Title:
JOINT FORECASTING OF FEATURE AND FEATURE MOTION
Document Type and Number:
Japanese Patent JP2022090599
Kind Code:
A
Abstract:
To provide a computer-implemented method of forecasting semantic output of at least one frame.SOLUTION: A method includes the steps of receiving a plurality of input frames from a camera up to a predetermined time, processing via a down-sampling module of a neural network the plurality of input frames to receive a plurality of feature tensors, determining spatio-temporal correlations between the plurality of feature tensors, processing the plurality of feature tensors and the spatio-temporal correlations to receive at least one forecasted feature tensor, and processing via an up-sampling module of the neural network the at least one forecasted feature to receive at least one forecasted semantic output for a time longer than the predetermined time.SELECTED DRAWING: Figure 1
More Like This:
JP6236363 | Subject recognition device |
JP2022144486 | IMAGE PROCESSING DEVICE |
JP4227432 | Image processing method |
Inventors:
TONCI ANTUNOVIC
MARIN ORSIC
JOSIP SARIC
SINISA SEGVIC
SACHA VRAZIC
MARIN ORSIC
JOSIP SARIC
SINISA SEGVIC
SACHA VRAZIC
Application Number:
JP2021094339A
Publication Date:
June 17, 2022
Filing Date:
June 04, 2021
Export Citation:
Assignee:
RIMAC AUTOMOBILES LTD
International Classes:
G06T7/00; G06N3/08
Attorney, Agent or Firm:
Murayama Yasuhiko
Shinya Mihiro
Tatsuhiko Abe
Shinya Mihiro
Tatsuhiko Abe
Previous Patent: Toilet seat device
Next Patent: Time interleaved A / D converter and laser gas analyzer
Next Patent: Time interleaved A / D converter and laser gas analyzer