Department of Systems and Control Engineering
Faculty of Engineering
University of Malta
Public Talk on:
Astrobiological Exploration
The Department of Systems and Control Engineering is organizing a
public talk entitled:
The Cyborg Astrobiologist: Teaching Computers to
Find Uncommon or Novel Areas of Geological
Scenery in Real-time
The speaker is Dr. Patrick McGuire from the Department of the
Geophysical Sciences, University of Chicago, USA.
The talk shall be held on Friday 2nd July 2010 from 12:00 to 13:00 in
Rom EB1, Engineering Building on campus.
Interested persons are cordially invited to attend. For further details,
please contact Ms. Alexandra Bonnici (abbart@eng.um.edu.mt).
Abstract and speaker biography can be found in the following pages.
Brief Biography of the Speaker
Dr. Patrick Mc. Guire is a Senior Research Associate of the Department of the
Geophysical Sciences at the University of Chicago, USA. He recieved the
B.A. degree in Physics and Mathematics in 1989 from the University of Chicago
and the Ph.D degree in Physics in 1994 from the University of Arizona.
Dr. Patrick C. McGuire has interests in computer vision, Mars exploration,
climate science, and is working on modelling the formation and stability of
methane hydrates underneath the seafloor. His broad background in
astrobiology, astronomy/astrophysics, complex systems, neural networks,
computer vision, and robotics is the springboard from which his current
interests in both climate science and Mars exploration have proceeded. After
his Ph.D. in astrophysics and neural networks, he worked in industry for two
years prior to working on neural networks, telescope instrumentation and
astronomy on the MMT Telescope in Arizona. He then worked in Germany and
Spain for almost six years on neural networks, robotics, computer vision, and
astrobiology. He has led the development of the Cyborg Astrobiologist system,
including field tests at several Mars analog sites in Spain, Malta and Utah. Since
2005, he has led the development of the atmospheric and thermal correction
system for CRISM multispectral mapping by the Mars Reconnaissance Orbiter.
Together with Navid Serrano and others, he won a NASA/JPL New Technology
Report Software Award in 2009 for “Using CTX image features to predict
HiRISE-equivalent rock density”. His teaching experience includes introductory
courses in astronomy, planetary science, and climate science. Since 2008, he
has spent part of each year as a research fellow in Berlin. In 2009, he began a
research position at the University of Chicago.
Abstract
In prior work, we have developed computer algorithms for real-time novelty
detection and rarity mapping for astrobiological and geological exploration.
These algorithms were tested at astrobiological field sites using mobile
computing platforms – originally with a wearable computer connected to a
digital video camera, but more recently with a phone camera connected
wirelessly to a local or remote server computer. The image features used in the
novelty detection and rarity mapping in prior work were based only upon RGB
or HSI color. In this work, we describe an image-compression technique of
Heidemann and Ritter that is capable of: (i) detecting novel textures in a series
of images, as well as of: (ii) alerting the user to the similarity of a new image to
a previously-observed texture. This image-compression technique has been
implemented and tested using our Astrobiology phone-cam system, which
employs Bluetooth communication to send images to a local netbook server in
the field for the image-compression analysis. By providing more advanced
capabilities for similarity detection and novelty detection, this imagecompression technique could be useful in giving more scientific autonomy to
robotic planetary rovers, and in assisting human astronauts in their geological
exploration.
References
Bartolo, A., et al. “The Cyborg Astrobiologist: Porting from a Wearable Computer to the Astrobiology Phonecam”, International Journal of Astrobiology, vol. 6, issue 4, pp. 255-261 (2007).
Gross, C., et al.“The Cyborg Astrobiologist: testing a novelty detection algorithm at the Mars Desert Research Station
(MDRS), Utah,” LPSCXLI, Lunar and Planetary Science Conf., Houston, Texas, extended abstract #2457 (2010).
Heidemann, G. and H. Ritter, “Compression for Visual Pattern Recognition”, Proc. of the Third International Symposium on
Communications, Control and Signal Processing (ISCCSP 2008), St. Julians, Malta, IEEE, pp. 1520-1523 (2008).
McGuire, P.C., et al. “The Cyborg Astrobiologist: First Field Experience”, International Journal of Astrobiology, vol. 3, issue
3, pp. 189-207 (2004).
McGuire, P.C., et al. “The Cyborg Astrobiologist: Scouting Red Beds for Uncommon Features with Geological
Significance”, International Journal of Astrobiology, vol. 4, issue 2, pp. 101-113 (2005).
McGuire, P.C., et al. “The Cyborg Astrobiologist: Testing a Novelty-Detection Algorithm on Two Mobile
Exploration Systems at Rivas Vaciamadrid in Spain and at the Mars Desert Research Station in
Utah”, International Journal of Astrobiology, Vol. 9, pp. 11-27 (2010).
Bonnici, A., et al. “The Cyborg Astrobiologist: Compressing Images for the Matching of Prior Textures and
for the Detection of Novel Textures “, European Planetary Science Congress, Rome (2010, submitted).