BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:EagleEye: Feature Extraction from Satellite Images Using a Hybrid 
 Computing Architecture
DTSTART;VALUE=DATE-TIME:20121018T134500Z
DTEND;VALUE=DATE-TIME:20121018T150000Z
DTSTAMP;VALUE=DATE-TIME:20261011T050448Z
UID:indico-contribution-172@indico.ipb.ac.rs
DESCRIPTION:Speakers: Razvan Dobre (University Politehnica of Bucharest)\n
 Feature extraction from satellite images has become a wide area of interes
 t in the last two decades with the increase in the number of commercial ea
 rth observation satellites. This work focuses on extracting roads and citi
 es from true color multi-spectral images that suffer from different qualit
 y problems like blurriness\, increased amount of noise or abnormal color v
 ariations. To assist in the feature extraction process we extract city loc
 ation information from almost 200 military maps. We present an approach fo
 r automatic and independent road detection in satellite images\, an automa
 tic city detection process in military maps and a semi-automatic (assisted
 ) method of detecting street layout inside cities in satellite images. We 
 also evaluate the accuracy and performance of our implementation by tests 
 that are done using a parallel infrastructure running over different types
  of blades inside an HPC computing cluster.\n\nhttps://events.saifa.rs/eve
 nt/291/contributions/172/
LOCATION:National Library of Serbia
URL:https://events.saifa.rs/event/291/contributions/172/
END:VEVENT
END:VCALENDAR