News & Events
CITRIS Research Exchange: Texture Analysis of Remote-Sensed Imagery
- November 15, 2006: 12:00pm - 1:00pm
- Contact: yvette@citris-uc.org
- Location: 290 Hearst Memorial Mining Building, the Maria & Dado Banatao Conference Room, UC Berkeley
"Texture Analysis of Remote-Sensed Imagery"
by Shawn Newsam, Assistant Professor at the School of Engineering at UC Merced
12:00 p.m. on Wednesday, November 15 in 290 HMMB, UC Berkeley. Part of the CITRIS Research Exchange at UC Berkeley. The complete schedule for the fall semester is online at RE-fall2006.
Watch talk online || View presentation (ppt)
Abstract:
Remote-sensed imagery acquired from satellites or aircraft
continues to offer passive, low-cost, and broad-field monitoring of Earth's
surface and has enabled a new suite of consumer-oriented applications such as
Google Earth. Advances in sensing technology are producing images with
increasing spatial resolution, which means that individual pixels are more
likely to represent the spectral reflectance of regions composed of single
rather than mixes of materials. The problem of determining the composition of
the regions imaged by single pixels through spectral un-mixing is giving way to
the problem of characterizing the spatial arrangement of the pixels. Such
characterizations can help distinguish land-cover classes consisting of similar
materials but in different spatial configurations.
In this context, I will present my work on analyzing spatial
relationships in remote-sensed imagery. I will discuss the application of a
homogeneous image texture descriptor to performing content-based similarity
retrieval in large collections of high-resolution satellite imagery. This serves
as motivation for my subsequent work on using image texture for a number of
classification tasks in remote-sensed imagery.
Biography:
Professor Newsam is an assistant professor of Computer Science and
Engineering and founding faculty at the new
---------------------------------