MACHINE LEARNING UNET-BASED SEGMENTATION OF SENTINEL-1A SATELLITE IMAGES

Journal Title: Engineering and Technology Journal - Year 2023, Vol 8, Issue 07

Abstract

Image segmentation is an area of study which has generated a lot of interest in engineering in the last few years. Segmentation of Sentinel 1A satellite images is an area that is not as common as that of its optical counterparts as a result of the appearance of its images. The focus of this paper is the segmentation of Sentinel-1A Synthetic Aperture Radar (SAR) satellite images using UNet, a Deep learning technique designed specifically for semantic segmentation of images. The model was developed with Python programming language in keras, which is a deep learning Python API running on the Tensorflow framework. The satellite images were acquired from the European Space Agency’s (ESA) Copernicus satellite acquisition hub. The performance evaluation was carried out with Jaccard Index or Intesection over Union (IoU) and Accuracy metrics. The IoU metric measures the number of pixels common between the target and prediction masks divided by the total number of pixels present across both masks while the Accuracy metric reports the percent of pixels in the image which were correctly classified. The results recorded in the evaluation had IoU as 0.42 and an Accuracy of 95%. This show a high performance of the model in segmenting images.

Authors and Affiliations

U. I. Nduanya1, K. A. Akpado2, S. N. Ogili3

Keywords

Related Articles

THE EFFECTS OF REIMPLEMENTING A BIOMETRIC ATTENDANCE MONITORING SYSTEM IN THE ELECTRONICS ENGINEERING DEPARTMENT AT DON HONORIO VENTURA STATE UNIVERSITY

Monitoring the attendance of staff and employees holds paramount importance in organizational settings. This can be accomplished either manually, using logbooks and daily time records, or automatically through advanced t...

Study on Geological Environmental Impact Assessment and Control Measures for Pingdingshan Tianan Six Coal Mine

The geological environment problems in Pingdingshan Tianan six coal mine, such as cave-in and fissure, have a serious impact on the local ecological environment. Through the detailed investigation of this mine, combinin...

Design of Rotary Motor Wiring Diagram for Tugboat Ship Maneuvering System Using Cam Switch Control

The maneuverability of tugboats is very necessary for narrow turning areas, so many tugboat maneuvering systems use motors which are currently applied with cam switches. It is important to plan a wiring system to anticip...

Optimization of Turning Process Performance Characteristics during Machining of AISI 304 Material

Turning process variables significantly affect the turning process performance. In the present work, Taguchi technique was applied to optimize the turning process performance during machining of AISI 304 material under c...

THE RARE EARTH ELEMENTS: AN IN-DEPTH EXPLORATION OF INDUSTRIAL UTILIZATION, RECYCLING POTENTIAL AND ENVIRONMENTAL RAMIFICATIONS

This comprehensive study delves into the extensive spectrum of applications attributed to rare earth elements (REEs), their potential for effective recycling, and the intricate environmental considerations entwined with...

Download PDF file
  • EP ID EP718671
  • DOI 10.47191/etj/v8i7.03
  • Views 19
  • Downloads 0

How To Cite

U. I. Nduanya1, K. A. Akpado2, S. N. Ogili3 (2023). MACHINE LEARNING UNET-BASED SEGMENTATION OF SENTINEL-1A SATELLITE IMAGES. Engineering and Technology Journal, 8(07), -. https://europub.co.uk/articles/-A-718671