Date of Award

1-1-2010

Document Type

Masters Thesis

Degree Name

M.S.

Organizational Unit

Daniel Felix Ritchie School of Engineering and Computer Science

First Advisor

Richard M. Voyles, Ph.D.

Second Advisor

Mohammad H. Mahoor, Ph.D.

Third Advisor

Matthew Rutherford

Keywords

Activity recognition, Gaussian Mixture Model, Motion estimation, SIFT, SIFT-ME, Scale-invariant feature transform

Abstract

Action representation for robust human activity recognition is still a challenging problem. This thesis proposed a new feature for human activity recognition named SIFT-Motion Estimation (SIFT-ME). SIFT-ME is derived from SIFT correspondences in a sequence of video frames and adds tracking information to describe human body motion. This feature is an extension of SIFT and is used to represent both translation and rotation in plane rotation for the key features. Compare with other features, SIFT-ME is new as it uses rotation of key features to describe action and it robust to the environment changes. Because SIFT-ME is derived from SIFT correspondences, it is invariant to noise, illumination, and small view angle change. It is also invariant to horizontal motion direction due to the embedded tracking information. For action recognition, we use Gaussian Mixture Model to learn motion patterns of several human actions (e.g., walking, running, turning, etc) described by SIFT-ME features. Then, we utilize the maximum log-likelihood criterion to classify actions. As a result, an average recognition rate of 96.6% was achieved using a dataset of 261 videos comprised of six actions performed by seven subjects. Multiple comparisons with existing implementations including optical flow, 2D SIFT and 3D SIFT were performed. The SIFT-ME approach outperforms the other approaches which demonstrate that SIFT-ME is a robust method for human activity recognition.

Publication Statement

Copyright is held by the author. User is responsible for all copyright compliance.

Rights Holder

Guosheng Wu

Provenance

Received from ProQuest

File Format

application/pdf

Language

en

File Size

60 p.

demoforpaper.avi (3177 kB)
Demonstration Video

Discipline

Computer engineering, Computer science



Share

COinS