Hierarchical clustering algorithms for segmentation of multispectral images

Пестунов, И А; Rylov, S. A.; Berikov, Vladimir

doi:10.3103/s8756699015040020

Cited by 21 publications

(8 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Isachenko [16] was used as well. The regularities of the spatial organization of plant communities in connection with the dynamics of the relief on a cartographic model were studied on the basis of field interpretation of high-resolution satellite images (WorldView-2 with a resolution of 1.8 m) using a multispectral image segmentation algorithm, based on computationally efficient hierarchical clustering algorithm HECA [17,18], and spectral-texture segmentation algorithm ESEG [19]. These algorithms were developed within the framework of the grid-based and ensemble approaches and allow to extract hierarchically nested clusters of complex shapes, different sizes and densities, even in the case of intersecting clusters (in the space of spectral features).…”

Section: Methodsmentioning

confidence: 99%

Study of the diversity and mapping of xerophytic vegetation of the southeastern coast of Crimea peninsula using remote sensing data

Ermakov¹,

Пестунов²,

Korzhenevskiy³

et al. 2021

Spatial Data Processing for Monitoring of Natural and Anthropogenic Processes 2021

View full text Add to dashboard Cite

The study of diversity and ecological-phytocenotic mapping of the vegetation cover was carried out at the key area located in the eastern part of the Echki-Dag mountain range in the territory of the Lisya Bay Reserve (Eastern Crimea). A generalization of the classification and ecological patterns of vegetation was carried out to create a legend for a large-scale ecological-phytocenotic cartographic model (at the scale of 1:10000). The ecological-geomorphological series and combinations of xerophytic and mesoxerophytic plant communities indicating erosion-denudation processes on different substrates of the underlying parent rocks were the thematic basis of the cartographic model. The developed legend is based on the units of vegetation of the association rank obtained using the Braun – Blanquet method combined into ecological series in accordance with their position on the gradients of the leading ecological factors as well as on the hierarchy of phytochories determined by the categories of erosion-denudation relief of coastal slopes. The resulting vegetation map demonstrates the main regularities of the regional phyto-diversity and serves as the basis for assessing the resource potential of vegetation, its landscape-stabilizing and nature conservation value.

show abstract

Section: Methodsmentioning

confidence: 99%

Study of the diversity and mapping of xerophytic vegetation of the southeastern coast of Crimea peninsula using remote sensing data

Ermakov¹,

Пестунов²,

Korzhenevskiy³

et al. 2021

Spatial Data Processing for Monitoring of Natural and Anthropogenic Processes 2021

View full text Add to dashboard Cite

show abstract

“…Ensemble algorithms EMeanSC [17] and HECA [18] were designed using the first and the second ensemble construction method respectively. Basing on clustering algorithm CCA two ensemble algorithms were developed: CCAE (using first method) and ECCA [19] (using second method).…”

Section: Computationally Efficient Methods Of Clustering Ensemble Conmentioning

confidence: 99%

Computationally efficient methods of clustering ensemble construction for satellite image segmentation

Пестунов¹,

Rylov²,

Sinyavskiy³

et al. 2017

Collection of Selected Papers of the III International Conference on Information Technology and Nanotechnology

View full text Add to dashboard Cite

Combining multiple partitions into single ensemble clustering solution is a prominent way to improve accuracy and stability of clustering solutions. One of the major problems in constructing clustering ensembles is high computational complexity of the common methods. In this paper two computationally efficient methods of constructing ensembles of nonparametric clustering algorithms are introduced. They are based on the use of co-association matrix and subclusters. The results of experiments on synthetic and real datasets confirm their effectiveness and show the stability of the obtained solutions. The performance of the proposed methods allows to process large images including multispectral satellite data.

show abstract

“…Paper [14] suggested a method of spectral-textural segmentation. The advantage is the use of a single metric for both spectral and textural features in a heterogeneous feature space.…”

Section: Literature Review and Problem Statementmentioning

confidence: 99%

Devising a method for segmenting images acquired from space optical and electronic observation systems based on the Sine-Cosine algorithm

Khudov

Makoveichuk

Khudov

et al. 2022

EEJET

View full text Add to dashboard Cite

The object of this study is the process of segmentation of images acquired from space optoelectronic surveillance systems. The method to segment images from space optoelectronic surveillance systems based on the Sine-Cosine algorithm involves determining the threshold level; unlike the known ones, the following is carried out in it: – preliminary selection of red-green-blue color space brightness channels in the original image; – calculation of the maximum distance of movement of agents in the image in each brightness channel; – calculation of the values that determine the movement of agents in the image in each brightness channel; – determining the position of agents in the image using trigonometric functions of the sine and cosine in each brightness channel. An experimental study into segmenting images acquired from space optoelectronic surveillance systems based on the Sine-Cosine algorithm was carried out. It was found that the improved method of image segmentation based on the Sine-Cosine algorithm makes it possible to segment the images. In this case, objects of interest, snow-covered objects of interest, background objects, and undefined areas of the image (anomalous areas) are identified. The quality of image segmentation was assessed using the Sine-Cosine algorithm-based method. It was found that the improved segmentation method based on the Sine-Cosine algorithm reduces the segmentation error of the first kind by an average of 21 % and the segmentation error of the first kind by an average of 17 %. Methods of image segmentation can be implemented in software and hardware systems that process images acquired from space optoelectronic surveillance systems. Further studies may involve comparing the quality of segmentation by the method based on the Sine-Cosine algorithm with segmentation methods based on evolutionary algorithms (for example, genetic ones).

show abstract

Hierarchical clustering algorithms for segmentation of multispectral images

Cited by 21 publications

References 12 publications

Study of the diversity and mapping of xerophytic vegetation of the southeastern coast of Crimea peninsula using remote sensing data

Study of the diversity and mapping of xerophytic vegetation of the southeastern coast of Crimea peninsula using remote sensing data

Computationally efficient methods of clustering ensemble construction for satellite image segmentation

Devising a method for segmenting images acquired from space optical and electronic observation systems based on the Sine-Cosine algorithm

Contact Info

Product

Resources

About