Performance analysis of generated predictive frames using PredNet with multiple convolution kernels

Kanato Sakama; Shunichi Sekiguchi; Wataru Kameyama

doi:10.1117/12.2666864

25 March 2023 Performance analysis of generated predictive frames using PredNet with multiple convolution kernels

Kanato Sakama, Shunichi Sekiguchi, Wataru Kameyama

Proceedings Volume 12592, International Workshop on Advanced Imaging Technology (IWAIT) 2023; 125921N (2023) https://doi.org/10.1117/12.2666864
Event: International Workshop on Advanced Imaging Technology (IWAIT) 2023, 2023, Jeju, Korea, Republic of

Abstract

DNN-based video frame prediction can be a powerful tool to improve performance of motion-compensated prediction in video coding. In this paper, we propose a method applying multiple convolution kernels with different sizes to PredNet, which is one of the DNN-based video prediction schemes, to enhance the prediction accuracy by incorporating context adaptivity in its convolutional LSTM layers. We analyze the prediction performance of the proposal, and the results show that applying multiple-size kernels is effective than applying a single-size kernel in terms of prediction error reduction.

Citation Download Citation

Kanato Sakama, Shunichi Sekiguchi, and Wataru Kameyama "Performance analysis of generated predictive frames using PredNet with multiple convolution kernels", Proc. SPIE 12592, International Workshop on Advanced Imaging Technology (IWAIT) 2023, 125921N (25 March 2023); https://doi.org/10.1117/12.2666864

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
4 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Video

Convolution

Video coding

Neural networks

Video processing

RELATED CONTENT

An improved MDNet target tracking algorithm
Proceedings of SPIE (August 04 2022)

A bidirectional LSTM method based on temporal features for deep...
Proceedings of SPIE (September 27 2022)

Mixed 3D-(2+1)D convolution for action recognition
Proceedings of SPIE (August 14 2019)

Quality-aware CNN-based in-loop filter for video coding
Proceedings of SPIE (August 01 2021)

Bi-directional prediction for end-to-end optimized video compression
Proceedings of SPIE (August 01 2021)

Fake-buster: a lightweight solution for deepfake detection
Proceedings of SPIE (August 01 2021)

Design of car audio and video synchronization algorithm based on...
Proceedings of SPIE (September 11 2023)

Subscribe to Digital Library

Receive Erratum Email Alert

Keywords/Phrases

Search In:

Publication Years