Version 1
: Received: 10 November 2022 / Approved: 14 November 2022 / Online: 14 November 2022 (01:20:07 CET)
How to cite:
Selea, T.; Iuhasz, G.; Neagul, M. A Study of Deep Learning Model Performance for Remote Sensing Image Segmentation. Preprints2022, 2022110226. https://doi.org/10.20944/preprints202211.0226.v1
Selea, T.; Iuhasz, G.; Neagul, M. A Study of Deep Learning Model Performance for Remote Sensing Image Segmentation. Preprints 2022, 2022110226. https://doi.org/10.20944/preprints202211.0226.v1
Selea, T.; Iuhasz, G.; Neagul, M. A Study of Deep Learning Model Performance for Remote Sensing Image Segmentation. Preprints2022, 2022110226. https://doi.org/10.20944/preprints202211.0226.v1
APA Style
Selea, T., Iuhasz, G., & Neagul, M. (2022). A Study of Deep Learning Model Performance for Remote Sensing Image Segmentation. Preprints. https://doi.org/10.20944/preprints202211.0226.v1
Chicago/Turabian Style
Selea, T., Gabriel Iuhasz and Marian Neagul. 2022 "A Study of Deep Learning Model Performance for Remote Sensing Image Segmentation" Preprints. https://doi.org/10.20944/preprints202211.0226.v1
Abstract
Deep Learning is an extremely important research topic in Earth Observation. Current use-cases range from semantic image segmentation, object detection to more common problems found in computer vision such as object identification. Earth Observation is an excellent source for different types of problems and data for Machine Learning in general and Deep Learning in particular. It can be argued that both Earth Observation and Deep Learning as fields of research will benefit greatly from this recent trend of research. In this paper we take several state of the art Deep Learning network topologies and provide a detailed analysis of their performance for semantic image segmentation for building footprint detection. The dataset used is comprised of high resolution images depicting urban scenes. We focused on single model performance on simple RGB images. In most situations several methods have been applied to increase the accuracy of prediction when using deep learning such as ensembling, alternating between optimisers during training and using pretrained weights to bootstrap new models. These methods although effective, are not indicative of single model performance. Instead, in this paper, we present different topology variations of these state of the art topologies and study how these variations effect both training convergence and out of sample, single model, performance.
Keywords
deep learning; convolutional neural networks; remote sensing
Subject
Computer Science and Mathematics, Analysis
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
