         
|
GRASP Lab Seminar 2003-2004
July 21 (Wednesday), 10:00 AM, Levine Hall 307, hosted by Jianbo Shi.
Owen Carmichael
Carnegie-Mellon University
Detecting wiry objects in images
Abstract: This talk addresses the problem of recognizing "wiry" objects in images of highly-cluttered indoor scenes. Wiry objects are distinguished by a prevalence of very thin, elongated, stick-like components; examples include tables, chairs, bicycles, and desk lamps. They are difficult to recognize because they tend to lack distinctive color or texture characteristics and their appearance is not easy to describe succinctly in terms of rectangular patches of image pixels. I will talk about a set of algorithms that extends current capabilities to find wiry objects in highly cluttered images across changes in the clutter and object pose. Specifically, I will present discrimination-centered techniques for extracting shape features from portions of images, classifying those features as belonging to an object of interest or not, and aggregating found object parts together into overall instances of objects. I will present a suite of experiments on real, wiry objects-- a chair, cart, ladder, and stool respectively -- which substantiate the utility of these methods and explores their behavior.
Biography:
