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
- EP ID EP718671
- DOI 10.47191/etj/v8i7.03
- Views 53
- Downloads 0
Sustainable Seismic Practices in Offshore Exploration: A Conceptual Model for Minimizing Environmental Impact While Enhancing Resource Recovery
Offshore exploration for hydrocarbon resources often entails significant environmental challenges, including potential disruptions to marine ecosystems and water quality. This paper presents a conceptual model for sustai...
DYNAMIC RESOURCE ALLOCATION ALGORITHM FOR OFDM SYSTEMS (LTESTANDARD)
This paper proposes a resource allocation algorithm for MIMO-OFDM systems (LTE standard). The algorithm is developed for orthogonal frequency division multiple access (OFDMA) system with frequency hopping and adaptive su...
IMAGE ENHANCEMENT OF HUMAN FINGERPRINTS USING FEATURE EXTRACTION & MATCHING TECHNIQUES
Biometrics, which mentions to identification based on physical or behavioural characteristics, is being progressively adopted to provide positive identification with a high degree of confidence. Among all biometric techn...
ADVANCEMENTS IN HEALTHCARE THROUGH DESIGN AND DEVELOPMENT OF AN INTELLIGENT INTRAVENOUS BAG MONITORING AND ALERT SYSTEM
The Intelligent Intravenous Bag Monitoring and Alert System is a device designed for nighttime patient monitoring, allowing nurses to focus on other duties and prevent air bubbles from entering the patient's bloodstream....
OPTIMIZATION OF THE REMOVAL OF ANTIBIOTICS FROM PHARMACEUTICAL WASTEWATER ON ACTIVATED CARBON USING RESPONSE SURFACE METHODOLOGY
The improper disposal of antibiotics by pharmaceutical industries poses significant risks to both human health and the ecosystem. Although the concentration of these antibiotics in pharmaceutical wastewater may appear in...