Back to Search
Start Over
WHU-Hi: UAV-borne hyperspectral with high spatial resolution (H2) benchmark datasets and classifier for precise crop identification based on deep convolutional neural network with CRF
- Source :
- Remote Sensing of Environment. 250:112012
- Publication Year :
- 2020
- Publisher :
- Elsevier BV, 2020.
-
Abstract
- Unmanned aerial vehicle (UAV)-borne hyperspectral systems can acquire hyperspectral imagery with a high spatial resolution (which we refer to here as H2 imagery). As a result of the low operating cost, high flexibility, and the ability to achieve real-time data acquisition, UAV-borne hyperspectral systems have become an important data source for remote sensing based agricultural monitoring. However, precise crop classification based on UAV-borne H2 imagery is a challenging task when faced with a number of different crop classes. The traditional hyperspectral classification methods, such as the spectral-based and object-oriented classification methods, have difficulty in classifying H2 imagery, faced with the problems of salt-and-pepper (SP) noise and scale selection. In this article, the deep convolutional neural network with a conditional random field classifier (CNNCRF) framework is proposed for precise crop classification with UAV-borne H2 imagery. In the proposed method, a deep convolutional neural network (CNN) is designed to extract and fuse in-depth spectral and local spatial features, and the conditional random field (CRF) model further incorporates the spatial-contextual information to improve the problem of holes and isolated regions in the classification map. Meanwhile, virtual sample augmentation based on the hyperspectral imaging mechanism is used to lessen the issue of the limited labeled samples. To validate the results, a new dataset—the Wuhan UAV-borne hyperspectral image (WHU-Hi) dataset—has been built for precise crop classification. The experimental results obtained using the WHU-Hi dataset confirm the accuracy and visualization performance of the proposed CNNCRF classification method, which outperforms the previous methods. In addition, the WHU-Hi dataset could serve as a benchmark dataset for hyperspectral image classification studies.
- Subjects :
- Conditional random field
010504 meteorology & atmospheric sciences
business.industry
Computer science
0208 environmental biotechnology
Soil Science
Hyperspectral imaging
Geology
Pattern recognition
02 engineering and technology
01 natural sciences
Convolutional neural network
020801 environmental engineering
Visualization
Data acquisition
High spatial resolution
Artificial intelligence
Computers in Earth Sciences
business
Classifier (UML)
Image resolution
0105 earth and related environmental sciences
Remote sensing
Subjects
Details
- ISSN :
- 00344257
- Volume :
- 250
- Database :
- OpenAIRE
- Journal :
- Remote Sensing of Environment
- Accession number :
- edsair.doi...........0b74a3dfd808bdc9dc3b921d238596c7