Verfahren zum Trainieren eines Crnn und zur Semantischen Segmentierung eines Eingegebenen Videos unter Verwendung des Besagten Crnn

Details

Veröffentlichungs-Nr.

EP3608844

Aktenzeichen

EP18306104

Anmeldetag

10. August 2018

Veröffentlichung

2. Juli 2025

Erteilung

2. Juli 2025

Rechtsraum

EP

IPC

G06N3/04G06N3/08

Abstract

The present invention relates to a method for training a convolutional recurrent neural network, CRNN, for semantic segmentation in videos; the method being characterized in that it comprises the implementation, by a data processor (11a) of a first server (1a), of steps of:(a) Training from a base of training images already semantically segmented, a first convolutional neural network, CNN;(b) Training from a base of training videos already semantically segmented, a recurrent convolutional neural network, CRNN, corresponding to the first CNN wherein a convolutional layer has been replaced by a recurrent module having a hidden state; said training comprising, for each pair of successive frames (t- 1,t∈1;T²) of a video of said base of training videos already semantically segmented:(b1) Warping the internal state of the recurrent layer according to an estimated optical flow between the frames of the pair, so as to adapt the internal state to the motion of pixels between the frames of the pair;(b2) learning parameters of at least the recurrent moduleA method for semantic segmentation of an inputted video is further proposed.

Anmelder

Firma

Naver Corporation

Land

🇰🇷 Südkorea

Fachgebiete