Paper
23 October 2018 Analysis of winter wheat recognition ability based on multiphase Sentinel-2A data
Fanchen Peng, Shuhe Zhao, Wenting Cai, Yamei Wang, Zhaohua Zhang
Author Affiliations +
Abstract
Effective and dynamic recognition of winter wheat has important implications for the development of agriculture in In this paper, we proposed a method for winter wheat identification using particle swarm optimization-support vector machine (PSO-SVM) model and multi-temporal Sentinel-2A image. The eigenvector combination based on spectral information and the eigenvector combination based on texture information were constructed by using different phenological periods of winter wheat. The winter wheat was identified and extracted by PSO-SVM. The extraction accuracy under different feature band combinations was compared and analyzed. The results showed that PSO-SVM had higher accuracy than traditional SVM. Using PSO-SVM, the optimal combination was multi-temporal spectral and mean texture information combination and its classification accuracy was 91.25%. This paper provides a theoretical basis for the future use of Sentinel-2A data to extract other crop information.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Fanchen Peng, Shuhe Zhao, Wenting Cai, Yamei Wang, and Zhaohua Zhang "Analysis of winter wheat recognition ability based on multiphase Sentinel-2A data", Proc. SPIE 10780, Multispectral, Hyperspectral, and Ultraspectral Remote Sensing Technology, Techniques and Applications VII, 1078012 (23 October 2018); https://doi.org/10.1117/12.2324724
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image classification

Feature extraction

Remote sensing

Associative arrays

Particles

Particle swarm optimization

Principal component analysis

Back to Top