Synergistic exploitation of localized spectral-spatial and temporal information with DNNs for multisensor-multitemporal image-based crop classification

•Focus on localized spectral info during crop classification in mixed land cover.•Contribution of spectral info is increased via permuted sets of spectral bands.•Localized spectral-spatial convolutions extracted class-intensive selective features.•Temporal info in time-distributed spectral-spatial f...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:International journal of applied earth observation and geoinformation 2023-12, Vol.125, p.103595, Article 103595
Hauptverfasser: Phartiyal, Gopal Singh, Singh, Dharmendra, Yahia, Hussein
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:•Focus on localized spectral info during crop classification in mixed land cover.•Contribution of spectral info is increased via permuted sets of spectral bands.•Localized spectral-spatial convolutions extracted class-intensive selective features.•Temporal info in time-distributed spectral-spatial features is exploited via Bi-RNNs.•Classification accuracy of 99.10% and visual inspection supports the performance. The challenge of performing efficient and reliable crop classification with multisensor multitemporal (MSMT) images in mixed land cover scenarios i.e. presence of small land parcels (area 
ISSN:1569-8432
1872-826X
DOI:10.1016/j.jag.2023.103595