Neural-network-based optimal mode estimation for adaptive affine motion compensation

2021 ◽  
Author(s):  
Takahiro Kitamura ◽  
Toshiyuki Yoshida
Keyword(s):  
Neural Network ◽  
Motion Compensation ◽  
Mode Estimation ◽  
Affine Motion ◽  
Optimal Mode

An Improved Framework of Affine Motion Compensation in Video Coding

2019 ◽  
Vol 28 (3) ◽  
pp. 1456-1469 ◽  
Author(s):  
Kai Zhang ◽  
Yi-Wen Chen ◽  
Li Zhang ◽  
Wei-Jung Chien ◽  
Marta Karczewicz
Keyword(s):  
Video Coding ◽  
Motion Compensation ◽  
Affine Motion

Interweaved Prediction for Affine Motion Compensation

2019 ◽  
Author(s):  
Kai Zhang ◽  
Li Zhang ◽  
Hongbin Liu ◽  
Jizheng Xu ◽  
Yue Wang
Keyword(s):  
Motion Compensation ◽  
Affine Motion

scholarly journals SAR Mocomp by machine Learning

2021 ◽  
Author(s):  
Brianna Christensen ◽  
Enson Chang ◽  
Nathaniel Tamminga
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Unmanned Aerial Vehicles ◽  
Motion Compensation ◽  
Synthetic Aperture ◽  
Navigation Systems ◽  
Inertial Navigation Systems ◽  
Motion Error ◽  
Aerial Vehicles ◽  
Sudden Motion

All unmanned aerial vehicles that use synthetic aperture radar (SAR) systems are equipped with inertial navigation systems (INS) to reduce motion error. Additional motion compensation (MOCOMP) from the data itself is still necessary to achieve required accuracy of a SAR. An affordable method for small drones has yet to be created. We propose machine learning with deep convolutional neural network (CNN) to extract motion error such as sway (right and left) and surge (forward). Results show that the CNN is capable of recognizing gradual drone motion deviations. It has the potential to pick up sudden motion error as well, overcoming major deficiencies of traditional MOCOMP methods, and the need for INS.

Hardware Friendly Interweaved Prediction for Affine Motion Compensation

2021 ◽  
Author(s):  
Tianliang Fu ◽  
Kai Zhang ◽  
Li Zhang ◽  
Shanshe Wang ◽  
Siwei Ma
Keyword(s):  
Motion Compensation ◽  
Affine Motion
Sign in / Sign up

Export Citation Format

Share Document