Information processing apparatus, information processing method, and non-transitory computer readable medium
AssigneeRakuten Group, Inc.
InventorsVinayaraj Poliyapram, Jeremiah Anderson, Mayank Bansal
Life of this patent
Estimating the term…
Abstract
An information processing apparatus (1) includes: an acquisition unit (12) configured to acquire a satellite image; a first generation unit (13) configured to recursively predict and generate a first image representing a distribution of population values with respect to the satellite image, through machine learning, using the satellite image as an input; and a second generation unit (13) configured to predict and generate a second image representing probabilities of land types with respect to the satellite image, through the machine learning.
Claims11
An information processing apparatus comprising:
- at least one memory configured to store program code;
- at least one processor configured to access the program code and operate as instructed by the program code, the program code including:
- acquisition code configured to cause at least one of the at least one processor to acquire a satellite image;
- first generation code configured to cause at least one of the at least one processor to recursively predict and generate a first image representing a distribution of population values with respect to the satellite image, through machine learning with one learning model, using the satellite image as an input;
- and
- second generation code configured to cause at least one of the at least one processor to predict and generate a second image representing probabilities of land types with respect to the satellite image, through the machine learning,
- wherein the learning model includes a first part to which the satellite images are input and a second part that outputs the first image and the second image that have been predicted,
- the first part includes a plurality of convolutional layers, and
- the second part includes a first branch and a second branch, and the first branch and the second branch each include a plurality of convolutional layers.
An information processing method carried out by an information processing apparatus, comprising:
- acquiring a satellite image;
- recursively predicting and generating a first image representing a distribution of population values with respect to the satellite image, through machine learning with one learning model, using the satellite image as an input;
- and
- predicting and generating a second image representing probabilities of land types with respect to the satellite image, through the machine learning,
- wherein the learning model includes a first part to which the satellite images are input and a second part that outputs the first image and the second image that have been predicted,
- the first part includes a plurality of convolutional layers, and
- the second part includes a first branch and a second branch, and the first branch and the second branch each include a plurality of convolutional layers.
A non-transitory computer readable medium storing a computer program for causing a computer to:
- acquire a satellite image;
- recursively predict and generate a first image representing a distribution of population values with respect to the satellite image, through machine learning with one learning model, using the satellite image as an input;
- and
- predict and generate a second image representing probabilities of land types with respect to the satellite image, through the machine learning,
- wherein the learning model includes a first part to which the satellite images are input and a second part that outputs the first image and the second image that have been predicted,
- the first part includes a plurality of convolutional layers, and
- the second part includes a first branch and a second branch, and the first branch and the second branch each include a plurality of convolutional layers.
Dependencies are inferred from the claim text.