• Home
  • Search
  • Improving remote sensing scene classification using quality-based data augmentation
  • Cite Icon8
  • https://doi.org/10.1080/01431161.2023.2184213Copy DOI Icon

Improving remote sensing scene classification using quality-based data augmentation

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

ABSTRACT This study presents an improved data augmentation technique for the classification of remote sensing (RS) scenes. The method is called Quality-based Sample Selection (QSS) data augmentation technique. It is based on generating a large number of samples using geometric transformations and then selecting the best ones based on a quality criterion. Sample images are generated online, i.e. during training of the convolutional neural network (CNN) model. For each training sample image, a few images are generated randomly using a set of geometric transformations. Then, the generated images are passed to the CNN model being trained, and the predicted probabilities are used to evaluate the quality of the images. The motivation behind this research is that we aim to augment the training set with new images that will benefit the learning of the CNN model. Therefore, an objective method to evaluate the quality of the new images is the CNN model itself. The image with the best criteria score is used to augment the training set. Several quality criteria based on the prediction probabilities of the CNN model are considered including entropy, breaking-ties and our own proposed criteria called True Label Probability (TLP). QSS is tested on five common RS scene classification datasets: UCMerced, Optimal31, RSSCN7, AID and NWPU-RS45. It has outperformed all previous methods except for one case involving NWPU-RS45 dataset. For the 10%–90% train–test split, QSS achieved 94.51, 81.72, 89.89, 94.09 and 93.98, respectively, for the mentioned datasets. While for the 20%–80% train–test split, it achieved 97.09, 88.37, 94.01, 95.71 and 94.71, respectively, for the listed datasets. Thus, this work presents a novel data augmentation method that uses data with higher quality instead of randomly selected. The paper proves experimentally that the proposed method improves the classification accuracy of RS scene classification.

Similar Papers
  • Research Article
  • Citations140

Understanding the learning mechanism of convolutional neural networks in spectral analysis

  • Apr 08, 2020
  • Analytica Chimica Acta
  • Xiaolei Zhang +8
  • Research Article
  • Citations8

Pre- and post-fire forest canopy height mapping in Southeast Australia through the integration of multi-temporal GEDI data, satellite images, and Convolution Neural Network

  • May 07, 2024
  • International Journal of Remote Sensing
  • Tsung-Chi Chou +2
  • Conference Article
  • Citations4

Statistical Selection of CNN Models for Citrus Fruit Disease Prediction

  • Jun 14, 2023
  • Rajat Amat +3
  • Research Article
  • Citations1

Improving the Predictability of the US Seasonal Surface Temperature With Convolutional Neural Networks Trained on CESM2 LENS

  • Aug 08, 2024
  • Journal of Geophysical Research: Atmospheres
  • Yujay An +1
  • Book Chapter
  • Citations3

Employing Data Augmentation for Recognition of Hand Gestures Using Deep Learning

  • Jan 01, 2021
  • Deepak Kumar +2
  • Research Article
  • Citations41

Estimation and uncertainty analysis of groundwater quality parameters in a coastal aquifer under seawater intrusion: a comparative study of deep learning and classic machine learning methods.

  • Aug 08, 2022
  • Environmental Science and Pollution Research
  • Mehmet Taşan +2
  • Book Chapter
  • Citations1

Enhancing pepper growth and yield through disease identification in plants using leaf-based deep learning techniques

  • Jan 29, 2025
  • S Pradeep +5
  • Research Article
  • Citations42

Distinguishing pericarpium citri reticulatae of different origins using terahertz time-domain spectroscopy combined with convolutional neural networks

  • Apr 25, 2023
  • Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy
  • Hongbin Pu +4
  • Research Article

Predicting Within-City Variations in Ultrafine Particle and Black Carbon Concentrations in Bucaramanga, Columbia Using Open Source Data and Images

  • Aug 23, 2021
  • ISEE Conference Abstracts
  • Marshall Lloyd +7
  • PDF
  • Components

Table_1.docx

  • Nov 30, 2021
  • Figshare
  • Bin Xiao (146435) +7
  • Research Article

Penerapan Metode Convolutional Neural Network pada Sistem Klasifikasi Penyakit Tanaman Apel berdasarkan Citra Daun

  • Dec 19, 2024
  • Edumatic: Jurnal Pendidikan Informatika
  • Nicholas Bagus Pamungkas +1
  • Research Article
  • Citations77

Characterization and identification of asphalt mixtures based on Convolutional Neural Network methods using X-ray scanning images

  • Apr 17, 2018
  • Construction and Building Materials
  • Jiwang Jiang +3
  • Research Article
  • Citations1

Lung Cancer Diagnosis From Computed Tomography Images Using Deep Learning Algorithms With Random Pixel Swap Data Augmentation: Algorithm Development and Validation Study

  • Sep 03, 2025
  • JMIR Bioinformatics and Biotechnology
  • Ayomide Adeyemi Abe +1
  • PDF
  • Research Article
  • Citations16

The Real-Time Mobile Application for Classifying of Endangered Parrot Species Using the CNN Models Based on Transfer Learning

  • Mar 09, 2020
  • Mobile Information Systems
  • Daegyu Choe +2
  • Research Article
  • Citations26

A deep learning fusion model with evidence-based confidence level analysis for differentiation of malignant and benign breast tumors using dynamic contrast enhanced MRI

  • Nov 24, 2021
  • Biomedical Signal Processing and Control
  • Yunan Wu +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.