Method for Mapping Rice Fields in Complex Landscape Areas Based on Pre-Trained Convolutional Neural Network from HJ-1 A/B Data

Method for Mapping Rice Fields in Complex Landscape Areas Based on Pre-Trained Convolutional Neural Network from HJ-1 A/B Data

Accurate and timely information about rice planting areas is essential for crop yield estimation, global climate change and agricultural resource management. In this study, we present a novel pixel-level classification approach that uses convolutional neural network (CNN) model to extract the featur...

Full description

Bibliographic Details
Main Authors: Tian Jiang, Xiangnan Liu, Ling Wu
Format: Article
Language:English
Published: MDPI AG 2018-10-01
Series:ISPRS International Journal of Geo-Information
Subjects:
mapping rice fields
complex landscape
convolutional neural network
transfer learning
time series of vegetation index
Online Access:https://www.mdpi.com/2220-9964/7/11/418

Internet

https://www.mdpi.com/2220-9964/7/11/418

Similar Items