 Satellite image segmentation using UNet++ with Vgg19 deep learning modelYaragorla Raju () and M. Narayana () Edelweiss Applied Science and Technology, 2024, vol. 8, issue 6, 5707-5722 Abstract: Satellite image segmentation is an essential step in many applications, including urban planning, disaster response and environmental monitoring. The problem though is that existing methods suffer from high failure rates because of the intrinsic complexity and variation found in satellite images. This research uses deep learning UNet++ and Vgg19 models to construct advanced satellite image segmentation method as we propose a brand-new approach of our own. In this study, the effective segmentation method combines the powerful feature extraction capability of Vgg19 model which is improved version based on Unet++ approach and data route aggregation module are adopted to provide complex detail in satellite images and contextual information. Implementing deep network models using known architectures will help increase accuracy and efficiency in situations where training datasets can be limited. Apparently, the approach was tested and bench-marked over a set of datasets for several visual contexts confirmed by extensive testing which resulted in an increased precision, recall along with F1 scores. Keywords: Deep learning; Satellite image segmentation; Semantic segmentation; Unet; VGG19. (search for similar items in EconPapers) Downloads: (external link) Related works: Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text Persistent link: https://EconPapers.repec.org/RePEc:ajp:edwast:v:8:y:2024:i:6:p:5707-5722:id:3242 Access Statistics for this article More articles in Edelweiss Applied Science and Technology from Learning Gate |
Is your work missing from RePEc? Here is how to contribute.
Questions or problems? Check the EconPapers FAQ or send mail to .
EconPapers is hosted by the
School of Business at Örebro University.