Advisor(s)

Octavia Camps

Contributor(s)

Jennifer G. Dy, Brie Howley, Deniz Erdogmus

Date of Award

2010

Date Accepted

7-2010

Degree Grantor

Northeastern University

Degree Level

M.S.

Degree Name

Master of Science

Department or Academic Unit

College of Engineering, Department of Electrical and Computer Engineering

Keywords

electrical engineering, adaptive boosting AdaBoost, automatic detection, classification, pattern recognition, satellite images

Subject Categories

Land use--Remote sensing, Computer vision

Disciplines

Electrical and Computer Engineering

Abstract

In recent years, there has been an increasing demand for applications to monitor the targets related to land-use, using remote sensing images. Advances in remote sensing satellites give rise to the research in this area. Many applications ranging from urban growth planning to homeland security have already used the algorithms for automated object recognition from remote sensing imagery. However, they have still problems such as low accuracy on detection of targets, specific algorithms for a specific area etc.

In this thesis, we focus on an automatic approach to classify and detect building footprints, road networks and vegetation areas. The automatic interpretation of visual data is a comprehensive task in computer vision field. The machine learning approaches improve the capability of classification in an intelligent way.

We propose a method, which has high accuracy on detection and classification. The multi class classification is developed for detecting multiple objects. We present an AdaBoost-based approach along with the supervised learning algorithm. The combination of AdaBoost with "Attentional Cascade" is adopted from Viola and Jones [1]. This combination decreases the computation time and gives opportunity to real time applications. For the feature extraction step, our contribution is to combine Haar-like features that include corner, rectangle and Gabor. Among all features, AdaBoost selects only critical features and generates in extremely efficient cascade structured classifier.

Finally, we present and evaluate our experimental results. The overall system is tested and high performance of detection is achieved. The precision rate of the final multi-class classifier is over 98%.

Document Type

Master's Thesis

Rights Information

copyright 2010

Rights Holder

Cansu Gonulalan


View Full Text

Click button above to open, or right-click to save.

Share

COinS