Deep Optical Flow Supervised Learning With Prior Assumptions

Deep Optical Flow Supervised Learning With Prior Assumptions

Traditional methods for estimating optical flow use variational model that includes data term and smoothness term, which can build a constraint relationship between two adjacent images and optical flow. However, most of them are too slow to be used in real-time applications. Recently, convolutional...

Full description

Bibliographic Details
Main Authors: Xuezhi Xiang, Mingliang Zhai, Rongfang Zhang, Yulong Qiao, Abdulmotaleb El Saddik
Format: Article
Language:English
Published: IEEE 2018-01-01
Series:IEEE Access
Subjects:
Optical flow estimation
convolutional neural networks
supervised learning
prior assumptions
Online Access:https://ieeexplore.ieee.org/document/8425694/

Internet

https://ieeexplore.ieee.org/document/8425694/

Similar Items