Jove
Visualize
Contact Us

Related Experiment Videos

Environmental mapping based on spatial variability.

Nelley Kovalevskaya1, Vladimir Pavlov

  • 1Institute for Water and Environmental Problems, SB RAS 105 Papanintsev St., 656099 Barnaul, Russia. knm@iwep.ab.ru, knm@santafe.edu

Journal of Environmental Quality
|October 10, 2002
PubMed
Summary

This study introduces novel probabilistic models for environmental mapping using remotely sensed data. These models improve image segmentation and land cover mapping by incorporating spatial attributes for more accurate environmental state representation.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Absolute chronology of the Early Palaeolithic Karatau Culture in Central Asia.

Nature communications·2026
Same author

Development of otorhinolaryngology (ORL) in Bulgaria for the period 1880-1920.

The Journal of laryngology and otology. Supplement·2005
See all related articles
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Area of Science:

  • Environmental Science
  • Remote Sensing
  • Geographic Information Systems (GIS)

Background:

  • Environmental mapping utilizes remotely sensed data to identify land use and landscape features.
  • Traditional statistical and heuristic image classification methods have limitations in accounting for spatial variability and achieving optimal solutions.
  • Accurate environmental mapping is crucial for understanding landscape dynamics and informing land management decisions.

Purpose of the Study:

  • To present novel probabilistic models for environmental mapping and image segmentation.
  • To enhance the accuracy of land cover mapping by considering spatial attributes.
  • To segment real-world images more effectively using advanced modeling techniques.

Main Methods:

  • Development of probabilistic models for piecewise-homogeneous images, treating image-map pairs as Markov random fields.

Related Experiment Videos

  • Utilizing a joint Gibbs probability distribution for images and land cover maps.
  • Parameter estimation via stochastic approximation techniques, with experimental convergence analysis.

    • Main Results:

    • The proposed models effectively segment real images and generate accurate environmental maps.
    • Incorporating spatial attributes proved necessary for improving segmentation in areas with spatial data variations.
    • Experimental validation demonstrated the models' capability in segmenting both simulated and real-world data.

    Conclusions:

    • Novel probabilistic models offer a significant advancement in environmental mapping and image segmentation.
    • The integration of spatial attributes enhances the precision of land cover classification.
    • These methods provide a robust framework for analyzing remotely sensed data for environmental applications.