Map information processing device and map information processing method
View Patent ↗The map information processing device includes a processor. The processor that extracts difference data by comparing a movement track image based on individual movement tracks of a plurality of moving bodies with an image in a scalar form based on vector data that is different from the movement track image; and The processor that decides through machine learning whether the difference data corresponds to a road shape change.
1. A map information processing device comprising
a processor configured
to acquire probe data for each of a plurality of moving bodies;
to generate a movement track image in a scalar form on the basis of vector probe data acquired for each of the plurality of moving bodies;
to convert map information that includes information indicating a position and shape of a road from a vector form to a scalar form;
to extract difference data indicating a difference between the movement track image and a map image included in the map information converted into a scalar form; and
to decide through machine learning whether the difference data corresponds to a road shape change.
2. The map information processing device according to claim 1 , further comprising
a map information storage that stores the map information that includes information indicating a position and shape of a road, the map information being represented in a vector form.
3. The map information processing device according to claim 1 , wherein
the processor renders the movement track image on the basis of probe data of each of the plurality of moving bodies, and
the processor collectively renders movement track images located within a specified range.
4. The map information processing device according to claim 3 , wherein
the processor renders a past movement track image on the basis of probe data acquired for a particular period, then renders a movement track image on the basis of probe data acquired for a specified period, and finally decides, through a comparison, whether there is a difference between the rendered movement track image and the rendered past movement track image, and
the processor sets, as an object for which a difference-data extraction process is to be performed, only a movement track image for which it has been decided through a comparison that there is a difference from the past movement track image.
5. The map information processing device according to claim 1 , wherein
the processor retrieves only map image information indicating a road shape from among the map information and converts the retrieved map image from a vector form to a scalar form.
6. The map information processing device according to claim 1 , wherein
the processor performs machine learning in accordance with difference data extracted in the past and decides on the basis of a result of the machine learning whether newly extracted difference data corresponds to a road shape change.
7. The map information processing device according to claim 2 , wherein
the processor that updates map information stored in the map information storage,
the processor
converts difference data that the road shape change determination unit determines corresponds to a road shape change into vector data, and
updates map information stored in the map information storage by using the difference data converted into vector data.
8. The map information processing device according to claim 2 , wherein
for each of a plurality of scaling factors, the map information storage stores map information that includes information indicating positions and shapes of a plurality of roads, and
when the processor decides through the machine learning that the possibility of the difference data corresponding to a road shape change is less than or equal to a specified likelihood, the processor converts pieces of map information with a high scaling factor from among the map information stored in the map information storage from a vector form to a scalar form.
9. A map information processing method wherein a computer performs the processes of:
acquiring probe data for each of a plurality of moving bodies;
generating a movement track image in a scalar form on the basis of vector probe data acquired for each of the plurality of moving bodies;
converting map information that includes information indicating a position and shape of a road from a vector form to a scalar form;
extracting difference data indicating a difference between the movement track image and a map image included in the map information converted into a scalar form; and
deciding through machine learning whether the difference data corresponds to a road shape change.
10. A non-transitory computer-readable recording medium having stored therein a program for causing a computer to execute a processes comprising:
acquiring probe data for each of a plurality of moving bodies;
generating a movement track image in a scalar form on the basis of vector probe data acquired for each of the plurality of moving bodies;
converting map information that includes information indicating a position and shape of a road from a vector form to a scalar form;
extracting difference data indicating a difference between the movement track image and a map image included in the map information converted into a scalar form; and
deciding through machine learning whether the difference data corresponds to a road shape change.
11. A map information processing device, comprising:
a processor configured:
to acquire probe data for each of a plurality of moving bodies;
to generate a movement track image in a scalar form on the basis of vector probe data acquired for a specified period for each of the plurality of moving bodies;
to generate a past movement track image in a scalar form on the basis of vector probe data acquired for a particular period in advance for each of the plurality of moving bodies;
to extract difference data indicating a difference between the movement track image and the past movement track image; and
to decide through machine learning whether the difference data corresponds to a road shape change.
12. The map information processing device according to claim 11 , wherein
the processor performs machine learning in accordance with difference data extracted in the past and decides on the basis of a result of the machine learning whether newly extracted difference data corresponds to a road shape change.
13. A map information processing method wherein a computer performs the processes of:
acquiring probe data for each of a plurality of moving bodies;
generating a movement track image in a scalar form on the basis of vector probe data acquired for a specified period for each of the plurality of moving bodies;
generating a past movement track image in a scalar form on the basis of vector probe data acquired for a particular period in advance for each of the plurality of moving bodies;
extracting difference data indicating a difference between the movement track image and the past movement track image; and
deciding through machine learning whether the difference data corresponds to a road shape change.
14. A non-transitory computer-readable recording medium having stored therein a program for causing a computer to execute a processes comprising:
acquiring probe data for each of a plurality of moving bodies;
generating a movement track image in a scalar form on the basis of vector probe data acquired for a specified period for each of the plurality of moving bodies;
generating a past movement track image in a scalar form on the basis of vector probe data acquired for a particular period in advance for each of the plurality of moving bodies;
extracting difference data indicating a difference between the movement track image and the past movement track image; and
deciding through machine learning whether the difference data corresponds to a road shape change.