Abstract

This paper aims to develop a fast dynamic-texture prediction method, using tools from non-linear dynamical modeling, and fast approaches for approximate regression. We consider dynamic textures to be described by patch-level non-linear processes, thus requiring tools such as delay-embedding to uncover a phase-space where dynamical evolution can be more easily modeled. After mapping the observed time-series from a dynamic texture video to its recovered phase-space, a time-efficient approximate prediction method is presented which utilizes locality-sensitive hashing approaches to predict possible phase-space vectors, given the current phase-space vector. Our experiments show the favorable performance of the proposed approach, both in terms of prediction fidelity, and computational time. The proposed algorithm is applied to shading prediction in utility scale solar arrays.

Original languageEnglish (US)
Title of host publication2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings
PublisherIEEE Computer Society
Pages2107-2111
Number of pages5
ISBN (Electronic)9781479970612
DOIs
StatePublished - Aug 29 2018
Event25th IEEE International Conference on Image Processing, ICIP 2018 - Athens, Greece
Duration: Oct 7 2018Oct 10 2018

Publication series

NameProceedings - International Conference on Image Processing, ICIP
ISSN (Print)1522-4880

Conference

Conference25th IEEE International Conference on Image Processing, ICIP 2018
CountryGreece
CityAthens
Period10/7/1810/10/18

Fingerprint

Textures
Vector spaces
Time series
Experiments

Keywords

  • Dynamic textures
  • Phase-space reconstruction
  • Shading prediction
  • Solar energy

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Katoch, S., Turaga, P., Spanias, A., & Tepedelenlioglu, C. (2018). Fast Non-Linear Methods for Dynamic Texture Prediction. In 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings (pp. 2107-2111). [8451479] (Proceedings - International Conference on Image Processing, ICIP). IEEE Computer Society. https://doi.org/10.1109/ICIP.2018.8451479

Fast Non-Linear Methods for Dynamic Texture Prediction. / Katoch, Sameeksha; Turaga, Pavan; Spanias, Andreas; Tepedelenlioglu, Cihan.

2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings. IEEE Computer Society, 2018. p. 2107-2111 8451479 (Proceedings - International Conference on Image Processing, ICIP).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Katoch, S, Turaga, P, Spanias, A & Tepedelenlioglu, C 2018, Fast Non-Linear Methods for Dynamic Texture Prediction. in 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings., 8451479, Proceedings - International Conference on Image Processing, ICIP, IEEE Computer Society, pp. 2107-2111, 25th IEEE International Conference on Image Processing, ICIP 2018, Athens, Greece, 10/7/18. https://doi.org/10.1109/ICIP.2018.8451479
Katoch S, Turaga P, Spanias A, Tepedelenlioglu C. Fast Non-Linear Methods for Dynamic Texture Prediction. In 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings. IEEE Computer Society. 2018. p. 2107-2111. 8451479. (Proceedings - International Conference on Image Processing, ICIP). https://doi.org/10.1109/ICIP.2018.8451479
Katoch, Sameeksha ; Turaga, Pavan ; Spanias, Andreas ; Tepedelenlioglu, Cihan. / Fast Non-Linear Methods for Dynamic Texture Prediction. 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings. IEEE Computer Society, 2018. pp. 2107-2111 (Proceedings - International Conference on Image Processing, ICIP).
@inproceedings{986230485e594d83ad6f8ff70abf9984,
title = "Fast Non-Linear Methods for Dynamic Texture Prediction",
abstract = "This paper aims to develop a fast dynamic-texture prediction method, using tools from non-linear dynamical modeling, and fast approaches for approximate regression. We consider dynamic textures to be described by patch-level non-linear processes, thus requiring tools such as delay-embedding to uncover a phase-space where dynamical evolution can be more easily modeled. After mapping the observed time-series from a dynamic texture video to its recovered phase-space, a time-efficient approximate prediction method is presented which utilizes locality-sensitive hashing approaches to predict possible phase-space vectors, given the current phase-space vector. Our experiments show the favorable performance of the proposed approach, both in terms of prediction fidelity, and computational time. The proposed algorithm is applied to shading prediction in utility scale solar arrays.",
keywords = "Dynamic textures, Phase-space reconstruction, Shading prediction, Solar energy",
author = "Sameeksha Katoch and Pavan Turaga and Andreas Spanias and Cihan Tepedelenlioglu",
year = "2018",
month = "8",
day = "29",
doi = "10.1109/ICIP.2018.8451479",
language = "English (US)",
series = "Proceedings - International Conference on Image Processing, ICIP",
publisher = "IEEE Computer Society",
pages = "2107--2111",
booktitle = "2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings",

}

TY - GEN

T1 - Fast Non-Linear Methods for Dynamic Texture Prediction

AU - Katoch, Sameeksha

AU - Turaga, Pavan

AU - Spanias, Andreas

AU - Tepedelenlioglu, Cihan

PY - 2018/8/29

Y1 - 2018/8/29

N2 - This paper aims to develop a fast dynamic-texture prediction method, using tools from non-linear dynamical modeling, and fast approaches for approximate regression. We consider dynamic textures to be described by patch-level non-linear processes, thus requiring tools such as delay-embedding to uncover a phase-space where dynamical evolution can be more easily modeled. After mapping the observed time-series from a dynamic texture video to its recovered phase-space, a time-efficient approximate prediction method is presented which utilizes locality-sensitive hashing approaches to predict possible phase-space vectors, given the current phase-space vector. Our experiments show the favorable performance of the proposed approach, both in terms of prediction fidelity, and computational time. The proposed algorithm is applied to shading prediction in utility scale solar arrays.

AB - This paper aims to develop a fast dynamic-texture prediction method, using tools from non-linear dynamical modeling, and fast approaches for approximate regression. We consider dynamic textures to be described by patch-level non-linear processes, thus requiring tools such as delay-embedding to uncover a phase-space where dynamical evolution can be more easily modeled. After mapping the observed time-series from a dynamic texture video to its recovered phase-space, a time-efficient approximate prediction method is presented which utilizes locality-sensitive hashing approaches to predict possible phase-space vectors, given the current phase-space vector. Our experiments show the favorable performance of the proposed approach, both in terms of prediction fidelity, and computational time. The proposed algorithm is applied to shading prediction in utility scale solar arrays.

KW - Dynamic textures

KW - Phase-space reconstruction

KW - Shading prediction

KW - Solar energy

UR - http://www.scopus.com/inward/record.url?scp=85062844644&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062844644&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2018.8451479

DO - 10.1109/ICIP.2018.8451479

M3 - Conference contribution

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 2107

EP - 2111

BT - 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings

PB - IEEE Computer Society

ER -