JP2019158701A - Feature point generating method - Google Patents

Abstract

To provide a feature point generation method capable of generating a feature point of a new road, a feature point generation device, a feature point generation program, and a recording medium for recording the feature point generation program.SOLUTION: A server 10 generates a feature point Pfn for respective plurality of travel loci, and obtains an average position of a plurality of feature points Pfn when the generated feature point Pfn exists within a predetermined range A2 in the plural. Then, the server 10 integrates the plurality of feature points Pfn into the feature point Pfn of an average position.SELECTED DRAWING: Figure 7

Description

  The present invention relates to a feature point generation method.

  When a vehicle travels on a new travel route that does not exist in the map represented by the existing map data, such as a newly opened travel route, the map data is updated by inferring the shape of the new travel route from the vehicle location information and travel direction The technique which performs is known (patent document 1).

  When using the above technology for roads where there are many intersections and corners such as roads in parking lots, not only the shape but also the generation of feature points to identify intersections and corners can be used for navigation and automatic driving. Indispensable to use. However, in the technique of Patent Document 1, there is a problem that a new feature point is not generated only by estimating the shape of a new traveling road.

JP 2014-235510 A

  This invention makes it an example of a subject to cope with such a problem. That is, the present invention provides, for example, a feature point generation method, a feature point generation device, a feature point generation program, and a recording medium on which the feature point generation program is recorded that can generate a feature point of a new road. It is said.

  The feature point generation method according to claim 1, which has been made to solve the above-described problem, is a feature point generation method for generating a feature point that is a candidate for a node on a travel path based on a travel locus of a moving object, A generation step of generating feature points for each of a plurality of travel trajectories; and an integration step of integrating the plurality of feature points when a plurality of the generated feature points exist within a predetermined range. .

  The feature point generation device according to claim 3 is a feature point generation device that generates a feature point that is a candidate for a node on a travel path based on a travel locus of a moving body, and generates a feature point for each of a plurality of travel trajectories. And a combining unit that integrates the plurality of feature points when a plurality of the generated feature points exist within a predetermined range.

  The feature point generation program according to claim 4 is a feature point generation program for causing a computer to generate a feature point that is a candidate for a node on a travel path based on a travel trajectory of a mobile object. When a plurality of generated feature points exist within a predetermined range, a generation unit that generates points, and an integration unit that integrates the plurality of feature points, are configured to function.

  According to a fifth aspect of the present invention, a feature point generating program according to the fourth aspect is recorded.

1 is a system configuration using a feature point generation device and a link information generation device according to an embodiment of the present invention. It is a flowchart of the operation | movement concerning the feature point production | generation of the feature point production | generation apparatus shown by FIG. It is explanatory drawing which showed the specific example of the feature point production | generation. It is explanatory drawing which showed the specific example of the feature point production | generation. It is explanatory drawing which showed the specific example of the feature point production | generation. It is explanatory drawing which showed the modification of feature point production | generation. It is explanatory drawing which showed the specific example of the feature point integration. It is a flowchart of the operation | movement concerning the feature point production | generation apparatus shown by FIG. (A) shows the integration result when the travel locus is small, and (B) shows the integration result when the travel locus is large. It is explanatory drawing which showed the specific example of link information generation. It is explanatory drawing which showed the specific example of link information generation. It is a flowchart of the operation | movement concerning the link information generation apparatus shown by FIG. It is explanatory drawing which showed the specific example of link information generation. It is explanatory drawing which showed the specific example of link information generation.

  A feature point generation method according to an embodiment of the present invention is a feature point generation method that generates a feature point that is a candidate for a node on a travel path on the basis of a travel trajectory of a moving object. A generation step of generating points; and an integration step of integrating the plurality of feature points when a plurality of the generated feature points exist within a predetermined range. Thereby, the feature point suitable for the use of navigation or automatic driving can be generated.

  Further, in the integration step, the plurality of feature points may be integrated into feature points having an average latitude and longitude. Thereby, the feature point suitable for the use of navigation or automatic driving can be further generated.

  A feature point generation device according to an embodiment of the present invention is a feature point generation device that generates a feature point that is a candidate for a node on a travel path based on a travel trajectory of a moving object. Each includes a generation unit that generates a feature point, and an integration unit that integrates the plurality of feature points when a plurality of the generated feature points exist within a predetermined range. Thereby, the feature point suitable for the use of navigation or automatic driving can be generated.

  Moreover, it is good also as a feature point production | generation program which makes a computer perform the feature point production | generation method mentioned above. Since the program is executed by the computer in this way, dedicated hardware or the like is not necessary, and can be installed and functioned in a general-purpose information processing apparatus.

  The feature point generation program described above may be stored in a computer-readable recording medium. In this way, the program can be distributed as a single unit in addition to being incorporated in the device, and version upgrades can be easily performed.

  A feature point generation device and a link information generation device of the present invention will be described with reference to FIGS. A server 10 as a feature point generation device and a link information generation device according to an embodiment of the present invention includes a communication unit 11, a feature point generation unit 12, a link information generation unit 13, and a storage unit 14. Yes.

  The communication part 11 communicates with the vehicle equipment 20 mentioned later via networks N, such as the internet. For example, the communication unit 11 receives a travel locus such as position information (latitude, longitude), a traveling direction, and an inclination angle of the vehicle (moving body) acquired by the in-vehicle device 20. In addition, when the in-vehicle device 20 is a device that requires map data such as a navigation device, the communication unit 11 receives map data stored in the storage unit 14 described later in response to a request from the in-vehicle device 20. Send.

  The feature point generation unit 12 generates feature points that are candidates for nodes on the travel path based on the travel locus received from the communication unit 11.

  The link information generation unit 13 generates a link that connects the feature points generated by the feature point generation unit 12.

  The storage unit 14 stores the feature points generated by the feature point generation unit 12 and the links generated by the link information generation unit 13. In addition, the storage unit 14 accumulates and stores travel trajectories received from the plurality of in-vehicle devices 20. In addition, the storage unit 14 stores existing map data in which the traveling path of the vehicle is indicated by nodes, links, and the like.

  In the above description, the feature point generation unit 12 and the link information generation unit 13 function as an arithmetic device such as a CPU (Central Processing Unit) of the server 10. The communication unit 11 functions as a network interface of the server 10. The storage unit 14 functions as a storage medium such as a hard disk of the server 10. Therefore, the flowcharts of FIGS. 2, 8, and 12 to be described later executed by the feature point generation unit 12 and the link information generation unit 13 are configured as computer programs executed by the CPU, so that the feature point generation program and link information generation are performed. It can be a program. Moreover, the server 10 implements the feature point generation method and the link information generation method of the present invention by the feature point generation unit 12 and the link information generation unit 13 executing the flowcharts shown in FIGS. .

  The in-vehicle device 20 is mounted on a vehicle and collects and transmits a travel locus to the server 10. Moreover, the vehicle equipment 20 requests | requires the map data produced | generated with respect to the server 10 as needed, when comprised as a navigation apparatus.

  The in-vehicle device 20 includes a communication unit 21, a control unit 22, and a vehicle information acquisition unit 23.

  The communication unit 21 communicates with the server 10 via a network N such as the Internet. The communication unit 21 transmits a travel locus including vehicle position information (latitude and longitude) acquired by the vehicle information acquisition unit 23, a traveling direction, an inclination angle, and the like. In this embodiment, as shown in FIG. 3, for example, the traveling locus is composed of point cloud data representing a position (latitude, longitude) on the locus on which the vehicle has traveled, and a traveling direction at the position is represented by a point representing the position. An inclination angle is added.

  In addition, when the in-vehicle device 20 is a device that requires map data such as a navigation device, the communication unit 21 requests the map data from the server 10 under the control of the control unit 22 and transmits the map data from the server 10. Received map data.

  The control unit 22 governs overall control of the in-vehicle device 20. The control unit 22 causes the communication unit 21 to transmit the position information (latitude, longitude), traveling direction, inclination angle, and the like collected by the vehicle information acquisition unit 23 to the server 10 as a travel locus.

  The vehicle information acquisition unit 23 is connected to a GPS (Global Positioning System) receiver, a gyro sensor, various sensors such as a vehicle speed pulse, a receiver, and the like. The vehicle information acquisition unit 23 collects information such as both position information (latitude and longitude), a traveling direction, and an inclination angle from the sensors described above.

  The in-vehicle device 20 is not limited to a car navigation system installed on a vehicle instrument panel or the like, and may be a mobile device such as a smartphone. That is, the in-vehicle device 20 may be detachably installed in the vehicle.

  In the above description, the control unit 22 functions as an arithmetic device such as a CPU of the in-vehicle device 20. The communication unit 21 functions as a communication circuit, an antenna, and the like of the in-vehicle device 20. The vehicle information acquisition unit 23 functions as an interface circuit with various sensors.

  Next, operations of the server 10 and the in-vehicle device 20 having the above-described configuration will be described. The in-vehicle device 20 transmits the travel locus to the server 10 at a predetermined timing such as every certain time or every certain distance. The server 10 functions as an acquisition unit, receives (acquires) a travel locus from the in-vehicle device 20, and sequentially stores it in the storage unit 14.

  The server 10 (the feature point generation unit 12) described above executes the feature point generation process shown in FIG. 2 at a predetermined timing, for example, every time a travel locus is received or every certain period. The server 10 reads one of the plurality of travel loci stored in the storage unit 14 that has not been subjected to the feature point generation process (step S1). Subsequently, the server 10 determines whether or not the read travel locus is a travel locus deviating from the travel path included in the map data using a known map matching technique (step S2).

  When the server 10 determines that the travel locus is a travel route included in the map data (N in step S2), the process is terminated.

  On the other hand, when the server 10 determines that the travel locus is a locus deviated from the travel path included in the map data (Y in step S2), the server 10 proceeds to steps S3 to S13 and determines the travel path node candidate from the travel trajectory. Is generated.

  First, the server 10 functions as an extraction unit, and extracts a straight line component from the travel locus using a well-known straight line extraction technique (step S3). Next, as shown in FIG. 3 (A), the server 10 includes an extension line LPn of the extracted linear component LSn and an extension line LPn + 1 of another linear component LSn + 1 that is adjacent to the linear component LSn in the travel locus. An intersection point is obtained (step S4). If the server 10 can obtain the intersection point in step S4 (Y in step S5), the intersection point obtained in step S4 is set as the feature point candidate Pcn as shown in FIG. 3B (step S6).

  Next, the server 10 determines whether or not a travel locus exists within a predetermined range A1 centered on the feature point candidate Pcn (step S7). In the present embodiment, the predetermined range A1 is an area within a circle centered on the feature point candidate Pcn, but is not limited thereto. The predetermined range A1 may have any shape as long as the feature point candidate Pcn is at the center.

  As shown in FIG. 3B, the server 10 has a traveling locus within a predetermined range A1 centered on the feature point candidate Pcn (Y in step S7), as shown in FIG. After functioning as the first generation unit and determining the feature point candidate Pcn as the feature point Pfn (step S8), the process proceeds to step S13.

  On the other hand, for example, as shown in FIG. 4A, the server 10 does not have a travel locus within a predetermined range A1 centered on the feature point candidate Pcn, such as when the radius of curvature of the travel locus is large (in step S5). N), go to step S9. Also, the server 10 proceeds to step S9 even when the intersection of the extension lines LPn and LPn + 1 cannot be made, for example, as in the locus of crank movement as shown in FIG. 5 (N in step S5).

  In step S9, as shown in FIG. 4B and FIG. 5, the server 10 tangents at the center of the trajectory from the point Pn out of the linear component LSn to the point Pn + 1 on the other linear component LSn + 1 in the traveling trajectory. Ltn is obtained. Then, the server 10 sets the intersection point of the obtained tangent line Ltn and the extension line LPn of the straight line component LSn as the feature point candidate Pcn1, and also sets the intersection point of the obtained tangent line Ltn and the extension line LPn + 1 of the straight line component LSn + 1 as the feature point candidate Pcn2. (Step S10).

  Thereafter, similarly to step S7, the server 10 determines whether or not a traveling locus exists within a predetermined range A1 centered on the feature point candidates Pcn1 and Pcn2 (step S11). When the traveling locus exists within the predetermined range A1 centered on the feature point candidates Pcn1 and Pcn2 (Y in step S11), the server 10 functions as a second generation unit, and the feature point candidates Pcn1 and Pcn2 are used as the feature points Pfn. After confirming, the process proceeds to step S13. On the other hand, if the travel locus does not exist within the predetermined range A1 centering on the feature point candidates Pcn1 and Pcn2 (N in Step S11), the server 10 proceeds to Step S13 without determining the feature point Pfn.

  Thereafter, the server 10 determines whether or not the process of determining the feature points in steps S4 to S12 has been executed for all the linear components adjacent in the travel locus (step S13). If the feature points have not been determined for all the adjacent linear components (N in step S13), the process returns to step S4 to execute a process for determining the feature points for the next adjacent linear components LSn + 1 and LSn + 2 on the travel locus. .

  According to the feature point generation process described above, the server 10 extracts a straight line component from the travel locus, and extends the extracted line LPn of the straight line component LSn and another straight line component LSn + 1 adjacent to the straight line component LSn in the travel locus. A feature point candidate Pcn that is an intersection with the line LPn + 1 is generated as a feature point Pfn. As a result, feature points can be generated at positions that are candidates for nodes, such as corners of the road and intersections, and feature points of the road suitable for use in navigation and automatic driving can be generated.

  Further, according to the above-described feature point generation processing, when there is no traveling locus within the predetermined range A1 centered on the feature point candidate Pcn that is the intersection of the extension lines LPn and LPn + 1, or the extension lines LPn and LPn + 1 If there is no intersection point, feature point candidates Pcn1 and Pcn2 that are intersection points between the tangent line Ltn and the extension lines LPn and LPn + 1 are generated as feature points Pfn.

  As a result, as shown in FIG. 4, when the radius of curvature of the travel locus is large, the feature point Pfn can be generated near the corner of the travel path and near the travel locus. As a result, map matching can be performed with high accuracy, and it is possible to further generate feature points of a travel route suitable for use in navigation and automatic driving.

  In the above embodiment, when there is no traveling locus within the predetermined range A1 centered on the intersection of the extension lines LPn and LPn + 1, the feature point Pfn is not generated at the intersection, but this is not restrictive. If there is an intersection of the extension lines LPn and LPn + 1 without determining whether or not a traveling locus exists within the predetermined range A1, the intersection may be set as the feature point Pfn.

  Further, when there is no travel locus within the predetermined range A1 centered on the intersection of the extension lines LPn and LPn + 1, the feature point Pfn is determined based on the extension lines LPn and LPn + 1 without newly obtaining the feature point candidates Pcn1 and Pcn2. It does not have to be generated.

  Further, in the above embodiment, when there is no travel locus within the predetermined range A1 centering on the intersection (feature point candidate Pcn1, Pcn2) of the tangent line Ltn and the extension lines LPn, LPn + 1, the feature point Pfn is not generated. It is not limited to this. The intersection of the tangent line Ltn and the extension lines LPn and LPn + 1 may be generated as the feature point Pfn without determining whether or not a travel locus exists within the predetermined range A1 centered on the feature point candidates Pcn1 and Pcn2.

  Further, when there is no traveling locus within the predetermined range A1 centering on the feature point candidates Pcn1 and Pcn2, a tangent line is drawn at a position slightly shifted from the center toward the points Pn and Pn + 1, and the tangent line and the extension line LPn, The intersection with LPn + 1 may be a new feature point candidate. Then, it is conceivable that the tangent line is shifted toward the points Pn and Pn + 1 until the travel locus exists within the predetermined range A1 centering on the new feature point candidate.

  In the above-described embodiment, the feature point Pfn is generated from the position (latitude, longitude) of the travel locus, but the present invention is not limited to this. For example, as illustrated in FIG. 6, the server 10 may set a feature point Pfn at a position on the travel locus where the change in the inclination angle is equal to or greater than a predetermined angle. In the present embodiment, the positions on the travel locus where the change in the inclination angle is 1 degree or more are set as the feature points Pfn and Pfn + 1. Thereby, for example, the feature points Pfn and Pfn + 1 can be generated at the boundary between each floor such as a self-propelled multilevel parking lot and a slope connecting each floor. Feature points may be generated using GPS altitude data. However, GPS altitude data is highly likely to have a large error. can get. For this reason, the feature points Pfn and Pfn + 1 suitable for use in navigation and automatic driving can be generated.

  In addition, a camera is installed in the vehicle, and the camera image is transmitted from the vehicle to the server 10. The server 10 may generate a point as a feature point by analyzing a camera image and detecting a landmark such as a toll booth. Further, a narrow band communication device (for example, DSRC) that communicates with a toll booth or the like may be mounted on the vehicle so that the communication information is added to the position information transmitted to the server 10. The server 10 generates the communication position as a feature point.

  By executing the feature point generation process described above, it is possible to generate feature points for each of a plurality of traveling trajectories. For this reason, as shown in FIG. 7, for example, a plurality of feature points Pf are generated for intersections of the same traveling road.

  Therefore, each time the feature point Pfn is determined by the feature point generation process (that is, every time steps S9 and S12 are executed), the server 10 functions as an integration unit and integrates a plurality of feature points Pfn. The feature point integration process shown in FIG.

  In the feature point integration processing, the server 10 determines whether or not an existing feature point Pfn determined before the feature point Pfn exists within a predetermined range A2 centered on the determined feature point Pfn ( Step S21). The predetermined range A2 may be the same as or different from the predetermined range A1 used for the feature point generation process. If there is an existing feature point Pfn in the predetermined range A2 (Y in step S21), the server 10 obtains an average position of the two feature points Pfn existing in the predetermined range A2 (step S22). Then, the server 10 integrates the feature points at the average position (step S23).

  Thereafter, the server 10 deletes the two feature points Pfn before integration, stores the integrated feature points Pfn as existing feature points Pfn in the storage unit 14 (step S24), and ends the processing. On the other hand, if the existing feature point Pfn does not exist within the predetermined range A2 (N in step S21), the server 10 stores the feature point Pfn determined this time in the storage unit 14 as the existing feature point (step S21). S24), the process is terminated.

  According to the feature point integration process described above, when a plurality of generated feature points Pfn exist within the predetermined range A2, a plurality of feature points Pfn can be integrated. As a result, a plurality of feature points Pfn are not attached to one turning corner or intersection of the traveling road, and feature points suitable for use in navigation and automatic driving can be generated.

  Further, according to the above-described feature point integration process, the feature points having the average position (latitude, longitude) of the plurality of feature points Pfn are integrated. Thereby, the feature point Pfn suitable for the use of navigation and automatic driving can be generated.

  The above-described feature point integration processing has different integration results depending on the number of travel tracks. FIG. 9A shows the feature point integration result when the travel locus is small. FIG. 9B shows a feature point integration result when there are many traveling tracks. When the traveling locus is large, the position of the feature point 1 moves slightly downward compared to when the traveling locus is small. In general, it is considered that the feature points become closer to the average of the travel path on which the actual vehicle travels as the travel trajectory increases. Thus, by generating feature points according to the actual travel route and using the map data, the accuracy of map matching can be improved.

  Note that the above-described feature point integration processing is integrated every time one feature point is generated by the feature point generation processing, but is not limited thereto. The feature point integration process may be executed after the feature point generation process is executed for a plurality of travel loci (that is, after the feature point generation process is executed a plurality of times). In this case as well, the latitudes and longitudes of a plurality of feature points existing within the predetermined range A2 are averaged and integrated into the averaged points. In addition, if there are a plurality of feature points having the same latitude and longitude among a plurality of feature points existing in the predetermined range A2, they may be integrated into a large number of latitudes and longitudes. Further, the feature points may be integrated into the center position of the figure formed by connecting a plurality of feature points existing within the predetermined range A2.

  The feature point integration process described above is a process of integrating the feature points generated from the extension lines LPn and LPn + 1 of the travel locus. However, it is conceivable that the feature points generated from the inclination angle are also integrated. For the feature point generated from the tilt angle, the tilt angle is added to the feature point. If there are a plurality of feature points having the same inclination angle within the predetermined range A2, the feature points may be integrated by averaging the latitude and longitude.

Next, the server 10 generates a link that connects the feature points integrated by the above-described feature point integration processing. As shown in FIG. 10, the server 10 (the link information generation unit 13) basically follows the order of passage of one traveling locus R1 passing through the predetermined range A3 from each of the plurality of feature points Pf ₇ and Pf _18. The characteristic points Pf ₇ and Pf ₁₈ are connected to each other. The predetermined range A3 may be the same as or different from the predetermined ranges A1 and A2 used for the feature point generation process and the feature point integration process. At this time, the connection direction of the feature points (vehicle passing direction) may be added to the link data.

  However, in this link generation method, as shown in FIG. 11B, a link that connects the feature point Pf3 and the feature point Pf2 is generated along the travel locus R2, and is generated based on the travel locus R1. Since the travel locus R2 passes through the predetermined range A3 centered on the feature point Pf8, a link connecting the feature point Pf2 → the feature point Pf8 → the feature point Pf3 is generated as shown in FIG. End up.

  Therefore, in this embodiment, the link generation process shown in FIG. 12 is executed. First, the server 10 generates the feature point generation process, and among the plurality of feature points integrated by the feature point integration process, the same traveling locus passes through the predetermined range A3 from each feature point and passes through the same. Three feature points in order are extracted (step S30). For example, in the example shown in FIG. 11, the feature points Pf2, Pf8, and Pf3 have three characteristics in which the travel locus R2 (one of a plurality of travel locus) passes through the predetermined range A3 and the passage order is continuous. Extracted as a point.

  Next, the server 10 includes a line L1 connecting the three consecutive extracted feature points Pf2, Pf8, and Pf3, and a travel locus R2 that passes through the predetermined range A3 from each of the three feature points Pf2, Pf8, and Pf3. The first evaluation result that evaluates the distance between is calculated (step S31). In the present embodiment, as shown in FIG. 11A, the server 10 first evaluates the maximum value among the distances until the normal line (indicated by the arrow in the figure) on the travel locus R2 intersects the line L1. As a result. In the example shown in FIG. 11A, the distance until the normal intersects the feature point Pf8 is the maximum value.

  Next, the server 10 calculates the second evaluation result that evaluates the distance between the line L2 connecting the first and last feature points Pf2 and Pf3 among the three feature points Pf2, Pf8, and Pf3 and the travel locus R2. (Step S32). In this embodiment, as shown in FIG. 11B, the server 10 uses the maximum value of the distances until the normal on the travel locus R2 intersects the line L2 as the second evaluation result. In the example shown in FIG. 11B, the distance until the normal intersects with the feature point Pf2 is the maximum value.

  Next, the server 10 compares the first evaluation result and the second evaluation result, and if the first evaluation result is larger than the second evaluation result by a certain value or more (Y in step S33), the middle feature point Without connecting Pf8, a link that connects the preceding and following feature points Pf2 and Pf3 is generated, and the process ends (step S34). On the other hand, if the first evaluation result is not larger than the second evaluation result by a predetermined value or more (N in step S33), the server 10 connects three consecutive feature points Pf2, Pf8, and Pf3 and ends the process. (Step S35).

  In particular, the traveling direction of the parking lot is often determined in detail, such as the direction of travel. In the example shown in FIG. 11, there is a pole cone between Pf2 and Pf8, and the link between Pf2 and Pf8 is It was an inappropriate link. According to the above-described embodiment, in the example illustrated in FIG. 11, the link connecting the feature points Pf2 and Pf3 is generated. For this reason, the accuracy of the link is improved, and link information suitable for use in navigation and automatic driving can be generated.

  In addition, a 1st evaluation result and a 2nd evaluation result are not limited to the Example mentioned above. As the first evaluation result, for example, as shown in FIG. 13A, a normal locus L3 on a travel locus R2, a line L1, and a travel locus R2 passing through the first feature point Pf3, and the last feature point Pf2, as shown in FIG. The area surrounded by the normal line L4 on the travel locus R2 passing through (indicated by the oblique lines in the figure) may be used. As the second evaluation result, for example, as shown in FIG. 13B, an area (indicated by hatching in the drawing) surrounded by the traveling locus R2, the line L2, and the normals L3 and L4 may be used.

  Moreover, as a 1st evaluation result, as shown to FIG. 14 (A), the maximum value may be sufficient among the distances until it intersects with the normal on driving track R2, and each of three feature points Pf2, Pf8, and Pf3. Moreover, as a 2nd evaluation result, as shown to FIG. 14 (B), the maximum value may be sufficient among the distances until the normal on the driving | running | working locus | trajectory R2 and each of the front and back features Pf2 and Pf3 intersect. In this case, as in the embodiment shown in FIG. 11, the distance until the normal on the travel locus R2 intersects with the feature point Pf8 is the first evaluation result, and the normal on the travel locus R2 intersects with the feature point Pf2. Is the second evaluation result.

  As described above, even when the first evaluation result and the second evaluation result are determined, the accuracy of the link is improved, and link information suitable for use in navigation and automatic driving can be generated.

  In the above-described embodiment, whether the first evaluation result is greater than a certain value compared to the second evaluation result, that is, whether the difference between the first evaluation result and the second evaluation result is greater than a certain value. The link was generated based on this, but it is not limited to this. A link may be generated based on whether the first evaluation result is greater than the second evaluation result. More specifically, if the first evaluation result> the second evaluation result, the middle feature point Pf8 is not connected, and a link connecting the preceding and following feature points Pf2, Pf3 is generated. On the other hand, if the first evaluation result ≦ the second evaluation result, the three feature points Pf2, Pf8, and Pf3 are connected to generate a link.

  Further, according to the above-described embodiment, the server 10 has extracted three consecutive feature points in the link information generation process, but the present invention is not limited to this. Three or more consecutive feature points may be extracted.

  Further, according to the above-described embodiment, the server 10 that can communicate with the in-vehicle device 20 via the network N generates the feature points and the link information. However, the present invention is not limited to this. The travel locus may be stored in a memory that is detachable from the in-vehicle device 20, and the feature points and link information may be generated using a device that reads the memory removed from the in-vehicle device 20. Alternatively, the in-vehicle device 20 may generate a feature point from its own travel locus and transmit it to the server 10.

  Further, according to the above-described embodiment, the generation of feature points, integration, and generation of link information are performed by one server 10, but the present invention is not limited to this. Generation of feature points, integration, and generation of link information may be performed by separate servers.

  In the above-described embodiments, the description has been made mainly assuming the traveling path in the parking lot, but the present invention is not limited to this. The travel path may be a general road.

  The present invention is not limited to the above embodiment. That is, various modifications can be made without departing from the scope of the present invention.

10 servers (feature point generator, link information generator, acquisition unit)
12 feature point generation unit (extraction unit, first generation unit, second generation unit, generation unit, integration unit)
13 Link information generator

Claims (5)

A feature point generation method for generating a feature point that is a candidate for a node on a travel path based on a travel locus of a moving object,
A generation step of generating feature points for each of a plurality of travel trajectories;
An integration step of integrating the plurality of feature points when a plurality of the generated feature points exist within a predetermined range.   The feature point generation method according to claim 1, wherein in the integration step, the plurality of feature points are integrated into feature points having an average latitude and longitude. A feature point generation device that generates a feature point that is a candidate for a node on a travel path based on a travel locus of a moving object,
A generating unit that generates feature points for each of a plurality of traveling tracks;
An integration unit that integrates the plurality of feature points when there are a plurality of the generated feature points within a predetermined range. A feature point generation program for causing a computer to generate a feature point that is a candidate for a node on a travel path based on a travel locus of a moving object,
A generating unit that generates feature points for each of a plurality of traveling tracks;
When a plurality of the generated feature points exist within a predetermined range, a feature point generation program that functions as an integration unit that integrates the plurality of feature points.   A recording medium in which the feature point generation program according to claim 4 is recorded.

Images