A fast hyperspectral change detection algorithm for agricultural crops based on spatial reconstruction.
Crop change detection plays a pivotal role in ensuring agricultural sustainability and environmental monitoring. Leveraging the high spectral resolution of hyperspectral imagery and bi-temporal analysis, this study presents a Fast Hyperspectral Change Detection algorithm based on Spatial Reconstruct...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0323446 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Crop change detection plays a pivotal role in ensuring agricultural sustainability and environmental monitoring. Leveraging the high spectral resolution of hyperspectral imagery and bi-temporal analysis, this study presents a Fast Hyperspectral Change Detection algorithm based on Spatial Reconstruction (FHCDSR) designed to identify subtle agricultural changes with improved accuracy and computational efficiency. The proposed method incorporates three key innovations: (1) boundary-constrained preprocessing of 3D hyperspectral data, (2) Laplacian-regularized spatial reconstruction, and (3) a novel tensor-based change detection framework. We conduct a comprehensive evaluation of FHCDSR using two datasets: the Hermiston dataset and the Yancheng dataset. Experimental results demonstrate that FHCDSR achieves superior performance on both datasets, with AUC values of 90.20% (Hermiston) and 95.39% (Yancheng), outperforming six state-of-the-art comparison methods by 3.39-14.78% in detection accuracy. Remarkably, the algorithm maintains high computational efficiency, completing analyses in 9.76 seconds (Hermiston) and 10.90 seconds (Yancheng), representing up to 94.05% reduction in processing time compared to conventional methods. The consistent performance across different agricultural landscapes highlights FHCDSR's robustness as an unsupervised change detection solution, with significant potential for precision agriculture and wetland ecosystem monitoring applications. |
|---|---|
| ISSN: | 1932-6203 |