Publication View

The whole world in your hand: Active and interactive segmentation (2003)

Abstract
This paper presents three approaches to object segmentation, a fundamental problem in computer vision. Each approach is aided by the presence of a hand or arm in the proximity of the object to be segmented. The first approach is suitable for a robotic system, where the robot can use its arm to evoke object motion. The second method operates on a wearable system, viewing the world from a human’s perspective, with instrumentation to help detect and segment objects that are held in the wearer’s hand. The third method operates when observing a human teacher, locating periodic motion (finger/arm/object waving or tapping) and using it as a seed for segmentation. We believe that object segmentation is a key resource for development, and demonstrate that once high-quality object segmentation is available, it is possible to train up both high-level visual modules (object recognition and localization) and to enhance lowlevel vision. 1.

Publication details
Download http://citeseerx.ist.psu.edu/viewdoc/summary?doi=?doi=10.1.1.13.7189
Source http://www.ai.mit.edu/people/paulfitz/pub/epirob03whole.pdf
Contributors CiteSeerX
Repository CiteSeerX - Scientific Literature Digital Library and Search Engine (United States)
Type text
Language English
Relation 10.1.1.132.5942, 10.1.1.18.6984, 10.1.1.23.7975, 10.1.1.21.2273, 10.1.1.37.2368, 10.1.1.129.514, 10.1.1.70.8035, 10.1.1.63.4228, 10.1.1.101.4858, 10.1.1.14.3129, 10.1.1.14.5813