Pixel-wise Agricultural Image Time Series Classification: Comparisons and a Deformable Prototype-based Approach
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913428158808064 |
|---|---|
| author | Vincent, Elliot Ponce, Jean Aubry, Mathieu |
| author_facet | Vincent, Elliot Ponce, Jean Aubry, Mathieu |
| contents | Improvements in Earth observation by satellites allow for imagery of ever higher temporal and spatial resolution. Leveraging this data for agricultural monitoring is key for addressing environmental and economic challenges. Current methods for crop segmentation using temporal data either rely on annotated data or are heavily engineered to compensate the lack of supervision. In this paper, we present and compare datasets and methods for both supervised and unsupervised pixel-wise segmentation of satellite image time series (SITS). We also introduce an approach to add invariance to spectral deformations and temporal shifts to classical prototype-based methods such as K-means and Nearest Centroid Classifier (NCC). We study different levels of supervision and show this simple and highly interpretable method achieves the best performance in the low data regime and significantly improves the state of the art for unsupervised classification of agricultural time series on four recent SITS datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2303_12533 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Pixel-wise Agricultural Image Time Series Classification: Comparisons and a Deformable Prototype-based Approach Vincent, Elliot Ponce, Jean Aubry, Mathieu Computer Vision and Pattern Recognition Improvements in Earth observation by satellites allow for imagery of ever higher temporal and spatial resolution. Leveraging this data for agricultural monitoring is key for addressing environmental and economic challenges. Current methods for crop segmentation using temporal data either rely on annotated data or are heavily engineered to compensate the lack of supervision. In this paper, we present and compare datasets and methods for both supervised and unsupervised pixel-wise segmentation of satellite image time series (SITS). We also introduce an approach to add invariance to spectral deformations and temporal shifts to classical prototype-based methods such as K-means and Nearest Centroid Classifier (NCC). We study different levels of supervision and show this simple and highly interpretable method achieves the best performance in the low data regime and significantly improves the state of the art for unsupervised classification of agricultural time series on four recent SITS datasets. |
| title | Pixel-wise Agricultural Image Time Series Classification: Comparisons and a Deformable Prototype-based Approach |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2303.12533 |