JP2023111921A - Information processing device - Google Patents

Abstract

To provide an information processing device with which it is possible to generate highly accurate overall point group data on the basis of individual point group data generated utilizing map data.SOLUTION: A collection unit 2 collects individual point group data generated on the basis of imaging information and map data, and a generation unit 3 generates overall point group data on the basis of a plurality of individual point group data. The collection unit 2 acquires attribute information pertaining to the map data and determines a degree of contribution of individual point group data on the basis of the attribute information, and it is thereby possible to raise the degree of contribution of individual point group data based on high- reliability map data and lower the degree of contribution of individual point group data based on low-reliability map data. Thus, it is possible to generate highly accurate overall point group data on the basis of individual point group data generated utilizing the map data.SELECTED DRAWING: Figure 1

Description

The present invention relates to an information processing device.

Conventionally, a method (SLAM: Simultaneous Localization and Mapping) is known in which self-location estimation and environment map creation are performed simultaneously in a mobile object. As one type of SLAM, a method using a video camera instead of a laser device (VSLAM; Visual SLAM) has been proposed (see, for example, Patent Document 1). A VSLAM such as that described in Patent Document 1 attempts to reduce costs by using a video camera.

JP 2014-222550 A

In the VSLAM as described in Patent Document 1, feature points are extracted in each image (frame) captured by a video camera, and self-position estimation and environment map creation are performed based on changes in feature points between the images. conduct. When creating an environmental map in this way, a method of improving accuracy by correcting point cloud data included in the environmental map by referring to existing map data is conceivable. Furthermore, a method of further improving accuracy by collecting and integrating a plurality of point cloud data for a predetermined section is conceivable.

However, when generating each point cloud data, the map data referred to are not always the same. Therefore, if the collected point cloud data contains old map data or point cloud data generated using low-accuracy map data, the accuracy of the integrated point cloud data may decrease. have a nature.

Accordingly, an object of the present invention is to provide an information processing apparatus capable of generating highly accurate comprehensive point cloud data based on individual point cloud data generated using map data.

In order to solve the above-described problems and achieve the object, an information processing apparatus according to claim 1 of the present invention includes a collection unit for collecting individual point cloud data generated based on imaging information and map data; and a generation unit that generates general point cloud data based on the individual point cloud data of, the collection unit acquires attribute information about the map data, and the generation unit includes the plurality of individual point cloud data is determined based on the attribute information to generate the comprehensive point cloud data.

1 is a block diagram showing an outline of an information processing apparatus according to an embodiment of the present invention; FIG.

Embodiments of the present invention will be described below. An information processing apparatus according to an embodiment of the present invention includes a collecting unit that collects individual point cloud data generated based on imaging information and map data, and a total point cloud data that generates comprehensive point cloud data based on a plurality of individual point cloud data. and a generator. The collection unit acquires, for each of the plurality of individual point cloud data, attribute information related to map data used to generate the individual point cloud data. The generation unit determines a degree of contribution based on the attribute information for each of the plurality of individual point cloud data, and generates comprehensive point cloud data.

According to the information processing apparatus of the present embodiment, the collecting unit acquires the attribute information about the map data, and determines the degree of contribution of the individual point cloud data based on the attribute information. The degree of contribution of individual point cloud data based on map data can be increased, and the degree of contribution of individual point cloud data based on map data with low reliability can be decreased. This makes it possible to generate comprehensive point cloud data with high accuracy based on individual point cloud data generated using map data.

The attribute information preferably includes time information about when the map data was last updated or created. At this time, it is preferable that the generation unit increases the degree of contribution of individual point cloud data based on map data that is new at the time of the last update or creation. Map data tends to be more reliable the more recently it was last updated or created. Therefore, if the degree of contribution of individual point cloud data based on map data that is new at the time of the last update or creation is increased, comprehensive point cloud data with high accuracy can be generated.

The attribute information may include the cumulative update count of the map data or the count information about the version number. At this time, it is preferable that the generation unit increases the degree of contribution of individual point cloud data based on map data with a large cumulative number of updates or a large version number. Map data tends to be new at the time of the last update and have a high degree of reliability when the cumulative number of update times is large or when the version number is large. Therefore, by increasing the degree of contribution of individual point cloud data based on map data with a large cumulative number of updates or a large version number, comprehensive point cloud data with high accuracy can be generated.

The attribute information may include definition information about the definition of map data. At this time, the generation unit preferably increases the degree of contribution of individual point cloud data based on map data with high definition. Map data may differ in definition depending on the creator (provider) and the purpose of use. Therefore, by increasing the degree of contribution of individual point cloud data based on high-definition map data, highly accurate comprehensive point cloud data can be generated.

An information processing method according to an embodiment of the present invention includes a collecting step of collecting individual point cloud data generated based on imaging information and map data, and generating comprehensive point cloud data based on a plurality of individual point cloud data. and a generating step. In the collection step, for each of the plurality of individual point cloud data, attribute information relating to the map data used to generate the individual point cloud data is acquired. In the generation step, for each of the plurality of individual point cloud data, the degree of contribution is determined based on the attribute information to generate comprehensive point cloud data. According to this information processing method, attribute information about map data is acquired in the collection process, and the degree of contribution of individual point cloud data is determined based on the attribute information in the generation process. Based on the obtained individual point cloud data, highly accurate comprehensive point cloud data can be generated.

Moreover, it is good also as an information processing program which makes a computer perform the information processing method mentioned above. By doing so, a computer can be used to generate comprehensive point cloud data with high accuracy based on individual point cloud data generated using map data.

Also, the information processing program described above may be stored in a computer-readable recording medium. By doing so, the program can be distributed as a single unit in addition to being incorporated into the device, and version upgrades and the like can be easily performed.

Examples of the present invention will be specifically described below. The information processing apparatus 1 of the present embodiment is installed in, for example, an external server 20 that communicates with a mobile unit 10, and includes a collection unit 2 and a generation unit 3, as shown in FIG. The moving body 10 is, for example, a vehicle, and is equipped with an imaging unit 11, an individual data generation unit 12, a communication unit 13, and a map information storage unit . Although only one mobile object 10 is shown in FIG. 1, the external server 20 may be capable of communicating with a plurality of mobile objects.

The imaging unit 11 is, for example, a video camera, and is arranged to capture an image of the front side of the moving body 10 in the direction of travel. A moving image captured by the imaging unit 11 is composed of a plurality of pieces of image information (frames), and is transmitted to the individual data generation unit 12 . Note that the imaging unit may be capable of continuously capturing still images at predetermined time intervals.

The individual data generation unit 12 acquires image information from the imaging unit 11 and generates individual point cloud data by VSLAM. That is, the individual data generating unit 12 extracts feature points from the image information and generates point cloud data based on changes in the feature points. The point cloud data may be three-dimensional point cloud data, for example. Note that the feature points to be extracted need only be distinguishable from other objects and can be tracked, such as the corners of an object. may be used, or other algorithms may be used.

Further, when the individual data generation unit 12 generates individual point cloud data, the map data stored in the map information storage unit 14 is also used. Furthermore, when the individual data generation unit 12 generates individual point cloud data, information on the imaging position and imaging direction of the imaging unit 11 is also used. That is, for example, current position information obtained by a self-position estimating unit such as a GPS (Global Positioning System) receiving unit, and displacement amount information obtained by an in-vehicle sensor such as a vehicle speed pulse obtaining unit, a gyro sensor, and an acceleration sensor are used. Accordingly, the imaging position and imaging direction of the imaging unit 11 can be specified.

By acquiring the map data and specifying the imaging position and imaging direction of the imaging unit 11, it is possible to determine what kind of object the feature points extracted in each frame and the constituent points constituting the point cloud data correspond to. can be estimated. The individual data generation unit 12 identifies feature points corresponding to, for example, moving objects (other vehicles, pedestrians, etc.) among the plurality of feature points extracted in each frame based on map information and traveling direction information. to remove. Further, when generating individual point cloud data based on a plurality of feature point groups, the individual data generation unit 12 selects features (vegetation, etc.) that can change over time among the constituent points that constitute the individual point cloud data. Corresponding feature points are identified and removed based on map information and traveling direction information. Note that the individual data generation unit 12 may perform only one of the removal of feature points and the removal of constituent points.

When generating the individual point cloud data, the individual data generating unit 12 gives the individual point cloud data attribute information related to the map data to be used as a flag. The attribute information includes time information about the last update time or creation time, count information about the cumulative update count or version number,
and definition information about the definition. Map data tends to be more reliable the more recent it was last updated or created. Further, map data tends to be new at the time of the last update and have a high degree of reliability when the cumulative number of update times is large or when the version number is large.

The communication unit 13 is composed of a circuit, an antenna, and the like for communicating with a network such as the Internet or a public line. group data).

The map information storage unit 14 is composed of, for example, a hard disk or non-volatile memory, and stores existing map data. The map data may include at least information about the shape of roads, and may be a city map, a line map, or an aeronautical map. Each moving object may not have a map information storage unit, and may acquire map data by communicating with a data center or the like.

The collection unit 2 of the information processing device 1 acquires the individual point cloud data generated by the individual data generation unit 12 via the communication unit 21 . The collecting unit 2 collects individual point cloud data by acquiring individual point cloud data from a plurality of mobile objects or by acquiring individual point cloud data from one mobile object a plurality of times.

The generation unit 3 generates comprehensive point cloud data based on the plurality of individual point cloud data collected by the collection unit 2 . The comprehensive point cloud data may be obtained by superimposing a plurality of individual point cloud data, or may indicate a positional average of constituent points of a plurality of individual point cloud data. When generating the comprehensive point cloud data, the generation unit 3 determines the degree of contribution of each piece of individual point cloud data based on the attribute information of the map data, and weights the data according to the degree of contribution, for example. At this time, the higher the reliability, the higher the contribution.

For example, when a predetermined number of years have passed since the last update or creation, the contribution may be set to 0 and the data may not be used (removed) depending on the attribute information. Further, the contribution determined as described above may be applied to the entire individual point cloud data, or may be applied only to the constituent points affected by the use of the map data among the constituent points constituting the individual point cloud data. may be applied to

Comprehensive point cloud data generated in this manner is used, for example, for self-position estimation of a moving object. That is, when a feature is detected by an optical sensor (so-called LIDAR; Laser Imaging Detection and Ranging) mounted on a mobile object, the self-position of the mobile object can be estimated by collating it with comprehensive point cloud data.

With the above configuration, the collecting unit 2 acquires the attribute information about the map data, and determines the contribution of the individual point cloud data based on the attribute information. The degree of contribution of individual point cloud data based on map data with low reliability can be reduced. This makes it possible to generate comprehensive point cloud data with high accuracy based on individual point cloud data generated using map data.

In addition, the degree of contribution of individual point cloud data based on map data that is new at the time of the last update or the time of creation is increased, and the degree of contribution of individual point cloud data based on map data with a large cumulative number of updates or a large version number is increased, By increasing the degree of contribution of individual point cloud data based on high-definition map data, highly accurate comprehensive point cloud data can be generated.

It should be noted that the present invention is not limited to the above embodiments, but includes other configurations and the like that can achieve the object of the present invention, and the following modifications and the like are also included in the present invention.

For example, in the above-described embodiment, the individual data generation unit 12 assigns the attribute information about the map data as a flag to the individual point cloud data. It does not have to be granted. For example, the collection unit 2 may acquire attribute information of map data stored in the moving object for which the individual point cloud data was generated. Further, when the map data is not stored in the mobile unit and is acquired from a data center or the like, the collecting unit 2 may acquire the attribute information of the map data from the data center or the like. Also, the collection unit 2 may estimate the attribute information of the map data used based on the generation date and time of the individual point cloud data.

In the above-described embodiment, the individual data generating unit 12 removes feature points and constituent points based on the map data when generating individual point cloud data. It doesn't have to be. For example, each constituent point of the individual point cloud data may be assigned a reliability based on the map data.

Also, the collection unit and the generation unit that configure the information processing apparatus may not be mounted on the external server, and may be mounted on different equipment or devices. That is, each configuration of the information processing apparatus may extend over a plurality of physically separated apparatuses.

In addition, although the best configuration, method, etc. for carrying out the present invention have been disclosed in the above description, the present invention is not limited thereto. That is, although the present invention has been particularly illustrated and described primarily with respect to particular embodiments, modifications may be made to such embodiments without departing from the spirit and scope of the invention. , materials, quantity, and other detailed configurations can be modified in various ways by those skilled in the art. Therefore, the descriptions that limit the shape, material, etc. disclosed above are exemplified to facilitate understanding of the present invention, and do not limit the present invention. The description by the name of the member that removes part or all of the limitation such as is included in the present invention.

1 information processing device 2 collection unit 3 generation unit

Claims (1)

a collection unit that collects individual point cloud data generated based on imaging information and map data;
a generation unit that generates comprehensive point cloud data based on the plurality of individual point cloud data,
The collection unit acquires attribute information about the map data,
The information processing apparatus, wherein the generating unit determines a degree of contribution for each of the plurality of individual point cloud data based on the attribute information, and generates the integrated point cloud data.

Images