Personal tools

Difference between revisions of "Accelerator for Spatio-Temporal Video Filtering"

From iis-projects

Jump to: navigation, search
Line 7: Line 7:
 
"[[Real-time View Synthesis using Image Domain Warping]]" and "[[A Multiview Synthesis Core in 65 nm CMOS]]".
 
"[[Real-time View Synthesis using Image Domain Warping]]" and "[[A Multiview Synthesis Core in 65 nm CMOS]]".
  
The goal of this project is to build is to look into an advanced saliency estimation  
+
The goal of this project is to look into an advanced saliency estimation  
 
algorithm, and to develop an efficient hardware architecture for it. Depending on  
 
algorithm, and to develop an efficient hardware architecture for it. Depending on  
 
the progress, the implementation can also be prototyped on a FPGA.
 
the progress, the implementation can also be prototyped on a FPGA.

Revision as of 17:29, 21 February 2014

Example for a saliency map (image copyright belongs to the [Blender Foundation]).

Short Description

Saliency estimation is an important building block in video processing applications. The goal of saliency estimation is to find visually important regions in the image, and this information can be used in further processing steps to adapt the video in a content-aware fashion. Examples for applications that use saliency estimates are "Real-time View Synthesis using Image Domain Warping" and "A Multiview Synthesis Core in 65 nm CMOS".

The goal of this project is to look into an advanced saliency estimation algorithm, and to develop an efficient hardware architecture for it. Depending on the progress, the implementation can also be prototyped on a FPGA.

Status: Available

Scope: Semester or Master Thesis
Looking for 1-2 Interested Students
Supervisors: Frank Gürkaynak, Michael Schaffner

Prerequisites

VLSI I
Introductory course in computer vision (recommended)
Interest in computer graphics / computer vision
Matlab, VHDL and C++

Character

25% Theory & Literature Study
25% Matlab Evaluations
50% Hw Architecture & FPGA Implementation

Professor

Luca Benini

Partners

Disney Research Zurich

↑ top

Detailed Task Description

Goals

Practical Details



↑ top