Fourth Edition of the International Conference on Research in Applied Mathematics and Computer Science ICRAMCS 2022
 March 24-25-26, 2022
Online and Face-to-Face Conference

ICRAMCS, 4 (2022) | Proceedings ISSN: 2605-7700

Research Communication | Open Access
Volume 2022 | Communication ID 253
Comparative Study of Semantic Segmentation Methods: Drone Images as a Case Study
Ilyas Bentachfine, Mohammed Erritali, Meryem Ameur
Academic Editor: Youssef EL FOUTAYENI
Received
Accepted
Published
January 28, 2022
March 03, 2224
April 15, 2224

Abstract: In this work, we propose a comparative study between some semantic segmentation methods, especially, Convolutional Neural Network methods. These techniques are able to segment the images quickly with a high precision. Our objective is to compare the semantic segmentation images among Fully Convolutional Network (FCN) [1], UNet [2,3], Pyramid scene parsing network (PSPNet)[4] and other performant models to segment images in terms of quality and execution time. We found that UNet provides the best quality with a less execution time. We applied those approaches to segment semantic drone dataset ...