Next Article in Journal
Evaluation of IEEE802.15.4g for Environmental Observations
Previous Article in Journal
An Optical Crack Growth Sensor Using the Digital Sampling Moiré Method
Open AccessArticle

Fusion of Unmanned Aerial Vehicle Panchromatic and Hyperspectral Images Combining Joint Skewness-Kurtosis Figures and a Non-Subsampled Contourlet Transform

1
National Joint Engineering Research Center for Analysis and Application of Agro-Ecological Big Data, Anhui University, Hefei 230601, China
2
National Engineering Research Center for Information Technology in Agriculture, Beijing 100089, China
*
Authors to whom correspondence should be addressed.
Sensors 2018, 18(10), 3467; https://doi.org/10.3390/s18103467
Received: 28 August 2018 / Revised: 10 October 2018 / Accepted: 11 October 2018 / Published: 15 October 2018
(This article belongs to the Section Remote Sensors, Control, and Telemetry)
  |  
PDF [4232 KB, uploaded 15 October 2018]
  |  

Abstract

To obtain fine and potential features, a highly informative fused image created by merging multiple images is usually required. In our study, a novel fusion algorithm called JSKF-NSCT is proposed for fusing panchromatic (PAN) and hyperspectral (HS) images by combining the joint skewness-kurtosis figure (JSKF) and the non-subsampled contourlet transform (NSCT). The JSKF model is used first to derive the three most sensitive bands from the original HS image according to the product of the skewness and the kurtosis coefficients of each band. Afterwards, an intensity-hue-saturation (IHS) transform is used to obtain the luminance component I of the produced false-colour image consisting of the above three bands. Then the NSCT method is used to decompose component I of the false-colour image and the PAN image. The weight-selection rule based on the regional energy is adopted to acquire the low-frequency coefficients and the correlation between the central pixel and its surrounding pixels is used to select the high-frequency coefficients. Finally, the fused image is obtained by applying an IHS inverse transform and an inverse NSCT transform. The unmanned aerial vehicle (UAV) HS and PAN images under low- and high-vegetation coverage of wheat at the flag leaf stage (Stage I) and the grain filling stage (Stage II) are used as the sample data sources. The fusion results are comparatively validated using spatial (entropy, standard deviation, average gradient and mean) and spectral (normalised difference vegetation, NDVI, and leaf area index, LAI) assessments. Additional comparative studies using anomaly detection and pixel clustering also demonstrate that the proposed method outperforms other methods. They show that the algorithm reported herein can better preserve the original spatial and spectral characteristics of the two types of images to be fused and is more stable than IHS, principal components analysis (PCA), non-negative matrix factorization (NMF) and Gram-Schmidt (GS). View Full-Text
Keywords: image fusion; non-subsampled contourlet transform (NSCT); joint skewness-kurtosis figure (JSKF); IHS transform; remote sensing image fusion; non-subsampled contourlet transform (NSCT); joint skewness-kurtosis figure (JSKF); IHS transform; remote sensing
Figures

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
SciFeed

Share & Cite This Article

MDPI and ACS Style

Zhao, J.; Zhou, C.; Huang, L.; Yang, X.; Xu, B.; Liang, D. Fusion of Unmanned Aerial Vehicle Panchromatic and Hyperspectral Images Combining Joint Skewness-Kurtosis Figures and a Non-Subsampled Contourlet Transform. Sensors 2018, 18, 3467.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Sensors EISSN 1424-8220 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top