JP7085506B2 - Information processing equipment, information processing methods and programs - Google Patents

Description

The present invention relates to an information processing apparatus, an information processing method and a program.

Techniques for searching a route from a starting point to a destination for the purpose of navigation to the destination have been conventionally known. In such a technique, a route considering cost (for example, time, cost, distance, etc.) is searched by using road network information. In addition, for cost reduction and safety, for example, it is possible to search for a route that avoids turning right as much as possible.

As a technique related to a route search in consideration of safety, a technique for searching a route in which a traffic accident with a large damage is unlikely to occur is known (see, for example, Patent Document 1).

Japanese Unexamined Patent Publication No. 2008-12153

However, since some traffic accidents do not cause damage to pedestrians, the magnitude of damage caused by traffic accidents does not necessarily match the magnitude of damage to pedestrians when a traffic accident occurs. Therefore, for example, in the technique described in Patent Document 1, it is not possible to appropriately search for a route in consideration of damage to pedestrians when a traffic accident occurs.

Further, for example, with the technique described in Patent Document 1, the magnitude of damage to a road on which a traffic accident has not occurred in the past cannot be calculated. For this reason, on roads where no traffic accidents have occurred in the past, the magnitude of damage when a traffic accident occurred was unknown, and the magnitude of damage to pedestrians was also unknown.

The present invention has been made in view of the above points, and an object of the present invention is to search for a route in consideration of damage to pedestrians when a traffic accident occurs.

In order to achieve the above object, an embodiment of the present invention comprises an image captured by imaging a road on which a predetermined feature is installed, and map information including feature information related to the feature. Based on the input means for inputting either and the input image or map information, the land related to the feature installed on the road represented by the link information with respect to the link information included in the road network information. It has a registration means for associating object information and registering it in a storage unit.

It is possible to search for a route in consideration of damage to pedestrians when a traffic accident occurs.

It is a figure which shows an example of the whole structure of the path search system which concerns on this embodiment. It is a figure which shows an example of the functional structure of the path search system which concerns on this embodiment. It is a figure which shows an example of the human damage evaluation table. It is a flowchart which shows an example of the feature registration process using the captured image. It is a flowchart which shows an example of the feature registration process using the map information. It is a flowchart which shows an example of the route search process in the case of searching a route with less human damage. It is a flowchart which shows an example of the route search process in the case of calculating the human damage value of a search route. It is a flowchart which shows an example of the route search processing at the time of determining whether the search route can be automatically operated. It is a figure which shows an example of the hardware configuration of a computer.

Hereinafter, embodiments of the present invention (hereinafter, also referred to as “the present embodiments”) will be described. In the present embodiment, a route search system 1 capable of searching for a route in consideration of damage to pedestrians (hereinafter, also referred to as “human damage”) when a traffic accident caused by a vehicle occurs will be described. The route may be referred to as a "route".

Here, on roads that can be passed by pedestrians, it is generally considered that roads with sidewalks are less likely to cause human damage to pedestrians in the event of a traffic accident than roads without sidewalks. .. In addition, on a road with a sidewalk, the sidewalk and the roadway are separated by predetermined features (for example, curbs, guard rails, tree planting zones, etc.), but when a traffic accident occurs depending on the type of feature or its combination. It is considered that the risk of human damage to pedestrians is different. The feature may be referred to as, for example, a "workpiece" or the like.

Therefore, in the present embodiment, the link information included in the road network information is registered in association with the information of the features existing on or around the road represented by this link information, and then the road represented by each link information. Search for routes that take into account the types of roads and information on features. As a result, in the present embodiment, it is possible to search for a route in consideration of human damage to pedestrians when a traffic accident occurs.

In addition, in this embodiment, the sidewalk means a part of a road sectioned with a roadway by a predetermined feature in order to be used exclusively for the passage of pedestrians. Therefore, a road with a sidewalk is a road having such a part. On the other hand, a road that is pedestrian-accessible and has no sidewalk is, for example, a road in which a part of the road used for pedestrian passage is visually divided by a roadside band or the like. It shall be said.

In the present embodiment, a road having a sidewalk is also referred to as a "pedestrian separation road", and a road that is accessible to pedestrians and has no sidewalk is also referred to as a "pedestrian coexistence road". In addition, a road on which pedestrians do not walk exclusively on the road and its surroundings and only vehicles pass through is also referred to as a "vehicle-only road". Examples of vehicle-only roads include highways and the like. In addition, since pedestrians generally do not pass on vehicle-only roads, it is considered that there is no risk of human damage to pedestrians in the event of a traffic accident (or the risk is extremely low). ..

<Overall configuration of pathfinding system 1>
First, the overall configuration of the route search system 1 according to the present embodiment will be described with reference to FIG. FIG. 1 is a diagram showing an example of the overall configuration of the route search system 1 according to the present embodiment.

As shown in FIG. 1, the route search system 1 according to the present embodiment includes a server device 10 and one or more terminal devices 20. Further, the server device 10 and each terminal device 20 are connected via, for example, a communication network N such as the Internet.

The server device 10 is, for example, a computer or a computer system that manages road network information and searches for a route from a departure point to a destination designated by the terminal device 20.

The terminal device 20 is, for example, a computer or a computer system that specifies route search conditions such as a departure point and a destination, displays a route search result on a map, and performs navigation to the destination. Examples of the terminal device 20 include a smartphone, a tablet terminal, a car navigation device mounted on a vehicle, a notebook PC (personal computer), a portable game device, a wearable terminal, and the like.

The configuration of the path search system 1 shown in FIG. 1 is an example, and may be another configuration. For example, when the terminal device 20 also has the functions realized by the server device 10 and the information (data) managed by the server device 10, the route search system 1 may not include the server device 10. ..

<Functional configuration of path search system 1>
Next, the functional configuration of the route search system 1 according to the present embodiment will be described with reference to FIG. FIG. 2 is a diagram showing an example of the functional configuration of the route search system 1 according to the present embodiment.

As shown in FIG. 2, the route search system 1 according to the present embodiment has a feature registration processing unit 101, an input unit 102, a route search processing unit 103, and an output unit 104 as functional units. Further, the route search system 1 according to the present embodiment has a road network information storage unit 110, a captured image storage unit 120, a map information storage unit 130, and a human damage evaluation table storage unit 140 as storage units. ..

The feature registration processing unit 101 uses the captured image stored in the captured image storage unit 120 or the map information stored in the map information storage unit 130 with respect to the link information included in the road network information. Information on features existing on or around the road represented by link information (hereinafter, also referred to as "feature information") is registered in association with each other.

The road network information is data for performing a route search, and is composed of, for example, node information and link information. The node information is information about a node indicating various points such as an intersection, a branch point, a place where a road attribute changes, and a place where a road width changes. The node information includes, for example, information such as a node number, latitude and longitude, an intersection name (Kanji and reading), and the presence or absence of a traffic light. On the other hand, the link information is information about a link connecting nodes. Link information includes, for example, link length and coordinate point sequence, link cost, node numbers of nodes at both ends of the link, number of lanes, width, road shoulder width, slope, direction of travel, altitude (elevation) of the road indicated by the link. Etc. are included.

The input unit 102 inputs a route search condition including a departure place, a destination, and the like. The route search conditions may include various conditions such as, for example, whether or not a waypoint or a toll road is used.

The route search processing unit 103 searches for a route from the departure point to the destination by using the route search condition input by the input unit 102 and the road network information stored in the road network information storage unit 110. At this time, the route search processing unit 103 converts the human damage evaluation table 1000 stored in the human damage evaluation table storage unit 140 and the feature information associated with the link information included in the road network information. It is used, for example, to search for a route considering human damage to pedestrians when a traffic accident occurs. The route search processing unit 103 uses a known algorithm such as the Dijkstra method, and the cost of the link from the departure point to the destination is the lowest (or the cost of the link from the departure point to the destination is small). Search for multiple routes in order).

The output unit 104 outputs the route search result (or information based on the route search result) by the route search processing unit 103. For example, the output unit 104 may display a map including the route obtained as a route search result on the display, or may output a voice related to the route guidance together with this display. Alternatively, for example, the output unit 104 may output a route search result or the like to a program or device for automatically driving the vehicle.

The road network information storage unit 110 stores road network information. The captured image storage unit 120 stores captured images of roads. As such an image, any image can be used as long as the image is an image of a road. For example, the captured image may be an image captured and created by an in-vehicle imaging device (for example, a drive recorder or the like), or may be captured and created by another method or purpose.

The map information storage unit 130 stores map information for each predetermined range (for example, a range partitioned in a mesh shape). The map information is, for example, information for displaying various buildings, roads, road signs, and the like. Here, in the present embodiment, the map information is associated with the link information of the road included in the map represented by this map information, and at least a part of the map information includes the feature information (that is, this map information). It is assumed that the feature information of the road included in the map to be represented) is included.

The human damage evaluation table storage unit 140 stores the human damage evaluation table 1000. The human damage evaluation table 1000 is a table in which evaluation values regarding human damage to pedestrians in the event of a traffic accident are stored according to the type of road, the type of feature, the combination of features, and the like. be. An example of the human damage evaluation table 1000 will be described later.

It should be noted that various configurations can be considered as to which functional unit and storage unit each of the server device 10 and the terminal device 20 has. For example, a feature registration processing unit 101, a route search processing unit 103, a road network information storage unit 110, a captured image storage unit 120, a map information storage unit 130, and a human damage evaluation table storage unit 140 are used as servers. The device 10 may have an input unit 102 and an output unit 104 in the terminal device 20. Alternatively, for example, the server device 10 has a feature registration processing unit 101, a road network information storage unit 110, a captured image storage unit 120, and a map information storage unit 130, an input unit 102, and a route search processing unit. The terminal device 20 may have a configuration in which the terminal device 20 includes the 103, the output unit 104, and the human damage evaluation table storage unit 140. Alternatively, for example, the terminal device 20 may have all the functional units and all the storage units shown in FIG. 2 (in this case, the route search system 1 may not include the server device 10). .).

<Human damage evaluation table 1000>
Here, an example of the human damage evaluation table 1000 stored in the human damage evaluation table storage unit 140 will be described with reference to FIG. FIG. 3 is a diagram showing an example of the human damage evaluation table 1000.

In the human damage evaluation table 1000 shown in FIG. 3, the “link road type”, the “feature type”, the “human damage value”, and the “weighting coefficient (cost adjustment value)” are associated with each other. There is. The human damage value and the weighting coefficient correspond to the evaluation value regarding human damage.

The type of road represented by the link is set in "Road type of link". For example, a "pedestrian-vehicle coexistence road", a "pedestrian-vehicle separation road", or a "vehicle-only road" is set as the "link road type".

In the "feature type", when the "pedestrian-vehicle separation road" is set in the "road type of the link", the type or combination of the feature information associated with the link is set. For example, "curb only", "guard fence only", "curb + tree planting zone", "curb + guard fence", "curb + guard fence + tree planting zone" and the like are set as the "feature type". In addition, for example, "curb only" means that only curb exists as a feature that separates the sidewalk and the roadway on the road represented by the link. Similarly, for example, "curb + tree-planting zone" means that a curb and a tree-planting zone exist as a feature that separates a sidewalk and a roadway on a road represented by a link (that is, a curb and a tree-planting zone). In combination with the belt, it indicates that the sidewalk and the roadway are separated.)

In the "human damage value", a predetermined human damage value is set as one of the evaluation values according to the "link road type" and the "feature type". The human damage value is used, for example, for the evaluation of the route searched by the route search (evaluation of the safety of the route, etc.).

In the example shown in FIG. 3, when the "road type of link" is "pedestrian-vehicle coexisting road", "+100" is set as the human damage value. Similarly, for example, when the "link road type" is "pedestrian-vehicle separation road" and the "feature type" is "curb only", "+70" is set as the human damage value. .. In this embodiment, the higher the human damage value, the higher the risk of human damage to pedestrians when a traffic accident occurs.

A predetermined weighting coefficient is set in the "weighting coefficient" as one of the evaluation values according to the "link road type" and the "feature type". The weighting coefficient is used, for example, for weighting the cost included in the link information when performing a route search. Since the weighting coefficient is a value for adjusting the cost included in the link information, it may be referred to as a “cost adjustment value”.

In the example shown in FIG. 3, when the "link road type" is "pedestrian-vehicle coexisting road", "+2.0" is set as the weighting coefficient. Similarly, for example, when the "link road type" is "pedestrian-vehicle separation road" and the "feature type" is "curb only", "+ 1.7" is set as the weighting coefficient. .. In this embodiment, the higher the weighting coefficient, the higher the risk of human damage to pedestrians when a traffic accident occurs.

As described above, in the human damage evaluation table 1000, a traffic accident occurred at this link for the road type of the link and the type or combination of features installed on the road represented by this link. The evaluation value regarding the human damage to the pedestrian at the time is associated. In the example shown in FIG. 3, the human damage value and the weighting coefficient are associated with each other as the evaluation value regarding the human damage, but for example, only one of the human damage value and the weighting coefficient corresponds. It may be attached.

Further, in the example shown in FIG. 3, curbs, guard rails, and tree planting zones are mentioned as the types of features, but the features are not limited to these. The feature may include, for example, utility poles, bollards, lamps, switchboards, and the like. That is, any work that is installed on or around the road and has the potential to reduce the risk of human injury to pedestrians in the event of a traffic accident caused by a vehicle. It can be a feature.

In addition, the types of features may be subdivided into more detailed types. For example, the type of feature may be subdivided into "distribution board (large)" and "distribution board (small)" according to the size of the distribution board. In this case, the evaluation value regarding human damage may be lower in the "distribution board (large)" than in the "distribution board (small)". Similarly, for example, the type of feature may be subdivided into "curb (high)", "curb (medium)", "curb (low)", etc. according to the height of the curb, and the guard rail may be subdivided according to the strength. It may be subdivided into "guard fence (strong)", "guard fence (medium)", "guard fence (low)", etc., and the tree-planting zone may be "tree-planting zone (wide)" or "tree-planting zone (wide)" depending on the width. It may be subdivided into "narrow)" and the like. In these cases as well, the higher the height of the curb, the stronger the guard fence, and the wider the width of the tree planting zone, the lower the evaluation value regarding human damage should be.

Further, on the pedestrian-vehicle separation road, the evaluation value regarding human damage may be different depending on the type of sidewalk. For example, if there are "flat type", "semi-flat type", and "mount-up type" as sidewalk types, the evaluation value for human damage should be reduced in the order of flat type, semi-flat type, and mount-up type. You may.

Further, the evaluation value regarding human damage may be different depending on at least one such as the number of lanes and width of the road represented by the link, the slope, the curve (curvature), the presence / absence of a signal, the width of the shoulder, and the like. For example, the larger the number of lanes, the smaller the evaluation value for human damage, and the smaller the number of lanes, the larger the evaluation value for human damage. Similarly, the wider the width, the lower the road slope, the gentler the curve (curvature), the wider the shoulder, the smaller the evaluation value for human damage, and the narrower the width, the higher the road slope. The steeper the curve (curvature) and the narrower the width of the shoulder, the larger the evaluation value for human damage. Similarly, if there is a signal on the pedestrian crossing on the road, the evaluation value for human damage is reduced, and if there is no signal, the evaluation value for human damage is increased.

In addition, the evaluation value regarding human damage may be different depending on the presence or absence of ruts on the road. Since ruts on the road often hinder the driving of vehicles (including automatic driving), if there are ruts, the evaluation value for human damage should be higher than if there are no ruts.

Furthermore, the evaluation value regarding human damage may be different depending on the time zone and the number of pedestrians. For example, in the case of a road where the number of pedestrians differs depending on the time zone, the evaluation value for human damage in the time zone with a large number of pedestrians is made larger than the evaluation value for human damage in the time zone with a small number of pedestrians. be. Further, for example, on a road designated as a school route, the evaluation value regarding human damage during the time of going to and from school may be larger than that of other time zones. At this time, for example, the evaluation value regarding human damage is set higher for the school route of the elementary school than for the school route of the junior high school or high school. You may make it different. Information representing the number of pedestrians existing on each road (link) for each time zone may be calculated in advance by statistical analysis, or real-time information (that is, the number of pedestrians on each road in real time). If there is a server or the like that can obtain the information), it may be acquired from the server or the like.

<Feature registration process>
Hereinafter, the process of registering the feature information in association with the link information (feature registration process) will be described. The feature registration process includes, for example, a feature registration process using a captured image of a road and a feature registration process using map information including at least a part of the road feature information. These may execute only one of the feature registration processes, or may execute both feature registration processes independently or complementarily.

<< Feature registration process using captured images >>
First, the feature registration process using the captured image will be described with reference to FIG. FIG. 4 is a flowchart showing an example of the feature registration process using the captured image.

The feature registration processing unit 101 selects one link information included in the road network information stored in the road network information storage unit 110 (step S101). This link information is the link information to be registered as the feature information. Hereinafter, the link information selected in this step is also referred to as “selected link information”.

Next, the feature registration processing unit 101 acquires an image captured around the link represented by the selected link information from the image storage unit 120 (step S102). The feature registration processing unit 101 may acquire a captured image around the link by using, for example, the position information of the coordinate point sequence included in the selected link information. If there are a plurality of the corresponding captured images, the feature registration processing unit 101 acquires all of the plurality of captured images.

Next, the feature registration processing unit 101 selects one captured image from the captured images acquired in step S102 above (step S103).

Next, the feature registration processing unit 101 analyzes the captured image selected in step S103 above to detect the feature in the captured image (step S104). Any object detection method can be used for the analysis of the captured image.

Next, the feature registration processing unit 101 determines whether or not the feature is detected from the captured image as the analysis result in the above step S104 (step S105).

When it is determined in step S105 that the feature is detected from the captured image, the feature registration processing unit 101 determines whether or not the feature information of the feature has been registered with respect to the selection link information (step). S106). That is, the feature registration processing unit 101 determines whether or not the feature information is already associated with the selection link information.

On the other hand, if it is not determined in step S105 that the feature is detected from the captured image, the feature registration processing unit 101 proceeds to the process of step S108 described later.

If it is determined in step S106 that the feature information of the feature has not been registered, the feature registration processing unit 101 registers the feature information of the feature in association with the selection link information (step S107). It is sufficient that the selection link information and the feature information are associated with each other, and the feature registration processing unit 101 may register (save) the feature information in an arbitrary storage unit. As an example, it is conceivable to store the feature information in the road network information storage unit 110 in association with the selection link information.

On the other hand, if it is determined in step S106 that the feature information of the feature has been registered, the feature registration processing unit 101 proceeds to the process of step S108 described later.

Here, in step S104 above, a plurality of features (that is, a plurality of types of features, such as a "curb" and a "guard rail") may be detected from the captured image. In this case, in step S106 above, the feature registration processing unit 101 may determine whether or not all the feature information of these plurality of features has been registered. Then, when the feature information of at least one feature is not registered in the selection link information, in step S107, the feature registration processing unit 101 associates the unregistered feature information with the selection link information. Just register.

The feature registration processing unit 101 determines whether or not there is an unselected captured image in the captured image acquired in step S102 above (step S108).

If it is determined in step S108 that there is an unselected captured image, the feature registration processing unit 101 returns to the process of step S103. As a result, the processes of steps S104 to S107 are repeatedly executed for each captured image acquired in step S102.

On the other hand, when it is determined in step S108 that there is no unselected captured image, the feature registration processing unit 101 is not included in the link information included in the road network information stored in the road network information storage unit 110. It is determined whether or not there is the selected link information (step S109).

If it is determined in step S109 that there is unselected link information, the feature registration processing unit 101 returns to the processing of step S101. As a result, the processes of steps S102 to S108 are repeatedly executed for each link information included in the road network information stored in the road network information storage unit 110.

On the other hand, if it is determined in step S109 that there is no unselected link information, the feature registration processing unit 101 ends the feature registration process using the captured image.

As described above, the path search system 1 according to the present embodiment can register the feature information in association with the link information by using the captured image.

Although the feature registration process using the captured image created in advance has been described in FIG. 4, the feature registration process may be performed using the captured image created in real time. For example, the processes of steps S104 to S107 described above are executed using the captured image created in real time by the drive recorder mounted on the vehicle and the link information indicating the road on which the vehicle is currently traveling. May be good. As a result, for example, when a vehicle travels on a road on which feature information is not registered, it becomes possible to dynamically register feature information for link information representing the road.

Further, in FIG. 4, the captured image is selected for the selection link information. For example, when the position information is given to the captured image, the captured image is selected first and then selected. The link information associated with the feature information may be selected by using the position information given to the captured image.

<< Feature registration process using map information >>
Next, the feature registration process using the map information will be described with reference to FIG. FIG. 5 is a flowchart showing an example of a feature registration process using map information.

The feature registration processing unit 101 selects one link information included in the road network information stored in the road network information storage unit 110 (step S201). Hereinafter, the link information selected in this step is also referred to as “selected link information”.

Next, the feature registration processing unit 101 acquires the map information associated with the selection link information from the map information storage unit 130 (step S202).

Next, the feature registration processing unit 101 determines whether or not the map information acquired in step S202 includes feature information (step S203).

When it is determined in step S203 that the map information includes the feature information, the feature registration processing unit 101 determines whether or not the feature information has been registered with respect to the selected link information (step S204). .. That is, the feature registration processing unit 101 determines whether or not the feature information included in the map information acquired in step S202 is already associated with the selection link information.

On the other hand, if it is determined in step S203 that the map information does not include the feature information, the feature registration processing unit 101 proceeds to the process of step S206 described later.

If it is determined in step S204 that the feature information has not been registered, the feature registration processing unit 101 registers the feature information in association with the selection link information (step S205).

On the other hand, if it is determined in step S203 that the feature information has been registered, the feature registration processing unit 101 proceeds to the process of step S206 described later.

Here, the map information acquired in step S202 above includes a plurality of feature information (that is, feature information of a plurality of types of features. For example, feature information of "curb" and feature information of "guard fence". Etc.) may be included. In this case, in step S204, the feature registration processing unit 101 may determine whether or not all of the plurality of feature information has been registered. Then, when at least one feature information is not registered in the selection link information, in step S205, the feature registration processing unit 101 registers the unregistered feature information in association with the selection link information. Just do it.

The feature registration processing unit 101 determines whether or not there is unselected link information in the link information included in the road network information stored in the road network information storage unit 110 (step S206).

If it is determined in step S206 that there is unselected link information, the feature registration processing unit 101 returns to the processing of step S201. As a result, the processes of steps S202 to S205 are repeatedly executed for each link information included in the road network information stored in the road network information storage unit 110.

On the other hand, if it is determined in step S206 that there is no unselected link information, the feature registration processing unit 101 ends the feature registration process using the map information.

As described above, the route search system 1 according to the present embodiment can register the feature information in association with the link information by using the map information. Although FIG. 5 describes the feature registration process using the map information possessed by the route search system 1, all or part of the map information used for the feature registration process is an external server or system or the like. May be obtained from. Further, in FIG. 5, the map information is selected for the selection link information. For example, the feature information included in the map information is first selected and then attached to the selected feature information. Link information associated with feature information may be selected using the location information.

<Pathfinding process>
Hereinafter, a process (route search process) for searching a route in consideration of human damage to pedestrians when a traffic accident caused by a vehicle occurs will be described using the link information associated with the feature information. In the present embodiment, in addition to the route search process for searching for a route with less human damage, a case where the human damage value of the search route is calculated as a variation of the route search process will also be described.

Further, as an application example of a route with less human damage, for example, application to automatic driving can be considered. Therefore, a case of determining whether or not the search route is safe enough for automatic driving will also be described.

<< Route search processing when searching for a route with less human damage >>
First, the route search process in the case of searching for a route with less human damage will be described with reference to FIG. FIG. 6 is a flowchart showing an example of a route search process when searching for a route with less human damage.

The input unit 102 inputs a route search condition including a starting point, a destination, and the like (step S301). As the departure point, for example, the current position measured by a GPS (Global Positioning System) receiver or the like may be input.

Next, the route search processing unit 103 uses the route search condition input in step S301, the road network information stored in the road network information storage unit 110, and the human damage evaluation table 100. Search for a route in consideration of human damage to pedestrians when a traffic accident occurs (step S302). That is, the route search processing unit 103 refers to the human damage evaluation table 1000, and the sum of the costs (adjustment costs) obtained by multiplying the cost of the link information included in the road network information by the corresponding weighting coefficient is the minimum. Search for a route. Here, the corresponding weighting coefficient corresponds to the road type of the road (link) represented by the link information and the feature information or a combination thereof associated with the link information in the human damage evaluation table 1000. It is a weighting coefficient to be used.

As a result, a route that takes into consideration the human damage to pedestrians when a traffic accident occurs is searched for. The route search processing unit 103 may search for a predetermined number of routes in ascending order of the total adjustment cost.

Next, the output unit 104 outputs the route (search route) searched in step S302 to a predetermined output destination (step S303). At this time, when a plurality of routes are searched for in step S302, the output unit 104 may display the routes used for navigation in a manner selectable by the user.

For example, when the route is displayed and output on the display, the output unit 104 may display the link in different colors according to the adjustment cost of the link included in the search route, for example. For example, a link with a low adjustment cost is displayed in blue to indicate that it is a safe road with little human damage, and a link with a high adjustment cost is displayed in red to indicate a road with a risk of human damage. It is displayed with.

As described above, the route search system 1 according to the present embodiment can search for one or more routes in consideration of human damage to pedestrians when a traffic accident occurs. Therefore, for example, the user of the terminal device 20 can go to the destination by using a safe route (that is, a route that causes less human damage to pedestrians even if a traffic accident should occur). ..

In step S302 described above, the route search is performed using the adjustment cost obtained by multiplying the cost of the link information by the weighting coefficient, but for example, the human damage value may be used. Specifically, for example, instead of the cost of the link information included in the road network information, a route that minimizes the total human damage value corresponding to the link information may be searched for. Here, the human damage value corresponding to the link information is the road type of the road (link) represented by the link information in the human damage evaluation table 1000, and the feature information or the feature information associated with the link information. It is the human damage value corresponding to the combination.

Alternatively, in step S302 described above, for example, the sum of the cost of the link information included in the road network information and the human damage value corresponding to the link information is used as the adjustment cost of the link information, and the total adjustment cost is the minimum. You may search for the route that becomes.

<< Route search processing when calculating the human damage value of the search route >>
Next, the route search process for calculating the human damage value of the search route will be described with reference to FIG. 7. FIG. 7 is a flowchart showing an example of the route search process when calculating the human damage value of the search route.

Similar to step S301 in FIG. 6, the input unit 102 inputs a route search condition including a starting point, a destination, and the like (step S401).

Next, the route search processing unit 103 searches for a route using the route search condition input in step S401 and the road network information stored in the road network information storage unit 110 (step S402). .. At this time, unlike step S302 in FIG. 6, the route search processing unit 103 searches for a route without considering human damage. That is, the route search processing unit 103 searches for a route that minimizes the total cost of the link information included in the road network information, for example. The route search processing unit 103 may search for a predetermined number of routes in ascending order of the total cost of the link information.

Next, the route search processing unit 103 refers to the human damage evaluation table 1000, and is the sum of the human damage values of each link included in the route searched in step S402 above (that is, the link of each of these links). The sum of the human damage values corresponding to each of the information) is calculated (step S403). When a plurality of routes are searched in step S402, the route search processing unit 103 calculates the total human damage value of each link included in the route for each of the plurality of routes.

Next, the output unit 104 outputs the route searched in step S403 and the sum of the human damage values to a predetermined output destination (step S404). At this time, when a plurality of routes are searched for in step S402, the output unit 104 has a mode in which the user can select a route to be used for navigation, and the plurality of routes and a person for each of the plurality of routes. The total damage value may be displayed.

As described above, the route search system 1 according to the present embodiment can obtain one or a plurality of routes and the human damage value (total) of these routes. Therefore, for example, the user of the terminal device 20 selects a desired route from a plurality of routes with reference to (the sum of) the human damage values of the routes, and then uses the selected route to reach the destination. It will be possible to go to.

<< Route search processing when determining whether automatic operation of the search route is possible >>
Next, the route search process for determining whether or not the search route can be automatically operated will be described with reference to FIG. FIG. 8 is a flowchart showing an example of the route search process when determining whether or not the search route can be automatically operated.

Similar to step S301 in FIG. 6, the input unit 102 inputs a route search condition including a starting point, a destination, and the like (step S501).

Next, the route search processing unit 103 uses the route search condition input in step S501 and the road network information stored in the road network information storage unit 110 in the same manner as in step S402 of FIG. , Search for a route (step S502).

Next, the route search processing unit 103 refers to the human damage evaluation table 1000, and sets the reference value of the human damage value in the link included in the route (search route) searched in step S502 above. It is determined whether or not the unsatisfied link is included (step S503). Here, satisfying the standard value of the human damage value means that, for example, the human damage value corresponding to the link information of the corresponding link is equal to or less than the standard value. As the reference value, an arbitrary value is appropriately set in advance according to, for example, the performance and accuracy of automatic operation.

When it is determined in step S503 that the search route includes a link whose human damage value does not satisfy the reference value, the route search processing unit 103 determines that automatic operation is not possible at least on the link (step S504).

On the other hand, when it is determined in step S503 that the human damage value satisfies the reference value for all the links included in the search route, the route search processing unit 103 determines that automatic operation is possible on the search route (step S505). ..

Following step S504 or step S505, the output unit 104 outputs the determination result of step S504 or step S505 described above (step S506). At this time, for example, when outputting the determination result of step S504, the output unit 104 performs manual operation (or recommends manual operation) on the road (link) where the human damage value does not meet the reference value. May be notified.

As described above, the route search system 1 according to the present embodiment can automatically operate on the search route according to the human damage value of each link included in the search route when the search route is used for automatic operation. It can be determined whether or not. Thereby, for example, the user of the terminal device 20 can know that it is safer to switch to the manual operation in the section (link) where the automatic operation is determined to be impossible.

<Hardware configuration of computer 600>
Finally, the hardware configuration of the computer 600 (for example, the computer that realizes the server device 10 and the computer that realizes the terminal device 20) constituting the route search system 1 according to the present embodiment will be described with reference to FIG. .. FIG. 9 is a diagram showing an example of the hardware configuration of the computer 600.

The computer 600 shown in FIG. 9 includes an input device 601, a display device 602, an external I / F 603, a RAM (Random Access Memory) 604, a ROM (Read Only Memory) 605, a processor 606, and a communication device 607. , With an auxiliary storage device 608. Each of these hardware is connected so as to be communicable via the bus B.

The input device 601 is, for example, a touch panel, various buttons, or the like. The display device 602 is, for example, a display or the like. The computer 600 does not have to have at least one of the input device 601 and the display device 602.

The external I / F 603 is an interface with an external device. The external device includes a recording medium 603a and the like. The computer 600 can read and write the recording medium 603a via the external I / F 603. Examples of the recording medium 603a include a CD (Compact Disc), a DVD (Digital Versatile Disk), an SD memory card (Secure Digital memory card), a USB (Universal Serial Bus) memory card, and the like. The one or more programs (or modules) that realize each functional unit of the route search system 1 (for example, a feature registration processing unit 101, an input unit 102, a route search processing unit 103, an output unit 104, etc.) are recording media. It may be stored in 603a.

The RAM 604 is a volatile semiconductor memory that temporarily holds programs and data. The ROM 605 is a non-volatile semiconductor memory that can hold programs and data even when the power is turned off. The ROM 605 stores, for example, setting information related to an OS (Operating System), setting information related to a communication network, and the like.

The processor 606 is an arithmetic unit such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or an FPGA (Field-Programmable Gate Array). Each functional unit of the path search system 1 is realized by reading one or more programs stored in the ROM 605 or the auxiliary storage device 608 onto the RAM 604 and executing the process by the processor 606.

The communication device 607 is an interface for connecting the computer 600 to the communication network. One or more programs that realize each functional unit of the route search system 1 may be acquired (downloaded) from a predetermined server via the communication device 607.

The auxiliary storage device 608 is a non-volatile storage device such as an HDD (Hard Disk Drive) or SSD (Solid State Drive). The programs and data stored in the auxiliary storage device 308 include, for example, an OS, an application program that realizes various functions on the OS, and one or more programs that realize each functional unit of the route search system 1. Each storage unit of the route search system 1 (for example, a road network information storage unit 110, a captured image storage unit 120, a map information storage unit 130, a human damage evaluation table storage unit 140, etc.) may use, for example, an auxiliary storage device 608. It is feasible to use.

The path search system 1 according to the present embodiment is composed of one or more computers 600 having the hardware configuration shown in FIG. The computer 600 shown in FIG. 9 may include a plurality of processors 606 and a plurality of memories (RAM 604, ROM 605, auxiliary storage device 608, etc.). Further, the computer 600 may include a GPS receiver that receives a signal from a GPS satellite and measures the current position.

The present invention is not limited to the above-described embodiment disclosed specifically, and various modifications and modifications can be made without departing from the scope of claims.

1 Route search system 10 Server device 20 Terminal device 101 Feature registration processing unit 102 Input unit 103 Route search processing unit 104 Output unit 110 Road network information storage unit 120 Captured image storage unit 130 Map information storage unit 140 Human damage evaluation table storage Department N communication network

Claims (8)

An input means for inputting either an image captured by imaging a road on which a predetermined feature is installed and map information including feature information related to the feature.
Based on the input image or the map information, the link information included in the road network information is associated with the feature information related to the feature installed on the road represented by the link information in the storage unit. Registration method to register and
From the departure place using the link information included in the road network information, the feature information registered in the storage unit in association with the link information, and the search condition including at least the departure place and the destination. A route search means for searching a route to the destination and
Have,
The route search means is
An evaluation value regarding damage to pedestrians when an accident occurs on the road is calculated according to the feature information and the type of road on which the feature represented by the feature information is installed, and the calculated evaluation value is calculated. An information processing device that searches for the route using the above . It has a detection means for detecting a feature in the captured image by a predetermined object detection method.
The registration means is
The first aspect of claim 1, wherein the link information is associated with the feature information related to the feature detected from the captured image created by imaging the road represented by the link information and registered in the storage unit. Information processing equipment. The evaluation value is
Depending on the feature information and the type of the road, it is a human damage value indicating the risk of causing damage to pedestrians when an accident occurs on the road, or a weighted value corresponding to the human damage value. The information processing apparatus according to claim 1 or 2 . The evaluation value is the weighted value, and is
It has a display means for displaying the searched route on a predetermined display unit.
The display means is
3. Claim 3 for displaying the link in the display unit in a different display mode according to the evaluation value of the feature information registered in the storage unit in association with the link information of the link included in the route. The information processing device described in. The route search means is
The information processing apparatus according to any one of claims 1 to 4, which calculates the evaluation value according to the current time or the information representing the number of pedestrians on the road at the current time. It has a determination means for determining whether or not the road represented by the link included in the searched route includes a road whose evaluation value does not meet a predetermined criterion.
When it is determined that a road whose evaluation value does not meet a predetermined standard is included, a notification means for notifying that the vehicle cannot be automatically driven on the route or a road whose evaluation value does not meet the predetermined standard, and a notification means.
The information processing apparatus according to any one of claims 1 to 5 . An input procedure for inputting either an image captured by imaging a road on which a predetermined feature is installed or map information including feature information related to the feature, and an input procedure.
Based on the input image or the map information, the link information included in the road network information is associated with the feature information related to the feature installed on the road represented by the link information in the storage unit. Registration procedure to register and
From the departure place using the link information included in the road network information, the feature information registered in the storage unit in association with the link information, and the search condition including at least the departure place and the destination. The route search procedure for searching the route to the destination and the route search procedure.
The computer runs ,
The route search procedure is
An evaluation value regarding damage to pedestrians when an accident occurs on the road is calculated according to the feature information and the type of road on which the feature represented by the feature information is installed, and the calculated evaluation value is calculated. An information processing method for searching the route using the above . An input procedure for inputting either an image captured by imaging a road on which a predetermined feature is installed or map information including feature information related to the feature, and an input procedure.
Based on the input image or the map information, the link information included in the road network information is associated with the feature information related to the feature installed on the road represented by the link information in the storage unit. Registration procedure to register and
From the departure place using the link information included in the road network information, the feature information registered in the storage unit in association with the link information, and the search condition including at least the departure place and the destination. The route search procedure for searching the route to the destination and the route search procedure.
Let the computer run
The route search procedure is
An evaluation value regarding damage to pedestrians when an accident occurs on the road is calculated according to the feature information and the type of road on which the feature represented by the feature information is installed, and the calculated evaluation value is calculated. A program that searches for the route using .

Images