ICRA 2011 Paper Abstract

Close

Paper WeP210.2

Sivalingam, Ravishankar (University of Minnesota), D'Souza, Alden (CSE, University of Minnesota), Morellas, Vassilios (U. of Minnesota), Papanikolopoulos, Nikos (University of Minnesota), Bazakos, Michael (Lockheed Martin), Miezianko, Roland (Lockheed Martin)

Dictionary Learning for Robust Background Modeling

Scheduled for presentation during the Regular Sessions "Surveillance, Search and Rescue Robotics" (WeP210), Wednesday, May 11, 2011, 15:40−15:55, Room 5E

2011 IEEE International Conference on Robotics and Automation, May 9-13, 2011, Shanghai International Conference Center, Shanghai, China

This information is tentative and subject to change. Compiled on December 10, 2019

Keywords Surveillance Systems, Visual Learning, Computer Vision for Robotics and Automation

Abstract

Background subtraction is a fundamental task in many computer vision applications, such as in robotics and automated surveillance systems. The performance of high-level tasks such as object detection and tracking is highly dependent on effective foreground detection techniques. In this paper, we propose a novel background modeling algorithm that represents the background as a linear combination of dictionary atoms and the foreground as a sparse error in this linear model. The dictionary atoms constitute the background model, and is learned from a batch of randomly sampled training frames. The sparse foreground estimation in the training as well as test phases is formulated as a Lasso problem, while the dictionary update step in the training phase is motivated from the K-SVD algorithm. Our proposed method works well in the presence of foreground in the training frames, and unlike other methods, gives the foreground masks for the training frames as a by-product of the training phase. Experimental validation is provided on standard datasets with ground truth information, and the receiver operating characteristic (ROC) curves are shown.

 

 

Technical Content © IEEE Robotics & Automation Society

This site is protected by copyright and trademark laws under US and International law.
All rights reserved. © 2002-2019 PaperCept, Inc.
Page generated 2019-12-10  06:27:54 PST  Terms of use