Inferring Non-Observable Object Properties

GRAND Seminar 11:00 am, May 26, Thur., 2011, ENGR 4201

Hedvig Kjellström
Associate Professor
Royal Institute of Technology, Stockholm, Sweden

Host:

Jana Koseka

Abstract:

The great majority of object analysis methods are based on visual object properties - objects are categorized according to how they appear in images. Visual appearance is measured in terms of image features (e.g., SIFTs) extracted from images or video. However, besides appearance, objects also have many properties that can be of interest, e.g., for a robot who wants to employ them in activities: Temperature, weight, surface softness, and also the functionalities or affordances of the object, i.e., how it is intended to be used. One example, recently addressed in the vision community, are chairs. Chairs can look vastly different, but have one thing in common: they afford sitting. At the Computer Vision and Active Perception Lab at KTH, we study the problem of inferring non-observable object properties in a number of ways. In this presentation I will describe some of this work. These methods can be seen as ways of incorporating contextual information in object detection and recognition. I will also describe our work on contextual human pose estimation: two different approaches to improving the estimation of human pose using object context.

If you would like to meet with the speaker contact kosecka@cs.gmu.edu.