Determination of the number of clusters on images from space optic-electronic observation systems using the k-means algorithm

Abstract

The object of research is the process of clustering images from space optical-electronic surveillance systems. The main hypothesis of the study assumed that experimental studies would make it possible to determine the number of clusters on images from space optical-electronic surveillance systems when using the k-means algorithm. The method of clustering images from space optical-electronic surveillance systems using the k-means algorithm, unlike the known ones, implies: – splitting the source image into Red-Green-Blue brightness channels; – determination of the Euclidean distance between pixels; – distribution of the entire set of image pixels into clusters; – recalculation of "centers" of each subset; – reassignment of new "centers" of each cluster; – minimization of the total intracluster variance. Experimental studies were conducted on the clustering of the original image using the k-means method at different values of k. It was established that with an increase in the value of k, the visual quality of clustering improves, and it is possible to visually determine a larger number of clusters in the images. To determine the number of clusters, the sum of clustering errors of type 1 and 2 at different values of k was evaluated. It was established that when the value of k increases, the sum of errors of the 1st and 2nd kind initially decreases exponentially. A further increase in the value of k does not lead to a significant decrease in errors of the 1st and 2nd kind. It was established that for a typical image from the space optical-electronic observation system, the value of k in the clustering method based on the k-means algorithm should be equal to 4. At the same time, the sum of errors of the 1st and 2nd kind is 31.3 %. Further research is directed to the development of clustering methods that reduce the sum of errors of the 1st and 2nd kind

Determination of the number of clusters of normalized vegetation indices using the k-means algorithm

“…On the basis of our research, a conceptual solution to the analysis of the composition of agricultural crops is proposed using the clustering of digitized remote sensing data of the North-Kazakhstan Agricultural Experiment Station, which are used to determine the quality of photosynthetically active biomass of agricultural crops. Determining the number of clusters by the proposed method will make it possible, in comparison with studies [8][9][10][11][12][13][14][15], to calculate the most favorable cluster in the phenological phase for increasing the productivity of spring wheat in the North Kazakhstan region.…”

“…The above-mentioned vegetation indices taking into account individual characteristics made it possible, in comparison with studies [10][11][12][13][14][15][16][17], to obtain the most effective analysis of the fields of the North Kazakhstan region.…”

“…The authors of [12], using the k-means algorithm, experimentally demonstrated the determination of the number of clusters in images of space optical-electronic observation systems. The disadvantage of the work is that the assessment of the state of crops using the clustering procedure is based only on the applied aspect of the k-means method; the work Calculation of normalized NDVI coefficients in geosystems is performed using a raster calculator using pre-loaded data from the field under study.…”