AlexandreAlahi

Contents

Home
Research Projects
Publications
Teaching
Data set
Source Code
CV
Media Coverage


Research fields

Computer Vision
Signal Processing
Machine learning
Robotics
Computational Neuroscience


Research Interests

Sparse approximation
Compressed-sensing
Inverse problems
Real-time vision
Bio-inspired vision
Large-scale vision
Big Visual data

 

Foreground silhouette extraction robust to sudden changes

- What is the problem?

Vision-based background subtraction algorithms model the intensity variation across time to classify a pixel as foreground. Unfortunately, such algorithms are sensitive to appearance changes of the background such as sudden changes of illumination or when videos are projected in the background.

- What is our solution?

We propose an algorithm to extract foreground silhouettes without modeling the intensity variation across time. Using a camera pair, the stereo mismatch is processed to produce a dense disparity based on a Total Variation (TV) framework.

- Why is our solution proposed?

Experimental results show that with sudden changes of background appearance, our proposed TV disparity-based extraction outperforms intensity-based algorithms and existing stereo-based approaches based on temporal depth variation and stereo mismatch.


Related publications:

A. Alahi, L. Bagnato, D. Matti, and P. Vandergheynst. Foreground Silhouettes Extraction robust to Sudden Changes of background Appearance. In IEEE International conference on Image Processing, 2012. [ Details | Full Text ]

 
top

© alahi {at} stanford.edu
updated: January 2015

Follow me on

Alahi on ScholarAlahi on LinkedinAlahi on Twitter

 

Schools Studied


Stanford


Ecole Polytechnique Fédérale de Lausanne


Labs Worked

Vision lab at Stanford

LTS2

Transpor


Companies Worked

VisioSafe