Road extraction in remote sensed images using stochastic geometry framework

Computer Science – Information Theory

Scientific paper

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

Telemetry: Remote Control, Remote Sensing, Radar, Image Processing, Information Theory And Communication Theory

Scientific paper

In this work we use stochastic geometry theory and Monte Carlo Markov Chains dynamics to extract roads in remote sensed images. The main hypothesis for this new approach is that the road network is a thin network which is composed of connected segments. To simulate and to extract thin networks in images we construct a Gibbs point process. The energy of this Gibbs process has two components: the external and the internal energies. The external energy gives the location of the network. The internal energy (Candy model) penalizes the segments which are not connected and not well aligned. The optimum configuration of the segments is estimated by the global minimum of the total energy of the Gibbs process. For the minimization procedure we design a simulated annealing algorithm based on a Metropolis-Hastings dynamics including Reversible Jumps. Finally, some results are shown on satellite images. .

No associations

LandOfFree

Say what you really think

Search LandOfFree.com for scientists and scientific papers. Rate them and share your experience with other people.

Rating

Road extraction in remote sensed images using stochastic geometry framework does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Road extraction in remote sensed images using stochastic geometry framework, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Road extraction in remote sensed images using stochastic geometry framework will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFWR-SCP-O-924097

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.