Generation of the NIR Spectral Band for Satellite Images with Convolutional Neural Networks

@article{Illarionova2021GenerationOT,
  title={Generation of the NIR Spectral Band for Satellite Images with Convolutional Neural Networks},
  author={Svetlana Illarionova and Dmitrii G. Shadrin and Alexey Trekin and Vladimir Ignatiev and I. Oseledets},
  journal={Sensors (Basel, Switzerland)},
  year={2021},
  volume={21}
}
The near-infrared (NIR) spectral range (from 780 to 2500 nm) of the multispectral remote sensing imagery provides vital information for landcover classification, especially concerning vegetation assessment. Despite the usefulness of NIR, it does not always accomplish common RGB. Modern achievements in image processing via deep neural networks make it possible to generate artificial spectral information, for example, to solve the image colorization problem. In this research, we aim to… 

Figures and Tables from this paper

From RGB to NIR: Predicting of near infrared reflectance from visible spectrum aerial images of crops

TLDR
This work investigates image-to-image translation as a means to generate an NIR spectral band from an RGB image alone in aerial crop imagery to evaluate efficacy in an agricultural context.

Tree Species Mapping on Sentinel-2 Satellite Imagery with Weakly Supervised Classification and Object-Wise Sampling

Information on forest composition, specifically tree types and their distribution, aids in timber stock calculation and can help to better understand the biodiversity in a particular region.

La especialización productiva y agrícola desde su análisis bibliométrico (1915-2019)

La creciente importancia de la planificación regional genera que la geografía económica y el análisis espacial, así como la producción científica en torno al tema, tomen relevancia. En ese sentido,

High-Resolution Satellite Imagery for Modeling the Impact of Aridification on Crop Production

The Cauvery Delta is a major rice cultivation region in Tamil Nadu, India, responsible for the food security and livelihoods of millions of farmers. In a given agricultural year, the farmers from the

XtremeAugment: Getting More From Your Data Through Combination of Image Collection and Image Augmentation

TLDR
This article reports on the comprehensive framework XtremeAugment which provides an easy, reliable, and scalable way to collect image datasets and to efficiently label and augment collected data.

References

SHOWING 1-10 OF 52 REFERENCES

Visualizing Near Infrared Hyperspectral Images with Generative Adversarial Networks

TLDR
An end-to-end neural network is proposed, based on the convolutional neural networks, to transform a hyperspectral image of hundreds of near infrared bands to a three-band image, which shows that the proposed method performs better in producing naturally looking details and colors for near infrared hyperspectrals.

MixChannel: Advanced Augmentation for Multispectral Satellite Images

TLDR
The proposed approach substitutes some channels of the original training image with channels from other images of the exact location to mix auxiliary data to achieve the more robust performance of the trained models.

GAN generation of synthetic multispectral satellite images

TLDR
The unpaired style transfer method is used to modify images that are dominant in vegetation land cover into image that are dominated by bare land cover and vice versa, showing that the land-cover transfer is an easier task compared to the GAN generation from scratch.

Training Deep Convolutional Neural Networks for Land–Cover Classification of High-Resolution Imagery

TLDR
This letter employs two techniques in conjunction with DCNN: transfer learning with fine-tuning and data augmentation tailored specifically for remote sensing imagery, which allows one to bootstrap a DCNN while preserving the deep visual feature extraction learned over an image corpus from a different image domain.

Deep Learning Classification of Land Cover and Crop Types Using Remote Sensing Data

TLDR
A multilevel DL architecture that targets land cover and crop type classification from multitemporal multisource satellite imagery outperforms the one with MLPs allowing us to better discriminate certain summer crop types.

Classification of High Resolution Remote Sensing Images using Deep Learning Techniques

TLDR
Transfer learning is used efficiently for the feature extraction from a pretrained Convolutional Neural Network model which is used for training in the classification task and the classification yielded a better accurate results.

Remote Sensing Image Colorization Based on Multiscale SEnet GAN

  • Min WuXin Jin Jinfang Huang
  • Mathematics
    2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)
  • 2019
TLDR
This paper combines multi-scale convolution with Squeeze-and-Excitation Networks (SEnet) to propose a new model that is applied to the generator of DCGAN, which retains the largest image features in the process of the generating images, but also can adjust the channel weights in the training process.

Deep learning in remote sensing scene classification: a data augmentation enhanced convolutional neural network framework

TLDR
A methodology to not only enhance the volume and completeness of training data for any remote sensing datasets, but also exploit the enhanced datasets to train a deep convolutional neural network that achieves state-of-the-art scene classification performance.

Spectral Synthesis for Geostationary Satellite-to-Satellite Translation

TLDR
This work tackles the problem of generating synthetic spectral imagery for multispectral sensors as an unsupervised image-to-image translation problem modeled with a variational autoencoder (VAE) and generative adversarial network (GAN) architecture and introduces a novel shared spectral reconstruction loss to constrain the high-dimensional feature space of multisectral images.

Object-Based Augmentation Improves Quality of Remote SensingSemantic Segmentation

TLDR
This study proposes a novel pipeline for georeferenced image augmentation that enables a significant increase in the number of training samples and leads to the meaningful improvement of U-Net model predictions from 0.78 to 0.83 F1-score.
...