processing apparatus 20 The normal guidance is uttered in the same manner as described in step 704 (step 709).
Then, the information processing apparatus 20 sets the unrecognized flag in the landmark learning DB 53 to ON (step 710). That is, the information processing apparatus 20 turns on the unrecognized flag of the landmark learning data corresponding to the intersection number of the guidance intersection in the landmark learning DB 53. At this time, the information processing apparatus 20 changes it to OFF if the recognition flag is ON.

Next, the information processing apparatus 20 searches past data in the landmark learning DB 53 (step 711).
Then, the information processing device 20 sets the facility corresponding to the landmark as the destination for the landmark learning data of the guidance intersection, performs the landmark disappearance estimation process from the vehicle behavior, and sets the landmark disappearance estimation flag of the landmark learning data. It is determined whether or not it is ON (step 712).
If the landmark disappearance estimation flag of the landmark learning data is not ON (step 712; N), that is, if the landmark presence flag is ON and the landmark disappearance estimation flag is OFF, or the destination has been set as a destination in the past If neither flag exists, the information processing apparatus 20 ends the process for the intersection and monitors the next guidance intersection if there is a next guidance intersection.

On the other hand, when the landmark disappearance estimation flag of the landmark learning data is ON (step 712; Y), the information processing apparatus 20 uses the unrecognized flag by the landmark image recognition process and the landmark by the landmark disappearance estimation process from the vehicle behavior. Since both the disappearance estimation flags are ON, the landmark learning data corresponding to the guidance intersection is deleted (step 713).
That is, the information processing apparatus 20 deletes the landmark type and each flag corresponding to the intersection number of the guidance intersection, erases the landmark learning data, ends the process for the intersection, and finds the next guidance intersection. For example, the next guidance intersection is monitored.

FIG. 8 is a flowchart showing the contents of the mark disappearance estimation process from the vehicle behavior in the present embodiment.
This flowchart is executed when a route search is performed with an intersection where a mark exists as a destination, and the vehicle travels on the searched travel route.
The information processing apparatus 20 acquires the current position on the travel route by map matching, and determines whether or not it is within a predetermined distance to the destination (step 801). As the predetermined distance, an arbitrary distance Xm before the destination, for example, 300 m before, 500 m before, or the like is adopted.

When the current position of the vehicle is within a predetermined distance to the destination (step 801; Y), the information processing apparatus 20 determines whether the destination is at the own vehicle position where it is difficult to enter (step 802), and the destination It is determined whether there is full vehicle information or parking information for other vehicles (step 803). Examples of the vehicle position where the destination is difficult to enter include a vehicle position where a U-turn is required for the destination, a vehicle position on the opposite lane side of the median strip with respect to the destination. The order of determination in steps 801 and 802 is not particularly limited.
The information processing apparatus 20 is configured to prevent both determinations in steps 801 and 802 from erroneously determining that a landmark facility (for example, a store in business) has disappeared (store loss). It is processing.

When the destination is the own vehicle position where it is difficult to enter (step 802; Y), or when there is full information on the destination or parking information of another vehicle (step 803; Y), the information processing device 20 This process ends.
On the other hand, when the destination is not the vehicle position where the destination is difficult to enter (step 802; N), and the full vehicle information of the destination also has no parking information of other vehicles (step 803; N), the information processing device 20 It is determined whether or not the user has entered the site (step 804).
In determining whether to enter the destination site, the information processing apparatus 20 performs an off-road determination, and determines that the current position of the vehicle is away from the link of the map data 51 and determines that the vehicle has entered a dedicated link for the facility. In this case, it is determined that the vehicle has entered the destination site.

Next, the information processing apparatus 20 determines whether or not the vehicle has entered the destination site as a result of the entry determination to the destination site (step 805).
If it is determined that the vehicle has entered the destination site (step 805; Y), the information processing apparatus 20 turns on the marker presence flag of the landmark learning data corresponding to the destination in the landmark learning DB 53 (step 806). At this time, if the mark disappearance estimation flag is ON, the information processing apparatus 20 changes it to OFF, and ends the process for the intersection.

On the other hand, when it is not determined that the vehicle has entered the destination site (step 805; N), the information processing device 20 monitors the operation state of the navigation device (step 807).
Then, it is determined whether or not a new destination of the same genre as the set destination is newly set by operating the input device 41 or by voice input (step 808). If there is no destination setting (step 808; N), the information processing apparatus 20 ends this processing.
When a new destination of the same genre is set (step 808; Y), the information processing apparatus 20 turns on the landmark disappearance estimation flag in the landmark learning DB 53 (step 809).

Next, the information processing apparatus 20 searches past data in the landmark learning DB 53 (step 810).
Then, the information processing apparatus 20 determines whether or not the landmark learning data corresponding to the destination is subjected to the image recognition processing of the landmark for the facility at the destination and the unrecognized flag is ON (step 811). ).
When the unrecognized flag of the mark learning data is not ON (step 811; N), that is, when the recognition flag is ON and the unrecognized flag is OFF, or the image recognition process of the mark has not been performed in the past. In this case, the information processing apparatus 20 ends this process.

On the other hand, when the unrecognized flag of the landmark learning data is ON (step 811; Y), the information processing apparatus 20 does not recognize the landmark disappearance estimation flag based on the landmark disappearance estimation processing based on the vehicle behavior and the landmark image recognition processing. Since the recognition flags are both ON, the landmark learning data corresponding to the guidance intersection is deleted (step 812).
That is, the information processing apparatus 20 erases the landmark learning data by erasing the landmark type and each flag corresponding to the intersection number of the guidance intersection, and this process, that is, the disappearance estimation process of the landmark for the destination Exit.

Although one embodiment of the navigation device of the present invention has been described above, the present invention is not limited to the described embodiment, and various modifications can be made within the scope described in each claim.
For example, in the embodiment described above, in the landmark disappearance estimation process from the vehicle behavior described in FIG. 8, the destination is determined based on the relationship between the destination in Step 802 and the vehicle position and the destination parking lot in Step 803. Although the case where the mark disappears is not subject to determination (the mark is not determined to have disappeared) has been described even if it does not enter, the other situation may be excluded from the landmark disappearance determination.
For example, it is determined whether or not you have visited another facility of the same genre that is within a predetermined distance from the destination that did not enter the site, and even if you enter the site of the other facility, it is excluded from the determination of the disappearance of the landmark, , Do not estimate that the landmark has disappeared.
This is because the willingness to use other facilities (same genre) existing in the vicinity of the set destination facility may have changed.
Therefore, the predetermined distance needs to be within a range that can be visually recognized by the vehicle occupant, and is set to 500 m, for example.

  In addition, when the current position of the vehicle is in the vicinity of the destination, if the vehicle enters another facility of the same genre displayed on the display 42, it is not determined that the landmark has been lost for the same reason, that is, the landmark has disappeared. It may not be estimated.

In the embodiment and the modification described above, the navigation device mounted on the vehicle has been described as an example. However, a mobile phone equipped with the navigation program (function) described above or a personal digital assistant (PDA: Personal Digital Assistant, PND: Personal Navigation Device, etc.), personal computers may be used as navigation devices in vehicles.
In addition, when a user carries and uses each device such as a mobile phone, a moving body that changes to a vehicle may be applied as the user.

  Further, in the present embodiment and the modification, the description has been made on the guide intersection on the travel route. However, the present invention is not limited to the intersection, and guides a specific branch point existing on the travel route or guides straight ahead. It is also possible to apply to this.

In the embodiment and the modification described above, the case has been described in which the landmark learning data corresponding to the guide intersection mark and the landmark learning data corresponding to the facility set as the destination are deleted from the navigation device. The mark learning data may be erased at the information center.
The information center (server) in this case is realized by a computer system, a cloud system, or the like having a communication function with the navigation device.

When the information center erases the landmark learning data, the navigation apparatus transmits a recognition flag or an unrecognized flag indicating the recognition result to the information center in the image recognition processing of the landmark at the guidance intersection. Further, in the mark disappearance estimation process from the vehicle behavior, a mark presence flag or a mark disappearance estimation flag indicating the estimation result is transmitted to the information center.
In the navigation device, flag information indicating both the result of the mark image recognition process and the mark disappearance estimation process based on the vehicle behavior is transmitted to the information center. The learning data is not deleted. However, the flag may be changed and the landmark learning data may be deleted as in the embodiment described above.

  The information center includes a landmark learning DB similar to that described with reference to FIG. 3, and is based on a flag indicating both the results of the landmark image recognition process and the landmark disappearance estimation process from the vehicle behavior transmitted from each vehicle. In the same manner as described in the embodiment, when the unrecognized flag is ON and the flag information of the unmarked flag estimation flag ON is received, and the unrecognized flag ON flag information of the unmarked mark estimation flag is ON. When the mark is received, the mark learning data corresponding to the mark to be processed is deleted.

Each time the information center receives flag information from the navigation device, it determines whether or not to delete the corresponding landmark learning data. However, both results of the landmark image recognition process and the landmark disappearance estimation process from the vehicle behavior are obtained. Is transmitted from a plurality of navigation devices, it is sequentially stored in time series, and it is determined whether to delete it at a predetermined timing (for example, once a day, once a week). You may do it.
In this case, the information center determines whether or not both the unrecognized flag and the mark disappearance estimation flag are turned on for each mark learning data from the accumulated flag information history. Erase the landmark learning data.

  In the information center, when the flag information received from each navigation device is accumulated, it is determined as unrecognized when the unrecognized flag ON is continuously received a predetermined number of times (n times), and similarly the predetermined number of times ( It is determined that the disappearance of the mark has been estimated when the mark disappearance estimation flag ON is received (m times). In the information center, when both unrecognized and estimated disappearance of the landmark are determined, the landmark learning data may be deleted.

When the landmark learning data is erased at the information center described above, the result of the marker disappearance estimation (because of the marker presence flag or the marker disappearance estimation flag) due to the behavior is the navigation device that does not include the imaging device 43, that is, You may make it receive also from the navigation apparatus which does not perform an image recognition process but performs only the mark disappearance estimation by a behavior.
Since the number of times a landmark corresponding facility at the intersection is set as the destination is smaller than the number of times that the intersection with the landmark becomes a guidance intersection, the landmark is targeted by a navigation device that performs only the landmark disappearance estimation process. The number of receptions of the erasure estimation process result can be increased.

Further, in the embodiment described above, a case has been described in which it is determined that the landmark has disappeared when there is a setting of a new destination whose destination is another facility of the same genre.
On the other hand, when erasing the landmark learning data at the information center, each navigation device is said to have lost its destination (marker) when it has not entered the destination around the set destination. The flag information of the mark disappearance estimation flag ON may be estimated and transmitted to the information center.
In this case, the information center finalizes the marker disappearance estimation when the flag information of the marker disappearance estimation flag ON is continuously received from a plurality of navigation devices a predetermined number of times (P times).
Then, the information center erases the mark learning data corresponding to the mark on condition that the mark disappearance estimation is confirmed and the flag information of the unrecognized flag ON of the mark is received.

Further, in the embodiment and the modification described above, a case where two types of flags are stored and updated as flags indicating both the results of the mark image recognition process of the mark learning data and the mark disappearance estimation process from the vehicle behavior will be described. However, each of the unimage recognition flag and the marker disappearance estimation flag may be set as one flag.
In this case, the unrecognized flag is turned on when the mark image cannot be recognized, and the unrecognized flag is turned off when the mark is recognized. Further, when it is estimated that the mark has disappeared, the mark disappearance estimation flag is turned ON, and when it is not estimated, the mark disappearance estimation flag is turned OFF.

DESCRIPTION OF SYMBOLS 10 Current position detection apparatus 20 Information processing apparatus 40 Input / output apparatus 43 Imaging apparatus 44 Speaker 50 Information storage apparatus 51 Map data 52 Mark standard template 53 Mark learning database 54 Voice data 60 Communication control section 211 Location section 212 Image recognition section 213 Guide section

Claims (6)

Landmark learning data storage means for storing landmark learning data relating to landmarks of facilities existing at intersections;
Image recognition result acquisition means for acquiring an image recognition result of an image recognition process of a mark for recognizing a mark existing at a guidance intersection on a travel route searched for a route from a captured image captured in front of the vehicle imaged by the imaging device;
When a facility corresponding to a landmark is set as an initial destination for route search, and another destination of the same genre as the initial destination is newly set around the initial destination, it corresponds to the initial destination. A landmark disappearance estimation result acquisition means for acquiring an estimation result of a landmark disappearance estimation process for estimating that a landmark to be disappeared;
Erase to erase the landmark learning data corresponding to the landmark when the image recognition result of the landmark image recognition process is unrecognized landmark and the estimation result of the landmark disappearance estimation process is landmark disappearance estimation Means,
A route guidance device comprising: When the current position of the vehicle is in a position where it is difficult to enter the initial destination, or when the parking lot at the initial destination is full or other vehicles are parked, Do not determine that the landmark corresponding to the original destination has disappeared,
The route guidance apparatus according to claim 1 .   In the image recognition process and the landmark disappearance estimation process, the other process is performed in the travel before the travel in which one of the processes is performed.
The route guidance device according to claim 1 or 2, characterized by the above. Image recognition means for performing image recognition processing of the mark;
A landmark disappearance estimation means for performing the landmark disappearance estimation process,
The image recognition result acquisition means acquires a result of the mark image recognition processing by the image recognition means,
The landmark disappearance estimation result acquisition means obtains the result of the landmark disappearance estimation processing by the landmark disappearance estimation means,
The route guidance device according to claim 1 , claim 2, or claim 3 . The image recognition process of the mark and the mark disappearance estimation process are performed by a navigation device mounted on the vehicle,
The image recognition result acquisition means and the landmark disappearance estimation result acquisition means obtain a result of the landmark image recognition process and a result of the landmark disappearance estimation process from the navigation device.
The route guidance device according to claim 1 , claim 2, or claim 3 . A route guidance program for a route guidance device comprising landmark learning data storage means for storing landmark learning data relating to landmarks of facilities present at intersections,
An image recognition result acquisition function for acquiring an image recognition result of an image recognition process of a mark for recognizing a mark existing at a guidance intersection on a travel route searched for a route from a captured image captured in front of the vehicle imaged by the imaging device;
When a facility corresponding to a landmark is set as an initial destination for route search, and another destination of the same genre as the initial destination is newly set around the initial destination, it corresponds to the initial destination. A landmark disappearance estimation result acquisition function for obtaining an estimation result of a landmark disappearance estimation process for estimating that a landmark to be disappeared;
Erase to erase the landmark learning data corresponding to the landmark when the image recognition result of the landmark image recognition process is unrecognized landmark and the estimation result of the landmark disappearance estimation process is landmark disappearance estimation Function and
A route guidance program that makes a computer realize.

Images