Abstract
This paper presents the analyses of texture variables from the image enhanced using super-resolution mapping. Two widely known super-resolution mapping techniques, pixel swapping and Hopfield neural network are used. The texture analyses include land cover patches of varying sizes, shapes, and spatial pattern of patches. A time series coarse MODIS 250 images are used to improve the representation of land cover patches and reduce the spatial variability. Results show that using a fusion of time series images and properly setting the weights for the Hopfield neural network produce superior accuracy of representing the texture of land cover mapping.
| Original language | English |
|---|---|
| Title of host publication | 2017 IEEE 8th Control and System Graduate Research Colloquium, ICSGRC 2017 - Proceedings |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 51-56 |
| Number of pages | 6 |
| ISBN (Electronic) | 9781538603802 |
| DOIs | |
| Publication status | Published - 17 Oct 2017 |
| Event | 8th IEEE Control and System Graduate Research Colloquium, ICSGRC 2017 - Shah Alam, Malaysia Duration: 4 Aug 2017 → 5 Aug 2017 |
Other
| Other | 8th IEEE Control and System Graduate Research Colloquium, ICSGRC 2017 |
|---|---|
| Country | Malaysia |
| City | Shah Alam |
| Period | 4/8/17 → 5/8/17 |
Fingerprint
Keywords
- Hopfield neural network
- Landscape pattern
- Pixel swapping
- Remote sensing
- Texture variable
ASJC Scopus subject areas
- Computer Science Applications
- Control and Systems Engineering
- Electrical and Electronic Engineering
- Control and Optimization
- Instrumentation
Cite this
Texture variable analysis for landscape patches represented using super-resolution mapping. / Muad, Anuar Mikdad.
2017 IEEE 8th Control and System Graduate Research Colloquium, ICSGRC 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 51-56 8070567.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Texture variable analysis for landscape patches represented using super-resolution mapping
AU - Muad, Anuar Mikdad
PY - 2017/10/17
Y1 - 2017/10/17
N2 - This paper presents the analyses of texture variables from the image enhanced using super-resolution mapping. Two widely known super-resolution mapping techniques, pixel swapping and Hopfield neural network are used. The texture analyses include land cover patches of varying sizes, shapes, and spatial pattern of patches. A time series coarse MODIS 250 images are used to improve the representation of land cover patches and reduce the spatial variability. Results show that using a fusion of time series images and properly setting the weights for the Hopfield neural network produce superior accuracy of representing the texture of land cover mapping.
AB - This paper presents the analyses of texture variables from the image enhanced using super-resolution mapping. Two widely known super-resolution mapping techniques, pixel swapping and Hopfield neural network are used. The texture analyses include land cover patches of varying sizes, shapes, and spatial pattern of patches. A time series coarse MODIS 250 images are used to improve the representation of land cover patches and reduce the spatial variability. Results show that using a fusion of time series images and properly setting the weights for the Hopfield neural network produce superior accuracy of representing the texture of land cover mapping.
KW - Hopfield neural network
KW - Landscape pattern
KW - Pixel swapping
KW - Remote sensing
KW - Texture variable
UR - http://www.scopus.com/inward/record.url?scp=85039929582&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85039929582&partnerID=8YFLogxK
U2 - 10.1109/ICSGRC.2017.8070567
DO - 10.1109/ICSGRC.2017.8070567
M3 - Conference contribution
AN - SCOPUS:85039929582
SP - 51
EP - 56
BT - 2017 IEEE 8th Control and System Graduate Research Colloquium, ICSGRC 2017 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
ER -