Segmentation Analysis Using Particle Swarm Optimization - Self Organizing Map Algorithm and Classification of Remote Sensing Data for Agriculture
Remote sensing (RS) has become one of the vital approaches to get the information directly from the earth’s surface. In recent years, with the event of environmental informatics, RS information has contend a crucial role in several areas of analysis, like atmosphere science, ecology, soil pollution, etc. When monitoring, the multispectral satellite data problem are vital once. Therefore, in our analysis, automatic segmentation has aroused a growing interest of researchers over the past few years within the multispectral RS system. To beat existing shortcomings, we provide automatic semantic segmentation while not losing significant information. So, we use SOM for segmentation functions. Additionally, we’ve got planned a particle swarm improvement (PSO) algorithmic rule for directly sorting out cluster boundaries from SOM. The most objective of this work is to get a complete accuracy of over eighty fifth (OA> 85%). Deep Learning (DL) could be a powerful image process technique, together with RS image.
KeywordsDeep Learning Self organizing map Change detection Remote sensing Crop classification
- 10.Focareta, M., Marcuccio, S., Votto, C., Ullo, S. L.: Combination of Landsat 8 and Sentinel 1 data for the characterization of a site of interest. a case study: the royal palace of Caserta, October 2015Google Scholar