A Semi-Supervised Algorithm to Map Major Vegetation Zones Using Satellite Hyperspectral Data

Ekanayake, E. M. M. B.; Rathnayake, A. R.M.A.N.; Vithana, S. S. P.; Herath, Vijitha; Godaliyadda, G. M. R. I.; Ekanayake, M. P. B.

doi:10.1109/whispers.2018.8747025

Cited by 11 publications

(10 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first stage of the algorithm follows a similar approach to what is discussed by Ekanayake et al (2018) and Vithana et al (2019). A straightforward method, which considers the vector representation of spectral characteristics of a pixel, has been used.…”

Section: Classification Algorithm -Sub Component Analysismentioning

confidence: 99%

“…The intention of the initial stage was to classify the pixels in the selected image region under its underlying classes. Moreover, the algorithm discussed by Ekanayake et al (2018) identifies the pixels that contain more than one component (mixed pixels) along with their percentages. Since this algorithm requires normalised data, the standardisation mentioned in the earlier section is essential.…”

Section: Classification Algorithm -Sub Component Analysismentioning

confidence: 99%

See 1 more Smart Citation

Mapping ilmenite deposit in Pulmudai, Sri Lanka using a hyperspectral imaging-based surface mineral mapping method

Vithana

Ekanayake

Rathnayake

et al. 2019

J. Natn. Sci. Foundation Sri Lanka

View full text Add to dashboard Cite

Mineral detection using remote sensing techniques is important since it saves the time and effort of carrying out manual land surveys. In this paper a novel algorithm, which can be used to detect ilmenite using hyperspectral image analysis is discussed. To investigate this task, a hyperspectral image obtained from the Earth Observing-1 (EO-1) satellite's Hyperion sensor was used. In the proposed algorithm, first, principal component analysis (PCA) was used for dimensionality reduction and an Euclidean distancebased method was used to extract the pixels containing soil. Thereafter, lab spectral data of typical ilmenite deposits were considered as the reference and a correlation factor analysis was carried out to determine the soil pixels, which are most likely to contain ilmenite and most unlikely to contain ilmenite. Using these two sets of pixels, a training set was constructed to apply Fisher's discriminant analysis (FDA) in order to separate the dataset into two distinct classes-ilmenite and non-ilmenite. Based on the spectral similarity, each pixel of the image was classified under one of these classes. This paper also introduces a probability-based approach to obtain results that are more accurate. A probability density function was designed considering the spatial distribution of the mineral. Thereafter, classification was done considering the probability measure as well. Lab tests performed on the soil samples collected from the locations, which were detected by the algorithm validate that the algorithm is accurate.

show abstract

Section: Classification Algorithm -Sub Component Analysismentioning

confidence: 99%

Section: Classification Algorithm -Sub Component Analysismentioning

confidence: 99%

Mapping ilmenite deposit in Pulmudai, Sri Lanka using a hyperspectral imaging-based surface mineral mapping method

Vithana

Ekanayake

Rathnayake

et al. 2019

J. Natn. Sci. Foundation Sri Lanka

View full text Add to dashboard Cite

show abstract

“…The parameter σ can be identified as a parameter which controls the level of zooming in and out of the data set when performing spectral clustering. 4 When σ decreases, the degree of affinity between a given pair of points decreases. 4 This is similar to zooming into the data space where the distance between two points seems to appear much larger, lowering the degree of affinity.…”

Section: ) Generating the Distance Matrixmentioning

confidence: 99%

“…4 When σ decreases, the degree of affinity between a given pair of points decreases. 4 This is similar to zooming into the data space where the distance between two points seems to appear much larger, lowering the degree of affinity. Similarly, an increase in σ can be explained as the process of zooming out of the data space.…”

Section: ) Generating the Distance Matrixmentioning

confidence: 99%

“…Hence Hyperspectral Imaging (HSI) is widely used in many applications, such as remote sensing, food quality testing, medical imaging and surveillance. [1][2][3][4] In order to detect the finer details in a given image, a number of classification algorithms for HSI have been developed recently, which include pre-processing techniques, clustering algorithms, probabilistic frameworks etc.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive hierarchical clustering for hyperspectral image classification: Umbrella Clustering

Vithana

Ekanayake

Rathnayake

et al. 2019

J. Spectral Imaging

Self Cite

View full text Add to dashboard Cite

Hyperspectral Imaging (HSI) utilises the reflectance information of a large number of contiguous spectral bands to solve various problems. However, the relative proximity of spectral signatures among classes can be exploited to generate an adaptive hierarchical structure for HSI classification. This enables a level by level optimisation for clustering at each stage of the hierarchy. The Umbrella Clustering algorithm, introduced in this work, utilises this premise to significantly improve performance compared to non-hierarchical algorithms which attempt to optimise clustering globally. The key feature of the proposed methodology is that, unlike existing hierarchical algorithms which rely on fixed or supervised structures, the proposed method exploits a mechanism in spectral clustering to generate a self-organised hierarchy. The algorithm gradually zooms into the feature space to identify levels of clustering at each stage of the hierarchy. The results further demonstrate that the generated structure tallies with human perception. In addition, an improvement to Linear Discriminant Analysis (LDA) is also introduced to further improve performance. This modification maximises the pairwise class separation in the feature space. The entire algorithm includes this modified LDA step which requires a certain amount of class information in terms of features, at the training phase. The classification algorithm which incorporates all novel concepts was tested on the HSI data set of Pavia University as well the database of Common Sri Lankan Spices and Adulterants in order to assess the versatility of the algorithm.

show abstract

A critical survey of GEOBIA methods for forest image detection and classification

Kwenda,

Gwetu,

Fonou-Dombeu

2023

Geocarto International

View full text Add to dashboard Cite

A Semi-Supervised Algorithm to Map Major Vegetation Zones Using Satellite Hyperspectral Data

Cited by 11 publications

References 6 publications

Mapping ilmenite deposit in Pulmudai, Sri Lanka using a hyperspectral imaging-based surface mineral mapping method

Mapping ilmenite deposit in Pulmudai, Sri Lanka using a hyperspectral imaging-based surface mineral mapping method

Adaptive hierarchical clustering for hyperspectral image classification: Umbrella Clustering

A critical survey of GEOBIA methods for forest image detection and classification

Contact Info

Product

Resources

About