AlexandreAlahiAlexandreAlahiAlexandreAlahiAlexandreAlahiAlexandreAlahiAlexandreAlahiAlexandreAlahiAlexandreAlahiAlexandreAlahi

 

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: October 2016

Follow me on

Alahi on ScholarAlahi on LinkedinAlahi on Twitter