Classication of Agricultural Fields in Satellite Images Using Two-Dimensional Hidden Markov Models
Fil: Baumgartner, J. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales; Argentina.
| Main Authors: | , , , |
|---|---|
| Format: | conferenceObject |
| Language: | eng |
| Published: |
2021
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/11086/21531 |
| _version_ | 1801215179843698688 |
|---|---|
| author | Baumgartner, J. Giménez, J. Pucheta, J. Flesia, A. G. |
| author_facet | Baumgartner, J. Giménez, J. Pucheta, J. Flesia, A. G. |
| author_sort | Baumgartner, J. |
| collection | Repositorio Digital Universitario |
| description | Fil: Baumgartner, J. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales; Argentina. |
| format | conferenceObject |
| id | rdu-unc.21531 |
| institution | Universidad Nacional de Cordoba |
| language | eng |
| publishDate | 2021 |
| record_format | dspace |
| spelling | rdu-unc.215312021-11-17T12:53:33Z Classication of Agricultural Fields in Satellite Images Using Two-Dimensional Hidden Markov Models Baumgartner, J. Giménez, J. Pucheta, J. Flesia, A. G. Satellite farming pattern recognition image segmentation hidden Markov models Fil: Baumgartner, J. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales; Argentina. Fil: Giménez, J. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación; Argentina. Fil: Pucheta, J. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales; Argentina. Fil: Flesia, A.G. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación; Argentina. Fil: Flesia, A. G. Universidad Tecnológica Nacional. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Image segmentation is a key competence for many real life applications such as precision agriculture. In this work we present an approach to classify agricultural fields in noisy satellite images. We start with the Markovian neighborhood hypothesis from where on we derive a general two-dimensional hidden Markov model (2D-HMM). To make the 2D-HMM feasible we apply the Path-Constrained Variable-State Viterbi Algorithm (PCVSVA) which allows us to approximate the optimal hidden state map. We evaluate the PCVSVA for a Landsat image of the province of C´ordoba, Argentina and a synthetic satellite image. In both cases we use Cohen’s κb coefficient to compare the PCVSVA and the solution obtained by maximum likelihood (ML) to show the effectiveness of 2D-HMM of solving image segmentation tasks. Fil: Baumgartner, J. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales; Argentina. Fil: Giménez, J. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación; Argentina. Fil: Pucheta, J. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales; Argentina. Fil: Flesia, A.G. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación; Argentina. Fil: Flesia, A. G. Universidad Tecnológica Nacional. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Sistemas de Automatización y Control 2021-11-15T18:13:01Z 2021-11-15T18:13:01Z 2013 conferenceObject 1852-4850 1852-4850 http://hdl.handle.net/11086/21531 eng Attribution-NonCommercial-ShareAlike 4.0 International https://creativecommons.org/licenses/by-nc-sa/4.0/ Electrónico y/o Digital |
| spellingShingle | Satellite farming pattern recognition image segmentation hidden Markov models Baumgartner, J. Giménez, J. Pucheta, J. Flesia, A. G. Classication of Agricultural Fields in Satellite Images Using Two-Dimensional Hidden Markov Models |
| title | Classication of Agricultural Fields in Satellite Images Using Two-Dimensional Hidden Markov Models |
| title_full | Classication of Agricultural Fields in Satellite Images Using Two-Dimensional Hidden Markov Models |
| title_fullStr | Classication of Agricultural Fields in Satellite Images Using Two-Dimensional Hidden Markov Models |
| title_full_unstemmed | Classication of Agricultural Fields in Satellite Images Using Two-Dimensional Hidden Markov Models |
| title_short | Classication of Agricultural Fields in Satellite Images Using Two-Dimensional Hidden Markov Models |
| title_sort | classication of agricultural fields in satellite images using two dimensional hidden markov models |
| topic | Satellite farming pattern recognition image segmentation hidden Markov models |
| url | http://hdl.handle.net/11086/21531 |
| work_keys_str_mv | AT baumgartnerj classicationofagriculturalfieldsinsatelliteimagesusingtwodimensionalhiddenmarkovmodels AT gimenezj classicationofagriculturalfieldsinsatelliteimagesusingtwodimensionalhiddenmarkovmodels AT puchetaj classicationofagriculturalfieldsinsatelliteimagesusingtwodimensionalhiddenmarkovmodels AT flesiaag classicationofagriculturalfieldsinsatelliteimagesusingtwodimensionalhiddenmarkovmodels |