scholarly journals Motion Segmentation and Tracking with Edge Relaxation and Optimization using Fully Parallel Methods in the Cellular Nonlinear Network Architecture

2001 ◽  
Vol 7 (1) ◽  
pp. 77-95 ◽  
Author(s):  
László Czúni ◽  
Tamás Szirányi
Keyword(s):  
Network Architecture ◽  
Motion Segmentation ◽  
Parallel Methods ◽  
Nonlinear Network ◽  
Segmentation And Tracking

scholarly journals Bayesian Method for Motion Segmentation and Tracking in Compressed Videos

2005 ◽  
pp. 277-284 ◽  
Author(s):  
Siripong Treetasanatavorn ◽  
Uwe Rauschenbach ◽  
Jörg Heuer ◽  
André Kaup
Keyword(s):  
Bayesian Method ◽  
Motion Segmentation ◽  
Segmentation And Tracking

A novel framework for motion segmentation and tracking by clustering incomplete trajectories

2012 ◽  
Vol 116 (11) ◽  
pp. 1135-1148 ◽  
Author(s):  
Vasileios Karavasilis ◽  
Konstantinos Blekas ◽  
Christophoros Nikou
Keyword(s):  
Motion Segmentation ◽  
Segmentation And Tracking

scholarly journals Networks for Nonlinear Diffusion Problems in Imaging

2019 ◽  
Vol 62 (3) ◽  
pp. 471-487
Author(s):  
S. Arridge ◽  
A. Hauptmann
Keyword(s):  
Neural Network ◽  
Nonlinear Diffusion ◽  
Network Architecture ◽  
Diffusion Processes ◽  
Training Data ◽  
Network Architectures ◽  
Nonlinear Network ◽  
Image Dataset ◽  
Major Transformation ◽  
Diffusion Problems

Abstract A multitude of imaging and vision tasks have seen recently a major transformation by deep learning methods and in particular by the application of convolutional neural networks. These methods achieve impressive results, even for applications where it is not apparent that convolutions are suited to capture the underlying physics. In this work, we develop a network architecture based on nonlinear diffusion processes, named DiffNet. By design, we obtain a nonlinear network architecture that is well suited for diffusion-related problems in imaging. Furthermore, the performed updates are explicit, by which we obtain better interpretability and generalisability compared to classical convolutional neural network architectures. The performance of DiffNet is tested on the inverse problem of nonlinear diffusion with the Perona–Malik filter on the STL-10 image dataset. We obtain competitive results to the established U-Net architecture, with a fraction of parameters and necessary training data.

Sign in / Sign up

Export Citation Format

Share Document