Identifying Cotton Fields from Remote Sensing Images Using Multiple Deep Learning Networks

Remote sensing imageries processed through empirical and deterministic approaches help predict multiple agronomic traits throughout the growing season. Accurate identification of cotton crop from remotely sensed imageries is a significant task in precision agriculture. This study aims to utilize a d...

Full description

Saved in:
Bibliographic Details
Published in:Agronomy (Basel) 2021-01, Vol.11 (1), p.174
Main Authors: Li, Haolu, Wang, Guojie, Dong, Zhen, Wei, Xikun, Wu, Mengjuan, Song, Huihui, Amankwah, Solomon Obiri Yeboah
Format: Article
Language:English
Subjects:
Accuracy
Agriculture
Agronomy
Algorithms
Artificial neural networks
Cameras
Classification
Cotton
cotton identification
Crop fields
Crops
Deep learning
DenseNet
Growing season
Identification
Image resolution
Machine learning
Mountains
Neural networks
Precipitation
Precision farming
Remote sensing
remote sensing images
Satellites
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Remote sensing imageries processed through empirical and deterministic approaches help predict multiple agronomic traits throughout the growing season. Accurate identification of cotton crop from remotely sensed imageries is a significant task in precision agriculture. This study aims to utilize a deep learning-based framework for cotton crop field identification with Gaofen-1 (GF-1) high-resolution (16 m) imageries in Wei-Ku region, China. An optimized model for the pixel-wise multidimensional densely connected convolutional neural network (DenseNet) was used. Four widely-used classic convolutional neural networks (CNNs), including ResNet, VGG, SegNet, and DeepLab v3+, were also used for accuracy assessment. The results infer that DenseNet can identify cotton crop features within a relatively shorter time about 5 h for training convergence. The model performance was examined by multiple indicators (P, F1, R, and mIou) produced through the confusion matrix, and the derived cotton fields were then visualized. The DenseNet model has illustrated considerable improvements in comparison with the preceding mainstream models. The results showed that the retrieval precision was 0.948, F1 score was 0.953, and mIou was 0.911. Furthermore, its performance is relatively better in discriminating cotton crop fields’ fine structures when clouds, mountain shadows, and urban built up.
ISSN:2073-4395
2073-4395
DOI:10.3390/agronomy11010174