Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
April 10, 2026PeerJ Computer ScienceOpen Access

Scale-space-based patch selection for crop classification in satellite images

View Full Paper
Ask AI
Bookmark
Share

Authors

MRMonica Moreno ReveloJGJuan-Bernardo Gómez-MendozaJRJavier Revelo-Fuelagán

Discussion

Loading...

Member takes

Overview

Demonstrates a scale analysis technique improving accuracy in crop classification using satellite images, indicating enhanced feature extraction efficiency.

Key Points

  • The research aims to improve crop classification accuracy by optimizing patch size in satellite images.
  • Introduced a scale analysis technique for patch size determination.
  • Segmented satellite images into optimally sized patches.
  • Employed a convolutional neural network for binary classification of crop classes.
  • Tested methodology on the Campo Verde dataset.
  • Achieved an overall accuracy of 96.46%.
  • Sensitivity reached 95.88%.
  • F1-score calculated at 67.53%.
  • Demonstrated improved classification performance and decreased computational cost.

Cite This Study

Revelo et al. (2026) studied this question.

synapsesocial.com/papers/69d8958f6c1944d70ce06a65https://doi.org/10.7717/peerj-cs.3635
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Mapping Crop Types At a 10 m Scale Using Sentinel-2 Data and Machine Learning Methods2024 · 12 citations
  2. 2Advancing crop classification in smallholder agriculture: A multifaceted approach combining frequency-domain image co-registration, transformer-based parcel segmentation, and Bi-LSTM for crop classification2024 · 18 citations
  3. 3Parcel-Level Crop Classification in Plain Fragmented Regions Based on Multi-Source Remote Sensing Images2024 · 1 citations
  4. 4Crop mapping using sentinel-1 and sentinel-2 imagery: a systematic review of machine learning classification methods (2015–2025)2026
  5. 5Parcel-level crop classification in small and irregular fields using structured Sentinel-2 data and clustering based analysis2026