Back to results
US 11,231,776 B2Granted
Method and apparatus for predicting intention of user
AssigneeSamsung Electronics Co., Ltd.
InventorsSeungin Park, Hyong Euk Lee
Life of this patent
Estimating the term…
Abstract
A method and apparatus for predicting an intention acquires a gaze sequence of a user, acquires an input image corresponding to the gaze sequence, generates a coded image by visually encoding temporal information included in the gaze sequence to the input image, and predicts an intention of the user corresponding to the gaze sequence based on the input image and the coded image.
Claims24
A method of predicting an intention, the method comprising:
- acquiring a gaze sequence of a user;
- acquiring an input image corresponding to the gaze sequence;
- generating a coded image by visually encoding temporal information included in the gaze sequence to the input image;
- and
- predicting an intention of the user corresponding to the gaze sequence based on the input image and the coded image,
- wherein the generating comprises:
- generating coded partial images by encoding the temporal information to each RGB channel in regions of the input image to which gazes corresponding to the gaze sequence are mapped;
- and
- generating the coded image by combining the coded partial images.
6 more elements
An apparatus for predicting an intention, the apparatus comprising:
- one or more processors configured to
- acquire a gaze sequence of a user and an input image corresponding to the gaze sequence,
- generate a coded image by visually encoding temporal information included in the gaze sequence to the input image, and
- predict an intention of the user corresponding to the gaze sequence based on the input image and the coded image,
- wherein, for the generating of the coded image, the one or more processors are further configured to:
- generate coded partial images by encoding the temporal information to each RGB channel in regions of the input image to which gazes corresponding to the gaze sequence are mapped;
- and
- generate the coded image by combining the coded partial images.
5 more elements
Dependencies are inferred from the claim text.