Feature recognition device, feature recognition method, program, and storage medium

Abstract

To provide a feature recognition device capable of efficiently recognizing features from information acquired by an external sensor.SOLUTION: A feature recognition device provided herein is configured to: acquire external information from an external detection device provided on a vehicle and acquire feature location information indicative of a location of a feature near the vehicle; extract prediction information representing information belonging to the external information predicted to contain information of the feature; and recognize the feature based on the prediction information.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a technique for recognizing ground objects.

Background Art

[0002] Conventionally, as a technique for estimating a vehicle position, for example, Patent Document 1 is known. The method of Patent Document 1 detects the positions of a plurality of landmarks with respect to a vehicle based on the distances and directions of the plurality of landmarks with respect to the vehicle, and estimates the current position of the vehicle based on the collation result between the positions of at least one pair of landmarks among the detected plurality of landmarks and the positions of the landmarks on the map.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In such a technique, when detecting the position of a landmark from the information obtained by an external sensor, it is common to perform a process of extracting and recognizing the target landmark from the entire measured information, and there is room for improvement in terms of efficiency.

[0005] Examples of the problems to be solved by the present invention include the above. An object of the present invention is to provide a ground object recognition device capable of efficiently recognizing ground objects from information acquired by an external sensor.

Means for Solving the Problems

[0006] The invention according to the claim is a ground object recognition device, comprising: a first acquisition unit that acquires external information generated by a sensor disposed on a moving body; a second acquisition unit that acquires ground object position information indicating the position of a ground object existing around the moving body and attribute information including type information indicating the type of the ground object; and a recognition unit that recognizes the ground object by a recognition method for recognizing the ground object from a ground object prediction range that is a range in the external information where the ground object is predicted to exist and that is determined based on the ground object position information, and that is determined based on the type information.

[0007] The invention according to the claim is A method for recognizing features performed by a computer, a first acquisition step of acquiring external information generated by a sensor disposed on a moving body; a second acquisition step of acquiring ground object position information indicating the position of a ground object existing around the moving body and attribute information including type information indicating the type of the ground object; and a recognition step of recognizing the ground object by a recognition method for recognizing the ground object from a ground object prediction range that is a range in the external information where the ground object is predicted to exist and that is determined based on the ground object position information, and that is determined based on the type information.

[0008] A program executed by a ground object recognition device including a computer causes the computer to function as: a first acquisition unit that acquires external information generated by a sensor disposed on a moving body; a second acquisition unit that acquires ground object position information indicating the position of a ground object existing around the moving body and attribute information including type information indicating the type of the ground object; and a recognition unit that recognizes the ground object by a recognition method for recognizing the ground object from a ground object prediction range that is a range in the external information where the ground object is predicted to exist and that is determined based on the ground object position information, and that is determined based on the type information.

Brief Description of the Drawings

[0009] [Figure 1] It is a block diagram showing the configuration of the own vehicle position estimation device according to the embodiment. [Figure 2] It is a diagram for explaining a method of determining a landmark prediction range. [Figure 3] An example of landmark extraction processing is shown. [Figure 4] This diagram explains how to estimate the vehicle's position. [Figure 5] This is a flowchart of the vehicle position estimation process. [Modes for carrying out the invention]

[0010] In a preferred embodiment of the present invention, the feature recognition device includes: a first acquisition unit that acquires external information output by an external detection device placed on a moving body; a second acquisition unit that acquires feature location information indicating the location of features present around the moving body; and a recognition unit that extracts prediction information, which is information from the external information that is predicted to include information indicating the features, based on the feature location information, and recognizes the features based on the prediction information.

[0011] The above-described feature recognition device acquires external information from an external detection device placed on the moving object, as well as feature location information indicating the locations of features in the vicinity of the moving object. Based on the feature location information, it extracts predictive information, which is information from the external information that is expected to contain information indicating features, and recognizes features based on this predictive information. This means that features only need to be recognized based on the predictive information that is expected to contain information indicating features, and it is not necessary to perform feature recognition processing on all external information, thus enabling efficient feature recognition.

[0012] In one embodiment of the above-described feature recognition device, the second acquisition unit further acquires attribute information indicating the attributes of the feature, and the recognition unit recognizes the feature using a recognition method determined based on the attribute information. In this embodiment, the recognition method is determined based on attribute information indicating the attributes of the feature, and the feature is recognized.

[0013] In another embodiment of the feature recognition device described above, the second acquisition unit acquires first feature location information indicating the location of the first feature, first attribute information indicating the attributes of the first feature, second feature location information indicating the location of a second feature different from the first feature, and second attribute information indicating the attributes of the second feature. The recognition unit extracts first prediction information from the external information that is expected to include information indicating the first feature based on the first feature location information, recognizes the first feature using a first recognition method determined based on the first attribute information based on the first prediction information, extracts second prediction information from the external information that is expected to include information indicating the second feature based on the second feature location information, and recognizes the second feature using a second recognition method determined based on the second attribute information based on the second prediction information. In this embodiment, the first recognition method and the second recognition method are determined based on the attribute information indicating the attributes of the feature, and the first and second features are recognized.

[0014] In one embodiment of the above-described feature recognition device, the recognition unit recognizes the feature using a different recognition method for each of the feature's attributes. This makes it possible to recognize the feature using a recognition method suitable for the feature's attributes.

[0015] In another preferred embodiment of the present invention, a feature recognition method performed by a feature recognition device includes: a first acquisition step of acquiring ambient information output by an ambient detection device placed on a moving body; a second acquisition step of acquiring feature location information indicating the location of features in the vicinity of the moving body; and a recognition step of extracting predictive information, which is information from the ambient information that is expected to include information indicating the features, based on the feature location information, and recognizing the features based on the predictive information. With this method as well, it is sufficient to recognize features based on predictive information that is expected to include information indicating the features from the ambient information, and it is not necessary to perform feature recognition processing on all ambient information, thus enabling efficient feature recognition.

[0016] In another preferred embodiment of the present invention, a program executed by a feature recognition device equipped with a computer causes the computer to function as follows: a first acquisition unit that acquires external information output by an external detection device placed on a moving body; a second acquisition unit that acquires feature location information indicating the location of features present around the moving body; and a recognition unit that extracts prediction information, which is information from the external information that is expected to include information indicating the features, based on the feature location information, and recognizes the features based on the prediction information. By executing this program on the computer, the above-described feature recognition device can be realized. This program can be stored and handled on a storage medium. [Examples]

[0017] Hereinafter, preferred embodiments of the present invention will be described with reference to the drawings. [composition] Figure 1 shows a schematic configuration of a vehicle position estimation device to which the feature recognition device of the present invention is applied. The vehicle position estimation device 10 is mounted on a vehicle and is configured to communicate with a server 7, such as a cloud server, via wireless communication. The server 7 is connected to a database 8, which stores an advanced map. The vehicle position estimation device 10 communicates with the server 7 and downloads landmark information regarding landmarks around the vehicle's position.

[0018] The advanced maps stored in Database 8 store landmark information for each landmark. Here, landmark information includes a landmark map location indicating the location of the landmark on the map, and landmark attributes indicating the type and characteristics of the landmark, for each landmark ID that identifies the landmark. Landmark attributes are prepared according to the type and characteristics of the landmark and basically include the type of landmark and characteristic information. For example, if the landmark is a sign, the landmark attribute includes "sign" as the type of landmark and the shape (circular, triangular, square, etc.) and size of the sign, as well as the reflectivity of the sign, as characteristic information. If the landmark is a utility pole, the landmark attribute includes "utility pole" as the type of landmark and the shape (curvature of the cross-section, radius, etc.) and size of the utility pole, as characteristic information. Other examples of landmarks include road markers, traffic lights, and various buildings.

[0019] On the other hand, the vehicle position estimation device 10 includes an internal sensor 11, an external sensor 12, a vehicle position prediction unit 13, a measurement information acquisition unit 14, a communication unit 15, a landmark information acquisition unit 16, a landmark prediction unit 17, an extraction method selection unit 18, a landmark extraction unit 19, a correspondence unit 20, and a vehicle position estimation unit 21. In practice, the vehicle position prediction unit 13, the measurement information acquisition unit 14, the landmark information acquisition unit 16, the landmark prediction unit 17, the extraction method selection unit 18, the landmark extraction unit 19, the correspondence unit 20, and the vehicle position estimation unit 21 are implemented by a computer such as a CPU executing a pre-prepared program.

[0020] The internal sensor 11 determines the vehicle's position as a GNSS (Global Navigation Satellite System) / IMU (Inertia Measurement Unit) combined navigation system and includes a satellite positioning sensor (GPS), a gyro sensor, a vehicle speed sensor, etc. The vehicle position prediction unit 13 predicts the vehicle's position using GNSS / IMU combined navigation based on the output of the internal sensor 11 and supplies the predicted vehicle position to the landmark prediction unit 17.

[0021] On the other hand, the external sensor 12 is a sensor that detects objects around the vehicle and includes a stereo camera, Lidar (Light Detection and Ranging), etc. The measurement information acquisition unit 14 acquires measurement information from the external sensor 12 and supplies it to the landmark extraction unit 19.

[0022] The communication unit 15 is a communication unit for wireless communication with the server 7. The landmark information acquisition unit 16 receives landmark information about landmarks present around the vehicle from the server 7 via the communication unit 15 and supplies it to the landmark prediction unit 17. The landmark information acquisition unit 16 also supplies the landmark map locations included in the landmark information to the mapping unit 20.

[0023] The landmark prediction unit 17 determines a landmark prediction range, which is the area where a landmark is predicted to exist, based on the landmark map location included in the landmark information and the predicted vehicle position obtained from the vehicle position prediction unit 13, and supplies it to the landmark extraction unit 19. The landmark prediction unit 17 also supplies the landmark attributes included in the landmark information to the extraction method selection unit 18.

[0024] The extraction method selection unit 18 determines the feature extraction method that the landmark extraction unit 19 will execute to extract the landmark, based on the landmark attributes. As mentioned above, landmarks include signs, utility poles, and other types, and the method for extracting a landmark differs depending on the type of landmark. That is, the feature extraction method executed by the landmark extraction unit 19 differs depending on the type of landmark. Specifically, the landmark extraction unit 19 extracts feature objects as landmarks that have the features indicated by the feature information included in the landmark attributes. Therefore, the extraction method selection unit 18 selects the feature extraction method corresponding to the landmark to be extracted based on the landmark attributes of that landmark and instructs the landmark extraction unit 19 to perform the extraction.

[0025] The landmark extraction unit 19 extracts landmarks based on the landmark prediction range supplied by the landmark prediction unit 17 and the measurement information supplied by the measurement information acquisition unit 14. Specifically, the landmark extraction unit 19 extracts features from the measurement information included in the landmark prediction range and uses these as landmarks. In this process, the landmark extraction unit 19 extracts landmarks using the feature extraction method determined by the extraction method selection unit 18, that is, the feature extraction method corresponding to the landmark attributes. The landmark extraction unit 19 then outputs the landmark measurement position of the extracted landmark to the mapping unit 20.

[0026] The mapping unit 20 stores the landmark measurement location obtained from the landmark extraction unit 19 and the landmark map location obtained from the landmark information acquisition unit 16, associating them with the landmark ID. As a result, for each landmark ID, information (hereinafter referred to as "correspondence information") is generated in which the landmark map location and the landmark measurement location are associated.

[0027] The vehicle position estimation unit 21 then estimates the vehicle's position and azimuth angle for at least two landmarks, using the landmark map position and landmark measurement position included in the corresponding information.

[0028] In the above configuration, the external sensor 12 is an example of the external detection device of the present invention, the measurement information acquisition unit 14 is an example of the first acquisition unit of the present invention, the landmark information acquisition unit 16 is an example of the second acquisition unit of the present invention, and the landmark extraction unit 19 is an example of the recognition unit of the present invention. Furthermore, the landmark map location corresponds to the feature location information of the present invention, the measurement information corresponds to the external information of the present invention, and the measurement information of the landmark prediction range corresponds to the prediction information of the present invention.

[0029] [Determining the Landmark Prediction Range] Next, the method for determining the landmark prediction range performed by the landmark prediction unit 17 will be described in detail. FIG. 2 is a diagram for explaining the method for determining the landmark prediction range. As shown in the figure, in the map coordinate system (X m , Y m ), the vehicle 5 exists, and a vehicle coordinate system (X v , Y v ) is defined based on the position of the vehicle 5. Specifically, the traveling direction of the vehicle 5 is set as the X v axis of the vehicle coordinate system, and the direction perpendicular thereto is set as the Y v axis of the vehicle coordinate system.

[0030] There are landmarks L1 and L2 around the vehicle 5. In this embodiment, it is assumed that the landmark L1 is a sign and the landmark L2 is a utility pole. The positions of the landmarks L1 and L2 in the map coordinate system, that is, the landmark map positions, are included in the enhanced map as described above and are supplied from the landmark information acquisition unit 16. In FIG. 2, the landmark map position of the landmark L1 is P LM1 (mx m1 , my m1 ), and the landmark map position of the landmark L2 is P LM2 (mx m2 , my m2 ). On the other hand, the predicted own vehicle position P' VM (x' m , y' m ) is supplied from the own vehicle position prediction unit 13.

[0031] The landmark prediction unit 17 calculates the landmark prediction position P' VM in the vehicle coordinate system based on the predicted own vehicle position P' LM1 and the landmark map position P of the landmark L1 LV1 (l'x v1 , l'y v1 ), and determines the landmark prediction range R LV1 based on the landmark prediction position P' L1 . Similarly, the landmark prediction unit 17 calculates the landmark prediction position P' VM in the vehicle coordinate system based on the predicted own vehicle position P' LM2Based on this, the predicted landmark position P' in the vehicle coordinate system. LV2 (l'x v2 ,l'y v2 ) calculates the predicted landmark position P' LV2 Based on the landmark prediction range R L2 To decide.

[0032] The landmark prediction range R indicates the range in which landmark L is predicted to exist. The predicted vehicle position P' is obtained using the internal sensor 11. VM Since this includes a certain degree of error, the landmark prediction unit 17 determines the landmark prediction range R taking this error into consideration. For example, the landmark prediction unit 17 determines the landmark prediction position P' LV A circle centered at a predetermined distance is determined as the landmark prediction range R.

[0033] By determining the landmark prediction range R in this way, the landmark extraction unit 19 only needs to extract landmarks based on the measurement information obtained by the external sensor 12 that belongs to the landmark prediction range R. Generally, external sensors such as Lidar take measurements over a wide range, such as the entire circumference (360°) of the vehicle's position or 270° excluding the area behind the vehicle, generating measurement information over a wide range. In this case, if landmark extraction processing were to be performed on all of the obtained wide-range measurement information to extract landmarks, the amount of computation would be enormous. In contrast, in this embodiment, the area where landmarks are predicted to exist is determined as the landmark prediction range R based on the predicted vehicle position obtained using the internal sensor 11, and the landmark extraction processing is performed only on the measurement information belonging to that range, thereby significantly reducing the amount of computation and enabling efficient landmark detection.

[0034] In actual processing, the external sensor 12 performs measurements over a wide area as described above and outputs measurement information over a wide area. The landmark extraction unit 19 then extracts only the measurement information within the landmark prediction range R and uses it for landmark extraction processing. Alternatively, the external sensor 12 may be controlled to measure only within the landmark prediction range R.

[0035] [Landmark extraction process] Next, the landmark extraction process will be explained. Figure 3 shows an example of the landmark extraction process. In this embodiment, the landmark is assumed to be a sign. In this case, the landmark attribute included in the landmark information acquired by the landmark information acquisition unit 16 from the server 7 includes "sign" as the landmark type, and the extraction method selection unit 18 selects a feature extraction method corresponding to the sign based on this information and instructs the landmark extraction unit 19.

[0036] The landmark extraction unit 19 extracts landmarks based on the measurement information acquired from the measurement information acquisition unit 14. The Lidar, acting as an external sensor 12, emits light pulses into the surroundings and receives reflected light pulses from surrounding objects to generate point cloud data. The point cloud data includes the positions (3D positions) and reflection intensity data of objects around the vehicle. The measurement information acquisition unit 14 outputs this point cloud data as measurement information to the landmark extraction unit 19. The spacing of the point cloud data generated by the Lidar depends on the distance and direction from the Lidar to the measurement target, and the angular resolution of the Lidar.

[0037] As mentioned above, when a landmark is a sign, its landmark attributes include "sign" as the landmark type and shape (size) information and reflectance as feature information. Therefore, the landmark extraction unit 19 extracts feature objects based on the shape information and reflectance. Specifically, the landmark extraction unit 19 extracts circular point cloud data corresponding to the sign from the point cloud data acquired from the measurement information acquisition unit 14, based on the sign's shape information and reflectance, as shown in Figure 3. The landmark extraction unit 19 then calculates the centroid position (lx, ly, lz) of the extracted point cloud data of the sign and outputs this to the mapping unit 20 as the landmark measurement position.

[0038] The mapping unit 20 associates the landmark measurement position obtained from the landmark extraction unit 19 with the landmark map position obtained from the landmark information acquisition unit 16. Specifically, the mapping unit 20 generates and stores correspondence information by mutually associating the landmark ID, landmark measurement position, and landmark map position corresponding to that landmark. In this way, the landmark measurement position and the landmark map position are associated with the landmark extracted by the landmark extraction unit 19. In this embodiment, since the corresponding landmark map position is a position in a two-dimensional map coordinate system, the mapping unit 20 uses the two-dimensional position (lx, ly) from the calculated three-dimensional centroid position (lx, ly, lz) as the landmark measurement position. The correspondence information thus generated is used for self-position estimation by the self-position estimation unit 21.

[0039] In the example in Figure 3, the landmark was a sign, but landmark extraction can be performed similarly for other types of landmarks. However, the method of extracting features differs depending on the type of landmark. For example, if the landmark is a utility pole, the landmark attribute includes information about the shape of the utility pole (such as the arc shape of the cross-section, curvature, and radius) and its size as feature information. Therefore, the landmark extraction unit 19 extracts a feature corresponding to the utility pole from the measurement information based on the shape and size information of the utility pole, and outputs its center position as the landmark measurement position. Also, if the landmark is a road marker, the landmark attribute includes information about the shape and reflectivity of the road marker as feature information. Therefore, the landmark extraction unit 19 extracts a feature corresponding to the road marker from the measurement information based on the shape information and reflectivity, and outputs its center position as the landmark measurement position. Even if the landmark is another object such as a traffic light, the landmark extraction unit 19 can extract the landmark based on the type and feature information of the landmark, and output a predetermined position such as its center position as the landmark measurement position.

[0040] Thus, in this embodiment, the landmark information included in the advanced map includes attribute information for each landmark, and when extracting landmarks from measurement information by the external sensor 12, a feature extraction method corresponding to the attributes of the target landmark is used. This makes landmark extraction efficient. In other words, if the attributes of the landmark are not used as in this embodiment, it is unknown what the landmark to be extracted is, so as a feature extraction method, it is necessary to sequentially perform extraction methods suitable for all conceivable landmarks, such as a method suitable for signs, a method suitable for utility poles, a method suitable for road markers, etc., and extract one of the landmarks. In contrast, if the attributes of the landmark are known in advance, as in this embodiment, it is only necessary to perform the feature extraction method suitable for that landmark. For example, in the example in Figure 2, it is known from the landmark attributes that landmark L1 is a sign and landmark L2 is a utility pole. Therefore, the landmark prediction range R L1For this, a feature extraction process suitable for marking is performed, and the landmark prediction range R L2 For this, a feature extraction process suitable for utility poles should be performed. In this way, the processing load for landmark extraction can be reduced, and false detections and missed detections can be prevented.

[0041] [Vehicle position estimation] Next, the vehicle position estimation by the vehicle position estimation unit 21 will be explained. The vehicle position estimation unit 21 estimates the vehicle's position and azimuth angle using the correspondence information of two landmarks generated by the correspondence unit 20. Hereinafter, the vehicle position obtained by the vehicle position estimation will be called the "estimated vehicle position," and the azimuth angle obtained by the vehicle position estimation will be called the "estimated vehicle azimuth angle."

[0042] Figure 4 shows an example of vehicle position estimation. Map coordinate system (X m ,Y m Vehicle 5 is located on ), and the vehicle coordinate system (X) is based on the position of vehicle 5. v ,Y v ) is defined. The estimated position of vehicle 5 is P VM (x m ,y m ) is shown, and the estimated vehicle azimuth angle is Ψ m This is shown.

[0043] The vehicle position estimation unit 21 obtains correspondence information for two landmarks L1 and L2 from the correspondence unit 20. Specifically, the vehicle position estimation unit 21 obtains the landmark map position P for landmark L1. LM1 (mx m1 ,my m1 ) and landmark measurement position P LV1 (lx v1 ,ly v1 ) obtain the landmark map location P for landmark L2. LM2 (mx m2 ,my m2 ) and landmark measurement position P LV2 (lx v2 ,ly v2 ) obtain.

[0044] Using these landmark map locations and landmark measurement locations, the estimated vehicle azimuth angle Ψ can be calculated. m The following equation can be obtained for this.

[0045]

number

[0046]

number

[0047] [Vehicle position estimation process] Next, we will explain the processing flow by the vehicle position estimation device 10. Figure 5 is a flowchart of the processing by the vehicle position estimation device 10. This processing is realized by a computer such as a CPU executing a pre-prepared program and functioning as each component shown in Figure 1.

[0048] First, the vehicle position prediction unit 13 predicts the vehicle position P' based on the output from the internal sensor 11. VM The landmark information acquisition unit 16 then obtains the landmark map location (step S11). Next, the landmark information acquisition unit 16 connects to the server 7 via the communication unit 15 and obtains the landmark information from the advanced map stored in the database 8 (step S12). As mentioned above, the landmark information includes the landmark map location and landmark attributes, and the landmark information acquisition unit 16 supplies the landmark map location to the mapping unit 20. Note that steps S11 and S12 can be performed in any order.

[0049] Next, the landmark prediction unit 16 determines the landmark prediction range R based on the landmark map position included in the landmark information obtained in step S12 and the predicted vehicle position obtained in step S11, and supplies it to the landmark extraction unit 19 (step S13).

[0050] Next, the extraction method selection unit 18 selects a feature extraction method based on the landmark attributes included in the landmark information obtained in step S12 (step S14). Specifically, the extraction method selection unit 18 selects a feature extraction method suitable for the type of landmark indicated by the landmark attributes. For example, if the landmark is a sign, the extraction method selection unit 18 selects a feature extraction method suitable for a sign, as explained with reference to Figure 3, and instructs the landmark extraction unit 19 to do so.

[0051] Meanwhile, the landmark extraction unit 19 acquires measurement information output by the external sensor 12 from the measurement information acquisition unit 14 (step S15), and extracts landmarks within the landmark prediction range R obtained from the landmark prediction unit 17 using the feature extraction method instructed by the extraction method selection unit 18 (step S16). The landmark extraction unit 19 outputs the landmark measurement position as a landmark extraction result to the correspondence unit 20.

[0052] The correspondence unit 20 associates the landmark map location obtained from the landmark information acquisition unit 16 with the landmark measurement location obtained from the landmark extraction unit 19 for each landmark, generates correspondence information, and sends it to the vehicle position estimation unit 21 (step S17). Then, the vehicle position estimation unit 21 uses the correspondence information for the two landmarks to estimate the vehicle position and vehicle azimuth angle in the method described with reference to Figure 5 (step S18). In this way, the estimated vehicle position and estimated vehicle azimuth angle are output. [Explanation of Symbols]

[0053] 5 vehicles 7 Servers 8 Databases 10. Vehicle position estimation device 11. Internal Sensors 12. External sensors 13. Vehicle position prediction unit 14 Measurement Information Acquisition Unit 17 Landmark Prediction Section 18. Extraction Method Selection Section 19. Landmark Extraction Section 21 Vehicle position estimation unit

Claims

1. A first acquisition unit that acquires external information generated by sensors placed on a moving object, A second acquisition unit acquires attribute information including feature location information indicating the location of features present around the moving object, and type information indicating the type of feature. A recognition unit that recognizes a feature from a feature prediction range which is a range in the external information in which the feature is predicted to exist and is determined based on the feature location information, based on a recognition method that recognizes the feature determined based on the type information, A feature recognition device equipped with the following features.

2. The attribute information further includes characteristic information defined according to the type, The feature recognition device according to claim 1, characterized in that the recognition unit recognizes the feature based on the feature information.

3. The feature recognition device according to claim 1, characterized in that the sensor generates external information using light reflected from the feature.

4. The object recognition device according to claim 3, wherein the sensor has an illumination unit that emits the light, and generates external information using the light reflected by the object.

5. A method for recognizing features performed by a computer, A first acquisition step involves acquiring external information generated by sensors placed on a moving object, A second acquisition step involves acquiring attribute information including feature location information indicating the location of features present around the moving body, and type information indicating the type of feature. A recognition step of recognizing a feature by a recognition method that recognizes the feature determined based on type information from a feature prediction range which is a range in the external information in which the feature is predicted to exist and is determined based on the feature location information, A method for recognizing geographic features.

6. The program executed by the computer-equipped feature recognition device is: A first acquisition unit that acquires external information generated by sensors placed on a moving object. A second acquisition unit acquires attribute information including feature location information indicating the location of features present around the moving body, and type information indicating the type of feature. A recognition unit recognizes a feature from a feature prediction range which is the range in which the feature is predicted to exist among the external information and which is determined based on the feature location information, using a recognition method that recognizes the feature determined based on the type information. A program that causes the aforementioned computer to function.

7. A storage medium storing the program described in claim 6.

Images