Image generating method and apparatus
AssigneeSamsung Electronics Co., Ltd.
InventorsKyoobin Lee, Eric Hyunsurk Ryu, Keun Joo Park
Life of this patent
Estimating the term…
Abstract
An image generating method and an image generating apparatus are provided. The image generating method includes generating a first image based on first event signals that are output from an event-based vision sensor during a first time period and stored in a buffer, generating a second image based on second event signals that are output from the event-based vision sensor during a second time period and stored in the buffer, and aligning the first image and the second image to generate a third image having a quality that is higher than qualities of the first image and the second image.
Claims29
An image generating method comprising:
- generating a first image based on first event signals that are output from an event-based vision sensor during a first time period and stored in a buffer;
- generating a second image based on second event signals that are output from the event-based vision sensor during a second time period and stored in the buffer;
- and
- aligning the first image and the second image to generate a third image having a quality that is higher than qualities of the first image and the second image.
An image generating apparatus comprising:
- an event-based vision sensor configured to output first event signals during a first time period and second event signals during a second time period;
- a buffer configured to store the first event signals and the second event signals;
- and
- a processor configured to:
- generate a first image based on the first event signals;
- generate a second image based on the second event signals;
- and
- align the first image and the second image to generate a third image having a quality that is higher than qualities of the first image and the second image.
An image generating method comprising:
- retrieving, from a buffer, first event signals that are output from an event-based vision sensor during a first time period, in an inverse order of time at which respective first events are sensed;
- generating a first image based on the retrieved first event signals;
- retrieving, from the buffer, second event signals that are output from the event-based vision sensor during a second time period, in an inverse order of time at which respective second events are sensed;
- generating a second image based on the retrieved second event signals;
- aligning the second image with the first image to generate aligned candidate images;
- determining similarities between the first image and the aligned candidate images;
- and
- aligning an aligned candidate image having a maximum similarity, among the similarities, with the first image to generate the third image.
Dependencies are inferred from the claim text.