Latest issue of IJRS

Volume 43, Issue 6

The latest issue of the International Journal of Remote Sensing is now available.

This issue includes seventeen research articles across various themes and disciplines within remote sensing. In this issue there are multiple papers looking at synthetic aperture radar, machine learning and image segmentation.

You can access the issue here.

Summary of published articles:

K.G. Toker and S.E. Yuksel (Hacettepe University) present a nearest subspace classifier (NSC) that utilises spatial information to classify hyperspectral imagery.

https://doi.org/10.1080/01431161.2022.2055986

Y. Sun and colleagues (PLA Strategic Support Force Information Engineering University) propose FOctConvPA, a fully octave convolution network with pyramid attention mechanism, for the classification of hyperspectral imagery.

https://doi.org/10.1080/01431161.2022.2054299

Y. Wang (Wuhan University) and colleagues examine Sentinel-1 satellite synthetic aperture radar (SAR) backscattering and depolarization parameters, and propose a new radar vegetation index to improve estimation of crop height.

https://doi.org/10.1080/01431161.2022.2054294

C. Shi (Hebei University of Technology) and colleagues propose CloudRAEDNet, a residual attention-based encoder-decoder network for ground-based cloud image segmentation.

https://doi.org/10.1080/01431161.2022.2054298

R. Wenger (University of Strasbourg) and colleagues use U-Net feature fusion to perform multi-class semantic segmentation of high resolution (10 m) Sentinel-2 satellite imagery to map urban fabrics in the Grand Est Region, France.

https://doi.org/10.1080/01431161.2022.2054295

N. Zhang (Chinese Academy of Agricultural Sciences) and colleagues propose a remote sensing approach to winter wheat crop yield estimation using hyperspectral imagery and the dynamic fraction of post-anthesis phase biomass accumulation.

https://doi.org/10.1080/01431161.2022.2054297

C.R. de Macedo (University of Porto) and colleagues investigate the scattering mechanisms associated with internal waves (IWs) using multi-polarization L-band synthetic aperture radar acquired with the ALOS-Palsar satellite.

https://doi.org/10.1080/01431161.2022.2050435

S. Zhang (Chinese Academy of Science) and colleagues introduce a novel multiknowledge learning module, MKLM, for the detection of objects in even complex and challenging remote sensing imagery.

https://doi.org/10.1080/01431161.2022.2061316

D. Mejía ávila and colleagues (University of Córdoba) evaluate Sentinel-2 satellite multispectral imagery and 39 spectral indices for the estimation of total dissolved solids (TDS) in freshwater wetlands of northern Colombia.

https://doi.org/10.1080/01431161.2022.2057205

X. Zhao (Capital Normal University) and colleagues identify construction and demolition waste (CDW) through a combination of change detection and deeplearning, using ZY-3 satellite multispectral imagery as an input to train DeepLabV3+.

https://doi.org/10.1080/01431161.2022.2054296

K. Peerbhay and colleagues (University of KwaZulu-Natal) used Landsat-8 satellite multispectral imagery and the Gradient Boosting Machine (GBM) machine learning approach to detect wattle rust (Uromycladium acacia) canopy defoliation in Southern Africa.

https://doi.org/10.1080/01431161.2022.2058891

E.F.L. Trotter and colleagues (Aalborg University) employ machine learning - specifically, a U-Net-like CNN (convolutional neural network) - to automatically detect historic stone walls in LiDAR data.

https://doi.org/10.1080/01431161.2022.2057206

N. Chaudhari (Dhirubhai Ambani Institute of Information and Communication Technology) and colleagues perform edge-preserving classification of polarimetric SAR (synthetic aperture radar) imagery using Wishart distribution and conditional random field (CRF).

https://doi.org/10.1080/01431161.2022.2054293

J. Huang (Chinese Academy of Sciences) and colleagues present an observational angular analysis which considers the hypothetical coverage of Earth when observed from a Moon-based platform.

https://doi.org/10.1080/01431161.2022.2058894

W. Doo and H. Kim (Korea Advanced Institute of Science and Technology) propose a method for the segmentation of hyperspectral images that simultaneously segments imagery and identifies bands which are highly involved in this segmentation.

https://doi.org/10.1080/01431161.2022.2058893

A. Khader and colleagues (Nanjing University of Science and Technology) introduce a novel fusion technique for high-resolution hyperspectral and multispectral imagery, based on a model-guided deep convolutional sparse coding network (MGDCSC).

https://doi.org/10.1080/01431161.2021.1995073

J. Wan (Xidian University) and colleagues present a cost-effective technique for emulation of aircraft motion drawing from shore-based multichannel radar sea clutter.

https://doi.org/10.1080/01431161.2022.2058892