Ent?te

Logo du LIFL

Depuis le 1er janvier 2015 le LIFL et le LAGIS forment le laboratoire CRIStAL

  1. Actualités

Séminaire de

B Prabhakaran

23 juin 2010
Amphithéâtre de l'IRCICA

Extracting Useful Features from Video for Human Action Recognition

In this talk, I focus on the issue of improving the quality of low level 2D feature extraction for human action recognition. For instance, existing algorithms such as the Optical Flow algorithm detects noisy and irrelevant features because of its lack of ground truth data sets for complex scenes. From these features, it is difficult to extract data such as coordinate positions of the features, velocity and the direction of the moving objects, and the differential data information between different frames.
Extracting such low level feature data is one of the major steps involved in video based Human action recognition.

I will describe two methods we have been working on:
a. Extended Optical Flow algorithm focusing on human actions: This uses a Frame Jump technique along with
thresholding of unwanted features to overcome the problems due to complex scenes.
b. Extension of a sparse `correlogram' into higher dimensional space:
We use this higher dimensional sparse correlogram to search input video for patterns of shape and motion while
ignoring color and lighting information. The method then analyzes the calculated information and returns a subset of this sparse correlogram.

Ours

UMR 8022 - Laboratoire d'Informatique Fondamentale de Lille - Copyright © 2012 Sophie TISON - Crédits & Mentions légales

Page respectant XHTML et CSS.

Pour tout commentaire / Comments and remarks : webmaster