Land-cover change detection using local feature descriptors extracted from spectral indices

Espinoza-Molina, Daniela; Bahmanyar, Reza; Dı́az-Delgado, Ricardo; Bustamante, Javier; Datcu, Mihai

doi:10.1109/igarss.2017.8127358

Cited by 7 publications

(12 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1. The results were then validated based on the previous studies of land-cover changes in the Doñana National Park [1], [8], [10]- [13]. Moreover, the results were qualitatively evaluated by a group of experts, knowledgeable on the land-cover of the Doñana National Park.…”

Section: Resultsmentioning

confidence: 88%

Land-cover evolution class analysis in Image Time Series of Landsat and Sentinel-2 based on Latent Dirichlet Allocation

Espinoza-Molina

Bahmanyar

Datcu

et al. 2017

2017 9th International Workshop on the Analysis of Multitemporal Remote Sensing Images (MultiTemp)

Self Cite

View full text Add to dashboard Cite

Satellite Image Time Series (SITS) are widely used in monitoring the Earth's changes for various applications such as land-cover evolution analysis. In this paper, we propose an approach based on Latent Dirichlet Allocation (LDA) which considers spatial and spectral information to measure the landcover changes in multispectral SITS. For our experiments, we focus on the vegetation dynamics of the Doñana National Park (in southwestern Spain) using a Landsat and a Sentinel-2 SITS dataset. The proposed approach represents each image by Normalized Difference Vegetation Index (NDVI) and tiles it into smaller patches. The patches are then modeled as Bag-of-Words (BoW) and LDA is applied to them in order to discover the latent structure of the image. The divergence between the latent structures of any two consecutive images is then considered as the measure of change. Results show that the changes measured by the proposed approach can represent the vegetation dynamics of the region of interest. Moreover, comparing the results obtained from the two datasets demonstrates that using highlevel information allows the proposed approach to measure the changes independent of the sensor. This will support long-term monitoring through combining various available data.

show abstract

Section: Resultsmentioning

confidence: 88%

Land-cover evolution class analysis in Image Time Series of Landsat and Sentinel-2 based on Latent Dirichlet Allocation

Espinoza-Molina

Bahmanyar

Datcu

et al. 2017

2017 9th International Workshop on the Analysis of Multitemporal Remote Sensing Images (MultiTemp)

Self Cite

View full text Add to dashboard Cite

show abstract

“…In fact, LCCD can be used for various purposes including monitoring and management of pollution [11], desertification [12], and deforestation [13]. Recently, several LCCD techniques have been proposed in the literature [14]- [17]. In [14], Zhu et al proposed a change detection and classification algorithm based on threshold derived from all spectral bands of the Landsat data.…”

Section: Introductionmentioning

confidence: 99%

“…In [16], Mayes et al introduced a linear spectral mixture analysis approach with Landsat data applied for forest changes assessment. In [17], Espinoza-Molina et al used local features extracted from spectral indices using a clustering algorithm. The LCCD is then performed by counting the frequency of the assignments of a changed pixel to a specific class along the time series.…”

Section: Introductionmentioning

confidence: 99%

A Machine Learning-Based Approach for Land Cover Change Detection Using Remote Sensing and Radiometric Measurements

et al. 2019

View full text Add to dashboard Cite

“…In fact, LCCD can be used for various purposes including monitoring and management of pollution [3], desertification [4], and deforestation [5]. Recently, several LCCD techniques have been proposed in the literature [6]- [9]. In [6], Zhu et al proposed a change detection and classification algorithm based on threshold derived from all spectral bands of the Landsat data.…”

Section: Introductionmentioning

confidence: 99%

“…In [8], Mayes et al introduced a linear spectral mixture analysis approach with Landsat data applied for forest changes assessment. In [9], Espinoza-Molina et al used local features extracted from spectral indices using a clustering algorithm. The LCCD is then performed by counting the frequency of the assignments of a changed pixel to a specific class along the time series.…”

Section: Introductionmentioning

confidence: 99%

Monitoring land-cover changes by combining a detection step with a classification step

Harrou

Zerrouki

Sun

et al. 2018

2018 IEEE Symposium Series on Computational Intelligence (SSCI)

View full text Add to dashboard Cite

CitationHarrou F, Zerrouki N, Sun Y, Hocini L (2018) Monitoring landcover changes by combining a detection step with a classification step. 2018 IEEE Symposium Series on Computational Intelligence (SSCI). Available: http://dx.Abstract-An approach merging the Hotelling T 2 control scheme with weighted random forest classifier is proposed and used in the context of detecting land cover changes via remote sensing and radiometric measurements. Hotelling T 2 procedure is introduced to identify features corresponding to changed areas. However, T 2 scheme is not able to separate real from false changes. To tackle this limitation, the weighted random forest algorithm, which is an efficient classification technique for unbalanced problems, has been successfully applied on features of the detected pixels to recognize the type of change. The performance of the algorithm is evaluated using SZTAKI AirChange benchmark data, results show that the proposed detection scheme succeeds to appropriately identify changes to land cover. Also, we compared the proposed approach to that of the conventional algorithms (i.e., neural network, random forest, support vector machine and k-nearest neighbors) and found improved performance.

show abstract

Land-cover change detection using local feature descriptors extracted from spectral indices

Cited by 7 publications

References 9 publications

Land-cover evolution class analysis in Image Time Series of Landsat and Sentinel-2 based on Latent Dirichlet Allocation

Land-cover evolution class analysis in Image Time Series of Landsat and Sentinel-2 based on Latent Dirichlet Allocation

A Machine Learning-Based Approach for Land Cover Change Detection Using Remote Sensing and Radiometric Measurements

Monitoring land-cover changes by combining a detection step with a classification step

Contact Info

Product

Resources

About