Classification of scene evolution patterns from Satellite Image Time Series based on spectro-temporal signatures

Costachioiu, Teodor; Lazarescu, V.; Datcu, Mihai

doi:10.1109/isscs.2011.5978721

Cited by 4 publications

(2 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, we proposed the digital interpretability is indicated by the spectral consistency of TBM images for the extraction of annual digital land cover information to answer the question of how many bands are used, which bands, and how many land cover classes can produce the optimal accuracy. The digital interpretability was measured by the accuracies (overall accuracy, user accuracy, and producer accuracy) of the classification results which were analyzed using master sample against the specified reference (Costa et al, 2018;Costachioiu et al, 2011;Danoedoro 2012;Gómez et al, 2016;Islam et al, 2016;Mausel, et al, 1990;Mitchell et al, 2011Mitchell et al, , 2012Peacock 2014;Zhongyang et al, 2011). The procedure to determine the digital interpretability of time-series annual Tile-Based Mosaic (TBM) of Landsat-8 OLI for land cover analysis image consisted of 4 (four) main processes.…”

Section: The Methodsmentioning

confidence: 99%

Digital Interpretability of Annual Tile-based Mosaic of Landsat-8 OLI for Time-series Land Cover Analysis in the Central Part of Sumatra

Dimyati

Danoedoro

HARTONO

et al. 2018

IJG

View full text Add to dashboard Cite

This paper presents an interoperability of annual tile-based mosaic (MTB) images, as well as a verification of the validity of the model for the time series land cover analysis purposes. The primary data used are MTB image of Landsat-8 of the central part of Sumatra, acquired from January 2015 to June 2017. The method used for the interoperability validation is the digital analysis of three-years time series land cover. The classification was performed with four band spectral groups. Training samples are taken from the image of 2016. The results are then reclassified to improve the overall accuracy score based on Jefferies Matusita (JM) distance. The interoperability can be measured by the average of overall accuracy (AOA) score, namely Good (scores > 80%), Fair (70.0% -79.9%), and Bad (< 70%). The results show that the use of the groups Bands 6-5-4-3-2 performs the consistent accuracy level of Good with an AOA score of 86% for six classes object. Whereas the use of the groups Bands 6-5-4-3-2, Bands 6-5-4, and Bands 6-5 shows the consistent accuracy level of Good up to four classes object with an AOA score of 89%, 82%, and 81%, respectively. It means that the annual mosaic image of MTB model is accepted for the image interoperability with an AOA score of > 80% for six and four classes object. Thus the most efficient for interoperability is the use of Bands 6-5 to analyze four class object of land cover.

show abstract

Section: The Methodsmentioning

confidence: 99%

Digital Interpretability of Annual Tile-based Mosaic of Landsat-8 OLI for Time-series Land Cover Analysis in the Central Part of Sumatra

Dimyati

Danoedoro

HARTONO

et al. 2018

IJG

View full text Add to dashboard Cite

show abstract

“…SITS have a far greater complexity than single satellite images, embedding spatial and temporal information. While supervised analysis method [1] can provide good results, with high user-semantic meaning, they depend on the size and quality of the training set, which is difficult and time-consuming to create. Often, in case of historical imagery, it is not possible to obtain the groundtruth information required for the creation on test and training data.…”

mentioning

confidence: 99%

Semantic Analysis of Satellite Image Time Series

Dumitru

Datcu

2021

Change Detection and Image Time Series Analysis 2

Self Cite

View full text Add to dashboard Cite

Large archives of satellite images have been created over time. The existence of these archives enables us to extract evolutions of the same of same geographic area over time, creating satellite image time series (SITS). As SITS represent an amount of information far greater than individual images, their analysis is complex and difficult. In this paper we propose a new unsupervised SITS analysis method based on the latent Dirichlet allocation (LDA) model, a hierarchical model originally developed for text analysis. In this model documents are represented as random mixture of latent topics, each topic being characterized by a distribution over words. This paper extends the use of LDA model for satellite image time series analysis by proposing a description language for SITS modeling according to the LDA model, and is applied on a SITS of 11 Landsat TM scenes acquired in 2007.

show abstract

Multitemporal Satellite Image Time Series analysis of urban development in Bucharest and Ilfov areas

Costachioiu

Constantinescu

Datcu

2014

2014 10th International Conference on Communications (COMM)

View full text Add to dashboard Cite

Classification of scene evolution patterns from Satellite Image Time Series based on spectro-temporal signatures

Cited by 4 publications

References 5 publications

Digital Interpretability of Annual Tile-based Mosaic of Landsat-8 OLI for Time-series Land Cover Analysis in the Central Part of Sumatra

Digital Interpretability of Annual Tile-based Mosaic of Landsat-8 OLI for Time-series Land Cover Analysis in the Central Part of Sumatra

Semantic Analysis of Satellite Image Time Series

Multitemporal Satellite Image Time Series analysis of urban development in Bucharest and Ilfov areas

Contact Info

Product

Resources

About