JP2009014518A - Device, method and program for generating road information - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To solve the problem that it is difficult to generate the information accurately showing connection of roads. <P>SOLUTION: The method comprises: acquiring the own vehicle position information showing the position of the vehicle; acquiring the image information showing the image around the vehicle; detecting a feature showing that the road on which the vehicle is traveling is connected with another road based on the image information; generating the road information showing the position of the road on which the vehicle is traveling and the connection of the road on which the vehicle is traveling with the other road based on the vehicle position information and the feature; and registering the road information in a memory medium. <P>COPYRIGHT: (C)2009,JPO&INPIT

Description

  The present invention relates to a road information generation apparatus, method, and program for generating information about roads.

Conventionally, a technique for generating new road information based on a travel history of a vehicle when updating map information used in a navigation device is known (for example, Patent Document 1).
JP 2004-251790 A

In the prior art, it has been difficult to accurately generate information indicating road connections.
That is, in the technique disclosed in Patent Document 1, based on the coordinate value indicating the current position of the vehicle acquired by the GPS, it is out of the range of the existing road, the coordinate value during traveling on the new road, Detects returning to the road. Then, node information and node connection information are generated based on the coordinate values during traveling on a new road. However, since roads such as elevated roads that intersect three-dimensionally exist, accurate road information cannot be generated even if road connections are determined based on two-dimensional coordinate values.
The present invention has been made in view of the above problems, and an object of the present invention is to accurately generate information indicating road connections.

  In order to achieve the above object, in the present invention, a connection between a road on which the host vehicle travels and another road is detected based on image information indicating an image around the host vehicle, and the connection and the host vehicle are traveling. Road information indicating the position of the road to be generated is generated and registered in the storage medium. That is, since a feature indicating that the road on which the host vehicle is traveling and another road is connected is detected based on the image information, the road on which the host vehicle is traveling and the other road are connected. The connection can be detected based on the feature that directly supports. Accordingly, it is possible to determine whether the roads are accurately connected or not connected as compared with the case where the road information indicating the connection of the roads is simply generated based on the coordinate values.

  Here, the own vehicle position information acquisition unit only needs to acquire the own vehicle position information indicating the position of the own vehicle, and various configurations for acquiring the information indicating the position of the own vehicle can be employed. For example, it is possible to adopt a configuration in which the position of the vehicle is specified by a sensor or camera, or a configuration in which the vehicle position information is acquired by a signal from GPS or a locus of the vehicle on a map, vehicle-to-vehicle communication, road-to-vehicle communication It is.

  The image information acquisition means obtains an image around the own vehicle, and is a feature that can exist around the own vehicle, and indicates that the road on which the own vehicle travels is connected to another road. What is necessary is just to be able to detect the feature to show. Accordingly, various configurations such as a configuration in which the surroundings of the host vehicle are photographed by a camera mounted on the host vehicle, a camera installed on the road surface, or the like can be employed.

  The feature detection means only needs to be able to detect a feature indicating that the road on which the vehicle travels is connected to another road based on the image information, and corresponds to various features in the image. It is possible to detect the feature based on the feature amount. That is, if road markings such as lines, arrows, letters, numbers, symbols, pedestrian crossings, road fences, stones, etc. on the surroundings of the vehicle indicate road connections, these roads By detecting the sign, it can be specified that the road is connected.

  In addition, when structures on the road such as expressway walls, shoulders, sidewalks, median strips, buildings, signs, signboards, traffic lights, etc., indicate road connections, these structures are detected as features. By doing so, it can be specified that the road is connected. Therefore, if feature quantities corresponding to these features are extracted based on the image information, it is possible to detect that the road on which the host vehicle is traveling is connected to another road. Of course, it may be specified that the road is connected by detecting both the road sign and the structure.

  The road information registration means only needs to be able to generate road information indicating the connection between the road on which the host vehicle travels and the other road and the position of the road on which the host vehicle travels, and register it in the storage medium. That is, since the position of the road on which the vehicle is traveling can be specified by the own vehicle position information and the connection of the other road to the road can be specified by the feature, road information indicating these can be generated. The road information is registered in a storage medium so that it can be used later. The position of the road may be a reference position determined in advance for the road. For example, a center point in the width direction of the road or an end point in the width direction can be defined as the position of the road. It should be noted that it is preferable to register a plurality of locations discretely in the direction in which the road extends rather than one location registered as road information.

  Furthermore, as a configuration example for specifying the connection of roads, a configuration in which the direction in which another road is connected to the road on which the host vehicle is traveling may be adopted. In other words, the above-described feature may have a characteristic that reflects a direction in which the other road is connected together with a characteristic that reflects the connection between the road on which the host vehicle is traveling and the other road. Therefore, if the direction in which the other road is connected is specified based on the image information, road information should be generated by determining whether there is an existing road connected in the direction based on the road information. It can be determined whether or not.

  Here, based on various characteristics, it is possible to specify the direction in which another road is connected to the road on which the host vehicle is traveling. For example, the direction in which other roads are connected by discontinuous or bent parts of the road, direction of arrows, text display contents, direction and shape of symbols, direction of pedestrian crossings, road fences and stones, etc. Can be specified. Also, other roads are connected by discontinuous parts of highway walls and road shoulders, the direction of sidewalks, placement of median strips, display content and placement of buildings, signs and signs, traffic light placement, etc. You may specify the direction.

  Furthermore, a configuration may be adopted in which road information relating to a road on which the vehicle travels in the storage medium is not registered and that road information is generated and registered. In such a configuration, the same information is not excessively registered, and the process for generating the same road information is not performed repeatedly, so that resources can be saved. In determining whether road information is unregistered, a configuration in which road information is determined to be unregistered when road information related to the road on which the host vehicle is not registered, road information related to the other roads Either a configuration in which road information is determined to be unregistered when no road information is registered, or a configuration in which road information is determined to be unregistered when road information regarding both is not registered may be employed.

  Further, the method of detecting the connection between the road on which the vehicle travels and the other road based on the image information as in the present invention and generating the road information indicating the position and the connection of the road can be a program or a method. Applicable. The road information generation device, program, and method as described above may be realized as a single road information generation device, or may be realized by using parts shared with each part provided in the vehicle. Various embodiments are included. For example, it is possible to provide a navigation device, a method, and a program that include the road information generation device as described above. Further, some changes may be made as appropriate, such as a part of software and a part of hardware. Furthermore, the invention is also established as a recording medium for a program for controlling the road information generating device. Of course, the software recording medium may be a magnetic recording medium, a magneto-optical recording medium, or any recording medium to be developed in the future.

Here, embodiments of the present invention will be described in the following order.
(1) Configuration of navigation device:
(2) Road information generation processing:
(3) Other embodiments:

(1) Configuration of navigation device:
FIG. 1 is a block diagram showing a configuration of a navigation device 10 including a road information generation device according to the present invention. The navigation device 10 includes a control unit 20 including a CPU, RAM, ROM, and the like and a storage medium 30, and the control unit 20 can execute a program stored in the storage medium 30 or the ROM. In the present embodiment, the navigation program 21 can be implemented as one of the programs. The navigation program 21 has a function of registering road information indicating the position and connection of the road as one of the functions, and the road. And a function of performing guidance based on information.

  The own vehicle (the vehicle on which the navigation device 10 is mounted) includes a GPS receiver 40, a vehicle speed sensor 41, a gyro sensor 42, a camera 43, a display unit 44, and a speaker 45 in order to realize the functions of the navigation program 21. The exchange of signals between these units and the control unit 20 is realized by an interface (not shown).

  The GPS receiver 40 receives radio waves from GPS satellites and outputs information for calculating the current position of the host vehicle via an interface (not shown). The control unit 20 acquires this signal and acquires the current position of the host vehicle. The vehicle speed sensor 41 outputs a signal corresponding to the rotational speed of the wheels provided in the host vehicle. The control unit 20 acquires this signal via an interface (not shown), and acquires the speed of the host vehicle. The gyro sensor 42 outputs a signal corresponding to the direction of the host vehicle. The control unit 20 acquires this signal via an interface (not shown) and acquires the traveling direction of the host vehicle. The vehicle speed sensor 41 and the gyro sensor 42 are used for correcting the current position of the host vehicle specified from the output signal of the GPS receiver 40. Further, the current position of the host vehicle is corrected as appropriate based on the travel locus of the host vehicle.

  The camera 43 captures an image around the host vehicle and outputs image information including a road on which the host vehicle travels. The control unit 20 acquires this signal via an interface (not shown), and acquires image information of an image including a road on which the host vehicle is traveling. The camera 43 in the present embodiment only needs to be able to acquire image information including the road on which the host vehicle travels, and is configured to be attached to the front, rear, etc. of the host vehicle and photograph the front or rear of the host vehicle. It can be adopted.

  In the present embodiment, the navigation program 21 performs a road information registration process, thereby causing the navigation device 10 to function as the road information generation device according to the present invention. For this reason, the navigation program 21 includes a host vehicle position information acquisition unit 21a, an image information acquisition unit 21b, a feature detection unit 21c, and a road information registration unit 21d. In addition, a guidance processing unit 21e is provided to execute guidance using road information.

  Further, the storage medium 30 stores map information 30a for performing guidance by the navigation program 21. The map information 30a includes node data indicating nodes set on a road, shape interpolation point data for specifying the shape of a road between nodes, link data indicating connection between nodes and shape interpolation points, and data indicating a target. Are used for specifying the current position of the own vehicle, guiding to the destination, correcting the vehicle position based on the travel locus of the own vehicle (map matching), and the like.

  In the present embodiment, the node data and the shape interpolation point data include data indicating the position on the road, and the node data, the shape interpolation point data, and the link data are registered in the storage medium 30 in advance, and It can be generated and registered by running. The node data, shape interpolation point data, and link data in this embodiment are included in the map information 30a. In the present embodiment, these data are also called road information 30b.

  The own vehicle position information acquisition unit 21a is a module that acquires own vehicle position information indicating the position of the own vehicle, acquires output signals of the GPS receiving unit 40, the vehicle speed sensor 41, and the gyro sensor 42, and obtains the current position of the own vehicle. The latitude and longitude of the vehicle is detected and used as vehicle position information. The image information acquisition unit 21b is a module that acquires image information output by the camera 43, and the acquired image information is transferred to the feature detection unit 21c.

  The feature detection unit 21c is a module that detects a feature indicating that a road on which the host vehicle is traveling and another road are connected based on the image information. In the present embodiment, the feature detection unit 21c is on a road surface. Extract the arrow paint image. In other words, the arrow paint may indicate that the vehicle can turn right or left or go straight on the road surface, and the host vehicle can be driven in the direction indicated by the arrow paint. Therefore, it can be said that other roads are connected in the direction indicated by the arrow paint on the road surface on the road on which the host vehicle travels.

  Therefore, the feature detection unit 21c detects the arrow paint based on the image information output from the camera 43, and detects the direction indicated by the arrow paint. For example, since the mounting position of the camera 43 in the host vehicle is a predetermined position, the relative relationship between the image at each position of the image captured by the camera 43 and the host vehicle is known in advance. Therefore, if the image of the arrow paint is extracted from the image information by pattern matching, edge extraction, etc., and the direction in which the tip is directed is specified, the road on which the vehicle travels is connected to the other road and The direction in which other roads are connected can be specified.

  The road information registration unit 21d generates road information indicating the position of the road on which the host vehicle is traveling and the connection of the other road to the road, and registers the road information in a storage medium. That is, the road information registration unit 21d specifies the position of the road on which the host vehicle is traveling based on the host vehicle position information, and generates node data or shape interpolation point data for the road on which the host vehicle is traveling. Furthermore, the road information registration unit 21d identifies the connection of another road to the road on which the host vehicle is traveling according to the feature, and generates link data indicating the connection of the other road. These data are registered in the storage medium 30 as road information 30b.

  The position of the road may be a reference position determined in advance for the road. For example, a center point in the width direction or an end point in the width direction can be defined as the position of the road. Moreover, it is preferable to register a plurality of locations discretely in the direction in which the road extends rather than one location registered as road information. In the above processing, since the arrow paint indicating that the road on which the host vehicle is traveling and another road is connected is detected based on the image information, the road on which the host vehicle is traveling and the other road are connected. The connection can be detected based on features that directly support the user. Therefore, it is possible to determine whether the road is accurately connected or not connected as compared with the case where the road information indicating the connection of the road is simply generated based on the coordinate value. Information 30b can be accumulated.

  The guidance processing unit 21e performs guidance processing with reference to the map information 30a and the road information 30b. That is, the map information 30a and the road information 30b are acquired, and a route search is performed based on the connection state of each road. Then, a control signal for performing guidance so as to travel along the searched route is output to the display unit 44 and the speaker 45, the guidance content is displayed on the display unit 44, and the guidance content is displayed from the speaker 45. Output. In this embodiment, since the link data of the road is generated when the host vehicle travels as described above, road information including the link data can be registered even if the road is newly opened. It is. Therefore, by performing the above guidance, it is possible to perform route guidance that appropriately considers a newly opened road.

(2) Road information generation processing:
Next, a road information generation process performed by the navigation device 10 in the above configuration will be described. When the navigation device 10 is being executed by the navigation device 10 while the host vehicle is traveling, the road information generation process shown in FIG. 2 is repeatedly performed at regular intervals (for example, 100 ms).

  In this process, first, the vehicle position information acquisition unit 21a acquires the output signals of the GPS reception unit 40, the vehicle speed sensor 41, and the gyro sensor 42, and acquires the vehicle position information (step S100). Next, the road information registration unit 21d determines whether road information of a road corresponding to the position of the host vehicle has been registered (step S105). In this embodiment, since the map matching process described above is performed in the navigation program 21, road information is not registered when the position of the host vehicle indicated by the host vehicle position information does not match in the matching process. .

  That is, map matching is a process that considers that the vehicle is traveling on the road indicated by the node or shape interpolation point when the traveling locus of the vehicle matches the sequence of nodes and shape interpolation points. To do so, nodes and shape interpolation points are required. Therefore, in the present embodiment, it is assumed that the node and the shape interpolation point are not registered when there is no matching. When it is determined in step S105 that the road information of the road corresponding to the position of the host vehicle has already been registered, it is not necessary to generate road information, and therefore step S110 and subsequent steps are skipped.

  On the other hand, if it is not determined in step S105 that the road information of the road corresponding to the position of the host vehicle has been registered, the road information is generated and registered in the storage medium 30 in step S110 and subsequent steps. In this process, first, the image information acquisition unit 21b acquires image information from the camera 43 (step S110), and the feature detection unit 21c performs image recognition (step S115). That is, the feature detection unit 21c performs processing for detecting an arrow paint image based on the image information. The detection result is delivered to the road information registration unit 21d.

  Next, the road information registration unit 21d performs processing for generating nodes and shape interpolation points (step S120). That is, the road information registration unit 21d generates a node or a shape interpolation point associated with the position indicated by the own vehicle position information. Then, the road information registration unit 21d determines whether or not arrow paint exists on the road on which the host vehicle is traveling based on the detection result delivered from the feature detection unit 21c (step S125).

  If it is determined in step S125 that arrow paint is present on the road on which the host vehicle is traveling, the surrounding road existing in the direction indicated by the arrow and the node or shape interpolation point generated in step S120 are displayed. Connect (step S130). That is, the road information registration unit 21d refers to the road information 30b and extracts a node or a shape interpolation point of another road existing in the direction indicated by the arrow. Further, link data indicating that the extracted node or shape interpolation point of the other road is connected to the node or shape interpolation point generated in step S120 is generated. Of course, at this time, the link data indicating that the node or the shape interpolation point existing behind the own vehicle on the road on which the own vehicle is traveling and the node or the shape interpolation point generated in step S120 are connected. Generate.

  The node data or shape interpolation point data indicating the position of the node or shape interpolation point generated in step S120 and the link data are registered in the storage medium 30 as road information 30b. It should be noted that whether the data generated here is a node or a shape interpolation point may be appropriately determined based on a predetermined rule. If it is not determined in step S125 that arrow paint is present on the road on which the host vehicle is traveling, step S130 is skipped because no other road is connected at the position of the host vehicle.

  In the present embodiment, the road information 30b is made more useful information by including information obtained from paints other than the arrow paint in the road information 30b. Therefore, in the present embodiment, in the image recognition in step S115 described above, the feature detection unit 21c also detects an image of paint other than arrow paint (for example, road signs such as characters and symbols), and the detection result Is transferred to the road information registration unit 21d.

  Accordingly, the road information registration unit 21d determines whether or not the other paint exists on the road on which the host vehicle is traveling based on the detection result delivered from the feature detection unit 21c (step S135). ). When it is determined in step S135 that the other paint is present on the road on which the host vehicle is traveling, information indicated by the other paint is added to the road information 30b (step S140), and the other paint is displayed. If it is not determined that it exists, step S140 is skipped. For example, the speed limit, the regulation information, the presence / absence of a signal, and the like are set as additional information on the road on which the vehicle is traveling. According to this configuration, it is possible to provide guidance corresponding to the speed limit, the restriction information, and the presence / absence of a signal when guiding in the guidance processing unit 21e.

FIG. 3 is an explanatory diagram of an example of the generation processing of the road information 30b based on the above-described arrow paint. In FIG. 3, nodes or shape interpolation points are indicated by white circles, and links are indicated by solid lines. Further, FIG. 3A, the vehicle C is a diagram schematically showing that the traveling on a new road in the direction of the arrow, the new road is a road crossing the link L _1. Figure 3B, 3C are views showing a state after crossing the link L ₁ traveling on the new road by the vehicle, Figure 3B there are arrows paint showing a left turn and straight ahead, Figure 3C is an arrow Paint An example of the case where it does not exist is shown.

When the host vehicle C is traveling on a new road, the road surface of the new road is analyzed in steps S110 and S115, and nodes or shape interpolation points are generated in step S120. In FIG. 3, the existing nodes N _{1 to} N ₃ and the newly established nodes are indicated as N ₄ and N ₅ . Figure 3B shows a case where the arrow paint showing a left turn and straight ahead exists, in this case, connecting the node N ₄ on the left side of the node N ₃ in step S130 after the determination at S125 in generating a node N ₄ . Since nodes N ₁ and N ₃ are connected by link L ₁ , node N ₄ is also connected to node N ₁ . Therefore, after the node N ₄ is generated, a new road can be the target of route guidance, and route guidance reflecting the connection of existing roads can be performed.

On the other hand, when the vehicle is no arrow painted on the road to travel, as shown in FIG. 3C, the node node N ₁ and the node N ₄ so skips step S125 in generating N _4, N ₃ Do not connect to For example, to produce a node N ₄ without new road connecting the nodes N ₄ to a node of another road when not linked to existing road a highway. Therefore, when performing route guidance after the node N ₄ is generated, it is determined that the road that is not actually connected is connected, and the route is determined and guidance is not performed, but accurate route guidance is performed. be able to.

(3) Other embodiments:
The above embodiment is an example for carrying out the present invention, and detects the connection between the road on which the vehicle travels and another road based on the image information, and generates road information indicating the position and connection of the road. As long as it can be done, various other embodiments can be adopted. For example, the vehicle position information may be a configuration using a part of the GPS receiving unit 40, the vehicle speed sensor 41, and the gyro sensor 42, or a part of the image information acquired by the camera. The vehicle position information may be acquired based on the information. Moreover, the structure etc. which acquire own vehicle position information by vehicle-to-vehicle communication, road-to-vehicle communication, etc. are employable. Furthermore, the acquisition mode of the image information is not limited to the mode of using the camera mounted on the host vehicle, and various configurations such as a configuration of photographing the surroundings of the host vehicle with a camera installed on the road surface can be adopted. is there.

  Furthermore, in order to determine the connection of roads based on image information, it is only necessary to detect a feature indicating that the road on which the vehicle travels is connected to another road based on the image information. The feature is not limited to the arrow paint described above. For example, when road markings such as lines, letters, numbers, symbols, pedestrian crossings, road fences, stones, etc. on roads indicate road connections, the roads are connected by detecting these road signs. Can be specified.

  In addition, when structures on the road such as expressway walls, shoulders, sidewalks, median strips, buildings, signs, signboards, traffic lights, etc., indicate road connections, these structures are detected as features. By doing so, it can be specified that the road is connected. Therefore, if feature quantities corresponding to these features are extracted based on the image information, it is possible to detect that the road on which the host vehicle is traveling is connected to another road. Of course, it may be specified that the road is connected by detecting both the road sign and the structure.

  Furthermore, the element for specifying the direction in which another road is connected to the road on which the host vehicle is traveling is not limited to the direction of the arrow paint, and various configurations can be adopted. For example, it is possible to specify the direction in which other roads are connected by discontinuous or bent parts of lines on the road, text display contents, direction and shape of symbols, direction of pedestrian crossings, road fences and stones, etc. is there. Also, other roads are connected by discontinuous parts of highway walls and road shoulders, the direction of sidewalks, placement of median strips, display content and placement of buildings, signs and signs, traffic light placement, etc. You may specify the direction.

  Furthermore, the configuration for determining whether or not the road information related to the road on which the host vehicle is traveling is not limited to the determination based on the success / failure of the matching process. That is, here, if road information is not registered in the storage medium, it is only necessary that road information can be generated and registered for the road, and it is determined whether road information in the vicinity of the vehicle position has been registered. It may be configured to. In such a configuration, the same information is not excessively registered, and the process for generating the same road information is not performed repeatedly, so that resources can be saved. In determining whether road information is unregistered, a configuration in which road information is determined to be unregistered when road information related to the road on which the host vehicle is not registered, road information related to the other roads Either a configuration in which road information is determined to be unregistered when no road information is registered, or a configuration in which road information is determined to be unregistered when road information regarding both is not registered may be employed.

  Furthermore, although useful information can be obtained by the processing after step S135 described above, additional information is added in the sense that the route information of the new road can be implemented by additionally registering the road information of the new road. Since it is a process, it can be omitted.

It is a block diagram of a navigation device including a road information generation device. It is a flowchart of a road information generation process. 3A to 3C are explanatory diagrams of a road information generation processing example.

Explanation of symbols

  DESCRIPTION OF SYMBOLS 10 ... Navigation apparatus, 20 ... Control part, 21 ... Navigation program, 21a ... Own vehicle position information acquisition part, 21b ... Image information acquisition part, 21c ... Feature detection part, 21d ... Road information registration part, 21e ... Guidance processing part 30 ... Storage medium, 30a ... Map information, 30b ... Road information, 40 ... Receiver, 41 ... Vehicle speed sensor, 42 ... Gyro sensor, 43 ... Camera, 44 ... Display, 45 ... Speaker

Claims (6)

Own vehicle position information acquisition means for acquiring own vehicle position information indicating the position of the own vehicle;
Image information acquisition means for acquiring image information indicating an image around the host vehicle;
A feature detection means for detecting a feature indicating that the road on which the host vehicle is traveling and another road are connected based on the image information;
Based on the own vehicle position information and the feature, road information indicating the connection between the road on which the host vehicle travels and the other road and the position of the road on which the host vehicle travels is generated and registered in a storage medium. Road information registration means,
A road information generation device comprising: The feature detection means specifies a direction in which the other road is connected to a road on which the host vehicle travels based on the feature,
The road information registration means refers to existing road information in the storage medium and generates road information indicating a connection between a road existing in a direction in which the other road is connected and a road on which the host vehicle is traveling. To
The road information generation device according to claim 1. The feature is one or both of a road marking and a structure on the road.
The road information generation device according to claim 1 or 2. The road information registration means determines whether or not the road information of one or both of the road on which the host vehicle is traveling and the other road has been registered in the storage medium, and the host vehicle is traveling The road information is generated and registered in the storage medium when the road information of either or both of the road and the other road is not registered in the storage medium,
The road information generation device according to any one of claims 1 to 3. Own vehicle position information acquisition step for acquiring own vehicle position information indicating the position of the own vehicle;
An image information acquisition step of acquiring image information indicating an image around the host vehicle;
A feature detection step of detecting a feature indicating that a road on which the vehicle travels and another road are connected based on the image information;
Based on the own vehicle position information and the feature, road information indicating the connection between the road on which the host vehicle travels and the other road and the position of the road on which the host vehicle travels is generated and registered in a storage medium. Road information registration process,
Road information generation method including Own vehicle position information acquisition function for acquiring own vehicle position information indicating the position of the own vehicle;
An image information acquisition function for acquiring image information indicating an image around the host vehicle;
A feature detection function for detecting a feature indicating that the road on which the host vehicle is traveling and another road are connected based on the image information;
Based on the own vehicle position information and the feature, road information indicating the connection between the road on which the host vehicle travels and the other road and the position of the road on which the host vehicle travels is generated and registered in a storage medium. Road information registration function,
Road information generation program that makes a computer realize.

Images