Idioma:

3D Convolutional Neural Networks for Crop Classification with Multi-Temporal Remote Sensing Images

Ji, Shunping ; Zhang, Chi ; Xu, Anjian ; Shi, Yun ; Duan, Yulin

Remote sensing (Basel, Switzerland), 2018-01, Vol.10 (1), p.75 [Revista revisada por pares]

Texto completo disponible

Citas Citado por

Título:
3D Convolutional Neural Networks for Crop Classification with Multi-Temporal Remote Sensing Images
Autor: Ji, Shunping ; Zhang, Chi ; Xu, Anjian ; Shi, Yun ; Duan, Yulin
Materias: 3D convolution ; active learning ; convolutional neural networks ; crop classification ; multi-temporal remote sensing images
Es parte de: Remote sensing (Basel, Switzerland), 2018-01, Vol.10 (1), p.75
Descripción: This study describes a novel three-dimensional (3D) convolutional neural networks (CNN) based method that automatically classifies crops from spatio-temporal remote sensing images. First, 3D kernel is designed according to the structure of multi-spectral multi-temporal remote sensing data. Secondly, the 3D CNN framework with fine-tuned parameters is designed for training 3D crop samples and learning spatio-temporal discriminative representations, with the full crop growth cycles being preserved. In addition, we introduce an active learning strategy to the CNN model to improve labelling accuracy up to a required threshold with the most efficiency. Finally, experiments are carried out to test the advantage of the 3D CNN, in comparison to the two-dimensional (2D) CNN and other conventional methods. Our experiments show that the 3D CNN is especially suitable in characterizing the dynamics of crop growth and outperformed the other mainstream methods.
Editor: MDPI AG
Idioma: Inglés

Volver a la lista de resultados

Anterior Resultado 8 Siguiente Ir a la siguiente página