Map processing system and computer-readable recording medium

Abstract

The map processing system (1) of the present invention includes: a feature amount calculation unit (14c) that calculates the feature amounts of feature points included in a map; an integrated feature point generation unit (14d) that generates integrated feature points by integrating a plurality of feature points; an integrated feature point matching unit (14e) that matches the integrated feature points between a plurality of maps; a feature point matching unit (14f) that matches individual feature points between a plurality of maps; and a map processing unit (14g) that processes the map based on the matching results of the integrated feature points and the matching results of the individual feature points.

Description

[0001] Cross - reference to related applications

[0002] This application is based on Japanese Application No. 2020 - 119192, filed on July 10, 2020, the contents of which are incorporated herein by reference. Technical field

[0003] The present disclosure relates to a map processing system and a computer - readable recording medium. Background art

[0004] There is provided a map processing device that acquires detection data from a vehicle side, generates an input map based on the acquired detection data, integrates a plurality of input maps to generate an integrated input map, or corrects the position of the input map to update a reference map. Specifically, for example, a plurality of input maps including position information of feature points such as landmarks are generated, the feature points included in the generated plurality of input maps are matched, and the plurality of input maps are overlapped to generate an integrated input map. In addition, the feature points included in the reference map and the feature points included in the input map are matched, the reference map and the input map are overlapped, the position of the input map is corrected, and the difference between the reference map and the input map is reflected in the reference map to update the reference map. When generating an integrated input map or updating a reference map in this way, it is preferable to improve the accuracy of the input map. For example, Patent Document 1 discloses the following method: A common three - point feature point is set between a plurality of maps, and the triangle formed by the set three - point feature point is corrected to improve the accuracy of the map.

[0005] Patent Document 1: Japanese Unexamined Patent Application Publication No. 2002 - 341757

[0006] In the method of Patent Document 1 described above, it is premised that any one of the overlapping plurality of maps includes feature points. In this case, the ground objects that can be feature points are various, such as signs, billboards, lane markings, and shape points at the ends of roads. If the number of feature points increases, the amount of data for matching feature points increases accordingly, and the amount of calculation increases. In view of this situation, it is considered to reduce the amount of calculation by integrating a plurality of feature points to generate integrated feature points and matching the integrated feature points.

[0007] In a structure for matching integrated feature points, there are cases where the integrated feature points can only be locally recognized. If the integrated feature points can only be locally recognized, the integrated feature points cannot be determined as integrated feature points shared among a plurality of maps. Summary of the invention

[0008] An object of the present disclosure is to appropriately reduce the amount of data when matching feature points, appropriately determine feature points shared among a plurality of maps, and appropriately process maps.

[0009] According to one aspect of the present disclosure, a feature quantity calculation unit calculates the feature quantity of feature points included in a map. An integrated feature point generation unit integrates a plurality of feature points to generate integrated feature points. When the integrated feature points are generated, an integrated feature point matching unit matches the integrated feature points among a plurality of maps. A feature point matching unit matches individual feature points among a plurality of maps. A map processing unit processes the map based on the matching results of the integrated feature points and the matching results of the individual feature points.

[0010] By integrating a plurality of feature points to generate integrated feature points and matching the integrated feature points among a plurality of maps, it is possible to appropriately reduce the amount of data when matching feature points. By matching the integrated feature points among a plurality of maps and then matching individual feature points among a plurality of maps, and processing the map based on the matching results of the integrated feature points and the matching results of the individual feature points, it is possible to appropriately determine the feature points shared among a plurality of maps. Thus, it is possible to appropriately reduce the amount of data when matching feature points, and appropriately determine the feature points shared among a plurality of maps, and appropriately process the map. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The above objects, other objects, features, and advantages of the present disclosure will become more apparent by referring to the following detailed description with reference to the accompanying drawings.

[0012] Figure 1 is a functional block diagram showing the overall structure of a map processing system according to one embodiment.

[0013] Figure 2 is a functional block diagram of a control unit in a server.

[0014] Figure 3 is a diagram for explaining a method of generating integrated feature points.

[0015] Figure 4 is a diagram for explaining a method of matching integrated feature points.

[0016] Figure 5 is a diagram showing a method of arranging signs on a road.

[0017] Figure 6 is a diagram showing feature points in an input map.

[0018] Figure 7 is a flowchart (one).

[0019] Figure 8 is a flowchart (two).

[0020] Figure 9 is a diagram for explaining a method of excluding feature points with a possibility of incorrect matching. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] Hereinafter, an embodiment will be described with reference to the accompanying drawings. In this embodiment, the case where the feature points included in the reference map and the feature points included in the input map are matched, the reference map and the input map are overlapped, the position of the input map is corrected, and the difference between the reference map and the input map is reflected in the reference map to update the reference map will be described. It can also be applied to the case where the feature points included in multiple input maps are matched and a unified input map is generated by overlapping the multiple input maps. That is, the multiple maps that are the objects of matching the feature points can be the reference map and the input map, or multiple input maps.

[0022] As Figure 1 shown, the map processing system 1 is configured such that the in-vehicle device 2 mounted on the vehicle side and the server 3 arranged on the network side can communicate data. The in-vehicle device 2 and the server 3 are in a many-to-one relationship, and the server 3 can communicate data with multiple in-vehicle devices 2.

[0023] The in-vehicle device 2 includes a control unit 4, a data communication unit 5, an image data input unit 6, a positioning data input unit 7, a sensor data input unit 8, and a storage device 9. Each functional module is configured to be able to communicate data via an internal bus 10. The control unit 4 is composed of a microcomputer having a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), and an I / O (Input / Output). The microcomputer executes a computer program stored in a non-transitory physical storage medium to perform processing corresponding to the computer program and control all operations of the in-vehicle device 2.

[0024] The data communication unit 5 controls the data communication with the server 3. The in-vehicle camera 11 is provided separately from the vehicle unit 2, captures the front of the vehicle, and outputs the captured image data to the vehicle unit 2. When the image data input unit 6 inputs the image data from the in-vehicle camera 11, it outputs the input image data to the control unit 4. The GNSS (Global Navigation Satellite System) receiver 12 is provided separately from the vehicle unit 2, receives the satellite signals transmitted from GNSS satellites and performs positioning, and outputs the positioning data to the vehicle unit 2. When the positioning data input unit 7 inputs the positioning data from the GNSS receiver 12, it outputs the input positioning data to the control unit 4. The various sensors 13 are provided separately from the vehicle unit 2, for example, include millimeter-wave radar, LiDAR (Light Detection and Ranging, Laser Imaging Detection and Ranging), etc., and output the measured sensor data to the vehicle unit 2. When the sensor data input unit 9 inputs the sensor data from the various sensors 13, it outputs the input sensor data to the control unit 4.

[0025] Based on the image data, positioning data, and sensor data, the control unit 4 establishes a correspondence relationship for the vehicle position, the time when the vehicle position is located, landmarks such as signs and billboards on the road, and the position of the lane markings, etc., to generate detection data, and stores the generated detection data in the storage device 9. In addition, the detection data may also include various information and position relationships such as road shape, road characteristics, and road width.

[0026] For example, the control unit 4 reads out the detection data from the storage device 9 every time a specified time elapses or every time the driving distance of the vehicle reaches a specified distance, and sends the read detection data from the data communication unit 5 to the server 3. The so-called segment unit is a unit that divides roads and regions in a predetermined unit for map management. In addition, the control unit 4 may also read out the detection data in a unit independent of the segment unit, and send the read detection data from the data communication unit 5 to the server 3. The so-called unit independent of the segment unit is, for example, a unit of the area specified by the server 3.

[0027] The server 3 includes a control unit 14, a data communication unit 15, and a storage device 16, and each functional module is configured to be able to perform data communication via the internal bus 17. The control unit 14 is composed of a microcomputer having a CPU, ROM, RAM, and I / O. The microcomputer executes the processing corresponding to the computer program by executing the computer program stored in the non-transitory physical storage medium, and controls all the operations of the server 3. The computer program executed by the microcomputer includes a map processing program.

[0028] The data communication unit 15 controls the data communication with the vehicle-mounted device 2. The storage device 16 includes: a detection data storage unit 16a for storing detection data, an input map storage unit 16b for storing the input map before format conversion, an input map storage unit 16c for storing the input map after format conversion, an input map storage unit 16d for storing the input map after position correction, a reference map storage unit 16e for storing the reference map before format conversion, and a reference map storage unit 16f for storing the reference map after format conversion. The input map is a map generated by the input map generation unit 14a described later based on the detection data. The reference map is, for example, a map generated by a map provider by measuring the site. That is, if the on-site data is not updated due to the opening of a new road or the like, the input map generated based on the detection data includes landmarks and lane markings, but the reference map corresponding to the site does not include landmarks and lane markings.

[0029] As Figure 2 shown, the control unit 14 includes an input map generation unit 14a, a format conversion unit 14b, a feature quantity calculation unit 14c, an integrated feature point generation unit 14d, an integrated feature point matching unit 14e, a feature point matching unit 14f, a map processing unit 14g, a difference detection unit 14h, and a difference reflection unit 14i. These functional modules correspond to the processing of a map processing program executed by a microcomputer.

[0030] If the detection data sent from the vehicle-mounted device 2 is received through the data communication unit 15, the input map generation unit 14a stores the received detection data in the detection data storage unit 16a. That is, since the vehicle-mounted device 2 and the server 3 are in a many-to-one relationship, the control unit 14 stores the multiple detection data received from the multiple vehicle-mounted devices 2 in the detection data storage unit 16a. The input map generation unit 14a reads the detection data from the detection data storage unit 16a and generates an input map based on the read detection data.

[0031] In this case, if the detection data sent from the vehicle-mounted device 2 is in segment units and the detection data is stored in the detection data storage unit 16a in segment units, the input map generation unit 14a directly reads the multiple detection data stored in the detection data storage unit 16a and generates an input map based on the read detection data. If the detection data sent from the vehicle-mounted device 2 is in a unit independent of segment units and the detection data is stored in the detection data storage unit 16a in a unit independent of segment units, the input map generation unit 14a reads the multiple detection data included in the segment as the object stored in the detection data storage unit 16a and generates an input map based on the read detection data.

[0032] When the input map generation unit 14a generates an input map, it stores the generated input map in the input map storage unit 16b. In this case, the input map generation unit 14a can store one input map in the input map storage unit 16b, or can integrate a plurality of input maps to generate an integrated input map and store the generated integrated input map in the input map storage unit 16b.

[0033] When integrating a plurality of input maps, the input map generation unit 14a can use the detection data transmitted from different vehicle-mounted devices 2, or can use the detection data transmitted from the same vehicle-mounted device 2 with a time difference. In addition, considering that there are feature points that cannot be set to be shared among a plurality of input maps, the input map generation unit 14a preferably obtains a segment including as many feature points as possible. That is, the input map generation unit 14a can also compare the number of feature points included in a segment with a specified number, and use a segment including more than the specified number of feature points as an acquisition target, while not using a segment not including more than the specified number of feature points as an acquisition target. In addition, the input map generation unit 14a can also determine the detection accuracy of the feature points, and use a segment including more than the specified number of feature points with a detection level of a specified level or higher as an acquisition target, while not using a segment not including more than the specified number of feature points with a detection level of a specified level or higher as an acquisition target.

[0034] The specified number and the specified level can be fixed values, or can be variable values determined according to, for example, the driving position and driving environment of the vehicle. That is, when the vehicle is driving in an area where the number of feature points is relatively small, if the specified number is set to a large value, there is a concern that the number of segments that may become acquisition targets is too small, so it is preferable to set the specified number to a small value. On the contrary, when the vehicle is driving in an area where the number of feature points is relatively large, if the specified number is set to a small value, there is a concern that the number of segments that may become acquisition targets is too large, so it is preferable to set the specified number to a large value. The same applies to the specified level. For example, in an environment where the detection environment is relatively poor due to the influence of climate or the like, if the specified level is set to a high level, there is a concern that the number of segments that may become acquisition targets is too small, so it is preferable to set the specified level to a low level. On the contrary, in an environment where the detection environment is relatively good, if the specified level is set to a low level, there is a concern that the number of segments that may become acquisition targets is too large, so it is preferable to set the specified level to a high level.

[0035] The form conversion unit 14b reads the reference map stored in the reference map storage unit 16e, converts the data form of the read reference map, and stores the reference map after converting the data form in the reference map storage unit 16f. The form conversion unit 14b reads the input map stored in the input map storage unit 16b, converts the data form of the read input map, and stores the input map after converting the data form in the input map storage unit 16c. The form conversion unit 14b converts the data forms of the reference map and the input map so that the data forms of the reference map and the input map are consistent.

[0036] The feature quantity calculation unit 14c calculates the feature quantities of the feature points. The feature quantities of the feature points are the type, size, position of the feature points, the positional relationship with surrounding ground objects, etc. As Figure 3 shown, the integrated feature point generation unit 14d generates integrated feature points by integrating multiple feature points in the reference map and generates integrated feature points by integrating multiple feature points in the input map. The conditions for integrating multiple feature points are: within the integrated group boundary, for example, (a) the distance between feature points is 10.0 meters or less, (b) the types of feature points are the same, (c) the size difference in the height direction is within 1.0 meter, (d) the size difference in the width direction is within 1.0 meter, (e) the azimuth difference of the normal line is within 45.0 degrees, etc. The integrated feature point generation unit 14d generates integrated feature points when all of these (a) to (e) conditions are satisfied. In Figure 3 the example shown, since the feature points A1 to A3 in the reference map satisfy all of the conditions (a) to (e), the integrated feature point generation unit 14d integrates the feature points A1 to A3 to generate integrated feature points, and since the feature points X1 to X3 in the input map satisfy all of the conditions (a) to (e), the integrated feature point generation unit 14d integrates the feature points X1 to X3 to generate integrated feature points.

[0037] If integrated feature points are generated by the integrated feature point generation unit 14d in the reference map and the input map, the integrated feature point matching unit 14e matches the integrated feature points between the reference map and the input map. The integrated feature point matching unit 14e determines: (f) the number of feature points constituting the integrated feature points is the same, (g) the distance between the centroids is 5.0 meters or less, (h) the types of the integrated feature points are the same, (i) the size difference in the height direction is within 1.0 meter, (j) the size difference in the width direction is within 1.0 meter, (k) the azimuth difference of the normal line is within 45.0 degrees, etc., to match the integrated feature points.

[0038] The feature point matching unit 14f determines whether the matching of the integrated feature points performed by the integrated feature point matching unit 14e is successful. As Figure 4As shown, if the integrated feature points that integrate the feature points A1 to A3 of the reference map and the integrated feature points that integrate the feature points X1 to X3 of the input map satisfy all the conditions (f) to (k), the feature point matching unit 14f determines that the matching of the integrated feature points is successful.

[0039] Here, as Figure 5 shown, when signs P1 to P5 are densely arranged on the road in the real world, if the freshness is different or the vehicle-mounted camera 11 generates blind spots, there will be a situation where the integrated feature points of the input map generated based on the detection data are different from the integrated feature points of the reference map generated based on the signs P1 to P5 in the real world. As Figure 6 shown, there is a situation where the signs P1 to P5 in the real world are normally recognized in the input map A, but for example, in the input map B, the signs P3 and P4 among the signs P1 to P5 in the real world are recognized as one sign P11, and in the input map C, the sign P5 among the signs P1 to P5 in the real world is not recognized.

[0040] In this case, if the integrated feature points that integrate the feature points corresponding to the signs P1 to P5 in the real world in the reference map and the integrated feature points that integrate the feature points in the input map A are matched, the feature point matching unit 14f determines that the matching of the integrated feature points is successful. On the other hand, if the integrated feature points that integrate the feature points corresponding to the signs P1 to P5 in the real world in the reference map and the integrated feature points that integrate the feature points in the input maps B and C are matched, the feature point matching unit 14f determines that the matching of the integrated feature points fails.

[0041] The feature point matching unit 14f determines whether there are integrated feature points with matching failures. If it is determined that there are integrated feature points with matching failures, the individual feature points with matching failures of the integrated feature points are used as objects, and the individual feature points are matched between the reference map and the input map. In addition, the feature point matching unit 14f determines whether there are individual feature points that deviate from the object for generating the integrated feature points. If it is determined that there are individual feature points that deviate from the object for generating the integrated feature points, the individual feature points that deviate from the object for generating the integrated feature points are used as objects, and the individual feature points are matched between the reference map and the input map. The feature point matching unit 14f determines: (l) the distance between feature points is 5.0 meters or less, (m) the types of feature points are the same, (n) the size difference in the height direction is within 1.0 meter, (o) the size difference in the width direction is within 1.0 meter, etc., to match the feature points.

[0042] The map processing unit 14g corrects the position of the input map based on the reference map, using the matching results of the integrated feature points from the integrated feature point matching unit 14e and the matching results of the individual feature points from the feature point matching unit 14f. That is, the map processing unit 14g overlaps the reference map and the input map to correct the position of the input map, so that the feature points included in the reference map and the feature points included in the input map overlap.

[0043] If the differential detection unit 14h determines that the positions of at least four feature points are consistent between the reference map and the input map, it determines that the position correction of the input map is successful and detects the difference between the reference map and the input map. In this case, the differential detection unit 14h reflects the static information and dynamic information as differences into the reference map. The static information includes feature point information related to feature points, zone line information related to zone lines, location information of locations, etc. The feature point information includes position coordinates indicating the position of the feature point, ID for identifying the feature point, size of the feature point, shape of the feature point, color of the feature point, type of the feature point, etc. The zone line information includes position coordinates indicating the position of the zone line, ID for identifying the zone line, types of dotted lines and solid lines, etc. The location information of locations includes GPS coordinates of locations on the road, etc. The dynamic information includes vehicle information related to vehicles on the road, such as vehicle speed values, turn signal operation information, lane crossing, steering angle values, yaw rate values, GPS coordinates, etc. If the differential between the reference map and the input map is detected by the differential detection unit 14h, the differential reflection unit 14i reflects the detected differential into the reference map to update the reference map.

[0044] Next, refer to Figures 7 to 9 to explain the functions of the above structure.

[0045] In the server 3, when the control unit 14 starts the position correction process of the input map, it reads out the reference map stored in the reference map storage unit 16e, reads out the input map stored in the input map storage unit 16b, and converts the data formats of the read reference map and input map to make the data formats consistent (S1). The control unit 14 stores the reference map with the converted data format in the reference map storage unit 16f, and stores the input map with the converted data format in the input map storage unit 16c (S2).

[0046] The control unit 14 moves to the feature point matching process (S3). When the control unit 14 starts the feature point matching process, it calculates the feature amounts of the feature points included in the reference map and the input map (S11, equivalent to the feature amount calculation step). The control unit 14 integrates multiple feature points in the reference map and the input map to generate integrated feature points (S12, equivalent to the integrated feature point generation step), and matches the integrated feature points between the reference map and the input map (S13, equivalent to the integrated feature point matching step).

[0047] The control unit 14 determines whether there are integrated feature points with matching failures (S14). If there are integrated feature points with matching failures (S14: Yes), the individual feature points with matching failures of the integrated feature points are targeted, and individual feature points are matched between the reference map and the input map (S15). The control unit 14 determines whether there are individual feature points that deviate from the object for generating integrated feature points (S16). If it is determined that there are individual feature points that deviate from the object for generating integrated feature points (S16: Yes), the individual feature points that deviate from the object for generating integrated feature points are targeted, and individual feature points are matched between the reference map and the input map (S17).

[0048] The control unit 14 excludes the integrated feature points and individual feature points with the possibility of false matching from the matching results of the integrated feature points and the matching results of the individual feature points (S18), and ends the feature point matching process.

[0049] As Figure 9 shown, if the integrated feature points with the possibility of false matching are excluded, the control unit 14 generates integrated feature points A to C in the reference map and integrated feature points W to Z in the input map. If the input map deviates from the reference map by the azimuth angle θ, and when there are integrated feature points Z and W as candidates for matching with the integrated feature point C in the reference map, if the angular differences between the AB vector and the XY vector, the BC vector and the YZ vector, and the AC vector and the XZ vector are all equal to the azimuth angle θ, and the angular differences between the BC vector and the YW vector and the AC vector and the XW vector are not equal to the azimuth angle θ, then the integrated feature point W with the possibility of false matching is excluded. The control unit 14 performs the same process as in the case of excluding the above integrated feature points when excluding the individual feature points with the possibility of false matching.

[0050] If the control unit 14 ends the feature point matching process, it calculates the offset value between the reference map and the input map (S4). The control unit 14 corrects the input map based on the calculated offset value (S5, equivalent to the map processing step), stores the corrected input map in the input map storage unit 16d (S6), and ends the position correction process of the input map. After that, the control unit 14 detects the difference between the reference map and the input map and reflects the detected difference in the reference map to update the reference map.

[0051] In addition, the above has described the case where in the server 3, the feature amounts of the feature points are calculated and the feature points are integrated to generate integrated feature points. However, it is also possible to calculate the feature amounts of the feature points in the vehicle-mounted device 2 and send the calculation results to the server 3, or to integrate the feature points and send the integration results to the server 3. That is, the functions can be shared between the server 3 and the vehicle-mounted device 2 in any way.

[0052] As described above, according to the present embodiment, the following effects can be obtained.

[0053] In the server 3, by integrating a plurality of feature points to generate integrated feature points and matching the integrated feature points between the reference map and the input map, the data amount when matching the feature points can be appropriately reduced. By matching the integrated feature points between the reference map and the input map, and then matching the individual feature points between the reference map and the input map, and processing the map based on the matching results of the integrated feature points and the matching results of the individual feature points, the feature points shared between the reference map and the input map can be appropriately determined. Thus, the data amount when matching the feature points can be appropriately reduced, and the feature points shared between the reference map and the input map can be appropriately determined, and the position of the input map can be appropriately corrected.

[0054] In the server 3, taking the individual feature points where the matching of the integrated feature points fails as the object, the individual feature points are matched between the reference map and the input map. By matching the individual feature points where the matching of the integrated feature points fails, the feature points shared between the reference map and the input map can be increased, and the shared feature points can be easily determined.

[0055] In the server 3, taking the individual feature points deviating from the object for generating the integrated feature points as the object, the individual feature points are matched between multiple maps. By matching the individual feature points deviating from the object for generating the integrated feature points, the feature points shared between the reference map and the input map can be increased, and the shared feature points can be easily determined.

[0056] This disclosure has been described based on the embodiments, but it should be understood that it is not limited to these embodiments and configurations. This disclosure also includes various modification examples and modifications within the equivalent scope. Among them, various combinations and methods, further including only one element, one or more, or other combinations and methods with one or less of them, are also included in the scope and concept of this disclosure.

[0057] The control unit and method described in the present disclosure can also be implemented by a dedicated computer, which is provided by a processor and a memory configured to execute one or more functions embodied by a computer program. Alternatively, the control unit and method described in the present disclosure can also be implemented by a dedicated computer provided by configuring a processor with one or more dedicated hardware logic circuits. Alternatively, the control unit and method described in the present disclosure can also be implemented by one or more dedicated computers, which are composed of a combination of a processor programmed to execute one or more functions, a memory, and a processor composed of one or more hardware logic circuits. In addition, the computer program can also be stored as instructions executed by a computer in a computer-readable non-transitory tangible recording medium.

[0058] Illustrated is a structure in the server 3 in which a segment not including a specified number or more of feature points and a segment not including a specified number or more of feature points with a detection level equal to or higher than a specified level are not acquisition targets. However, a condition for sending detection data including a segment to the server 3 can also be set in the in-vehicle device 2. That is, illustrated is a structure in the in-vehicle device 2 in which, for example, the detection data is sent to the server 3 every time a specified time elapses or every time the traveling distance of the vehicle reaches a specified distance. However, it can also be a structure in which the number of detected feature points included in the segment is determined, and the detection data is sent to the server 3 only when the number of detected feature points is equal to or more than a specified number. That is, for example, there may be a case where the number of detected feature points is not equal to or more than a specified number due to the presence of a vehicle in front. In a case where it is assumed that even if the detection data of a segment in which the number of detected feature points is not equal to or more than a specified number is sent to the server 3, the server 3 does not use the detection data as a processing target and discards it, the detection data is not sent to the server 3. By not sending unnecessary detection data to the server 3 from the in-vehicle device 2, the load of data communication can be reduced.

Claims

1. A map processing system, comprising: A feature quantity calculation unit that calculates the feature quantity of feature points included in a map; An integrated feature point generation unit that generates integrated feature points by integrating multiple feature points; An integrated feature point matching unit that matches the above-mentioned integrated feature points between multiple maps; A feature point matching unit that matches individual feature points between multiple maps; and A map processing unit that processes a map based on the matching result of the above-mentioned integrated feature points and the matching result of the above-mentioned individual feature points.

2. The map processing system according to claim 1, wherein, The above-mentioned feature point matching unit uses the individual feature points that failed to match the integrated feature points as objects, and matches the individual feature points among multiple maps.

3. The map processing system according to claim 1, wherein, The above-mentioned feature point matching unit uses the individual feature points that deviate from the object for generating the integrated feature points as objects, and matches the individual feature points among multiple maps.

4. The map processing system according to claim 2, wherein, The above-mentioned feature point matching unit uses the individual feature points that deviate from the object for generating the integrated feature points as objects, and matches the individual feature points among multiple maps.

5. The map processing system according to any one of claims 1 to 4, wherein, The above-mentioned feature quantity calculation unit calculates at least any one of the type, size, position of the feature point, and the positional relationship with surrounding ground objects as the feature quantity of the feature point.

6. The map processing system according to any one of claims 1 to 4, wherein, The above-mentioned integrated feature point matching unit matches the above-mentioned integrated feature points based on at least any one of the number of feature points constituting the integrated feature points, the distance between the centroids, the type of the integrated feature points, the size difference in the height direction, the size difference in the width direction, and the azimuth difference of the normal line.

7. The map processing system according to any one of claims 1 to 4, wherein, The above-mentioned feature point matching unit matches the above-mentioned feature points based on at least any one of the distance between features, the type of the feature point, the size difference in the height direction, and the size difference in the width direction.

8. The map processing system according to any one of claims 1 to 4, wherein, The above-mentioned integrated feature point matching unit matches the above-mentioned integrated feature points among multiple input maps. The above-mentioned feature point matching unit matches the above-mentioned individual feature points among multiple input maps. The above-mentioned map processing unit integrates multiple input maps to generate an integrated input map.

9. The map processing system according to any one of claims 1 to 4, wherein, The above-mentioned integrated feature point matching unit matches the above-mentioned integrated feature points between the input map and the reference map. The above-mentioned feature point matching unit matches the above-mentioned individual feature points between the input map and the reference map. The above-mentioned map processing unit corrects the position of the input map based on the reference map.

10. A computer-readable recording medium that stores a computer program, When the program is executed by at least one processor included in a map processing device, the following steps are executed: A feature quantity calculation step that calculates the feature quantity of feature points included in a map; An integrated feature point generation step of integrating multiple feature points to generate integrated feature points; An integrated feature point matching step of matching the above-mentioned integrated feature points among multiple maps; A feature point matching step of matching individual feature points among multiple maps; And A map processing step of processing the map based on the matching result of the above-mentioned integrated feature points and the matching result of the above-mentioned individual feature points.

11. A computer program product, which is a computer program product containing a computer program, When the computer program is executed by a processor, the following steps are implemented: Calculate the feature quantities of the feature points included in the map; Integrate multiple feature points to generate an integrated feature point; Match the above integrated feature points among multiple maps; Match individual feature points among multiple maps; And Process the map based on the matching result of the above-mentioned integrated feature points and the matching result of the above-mentioned individual feature points.

Images