scholarly journals Spectral Super-Resolution with Optimized Bands

2019 ◽  
Vol 11 (14) ◽  
pp. 1648 ◽  
Author(s):  
Utsav B. Gewali ◽  
Sildomar T. Monteiro ◽  
Eli Saber
Keyword(s):  
Network Architecture ◽  
Prior Information ◽  
Reflectance Spectrum ◽  
Super Resolution ◽  
High Dimensional ◽  
Sparse Signals ◽  
Reconstruction Accuracy ◽  
Neural Network Architecture ◽  
Real World Datasets ◽  
Very High

Hyperspectral (HS) sensors sample reflectance spectrum in very high resolution, which allows us to examine material properties in very fine details. However, their widespread adoption has been hindered because they are very expensive. Reflectance spectra of real materials are high dimensional but sparse signals. By utilizing prior information about the statistics of real HS spectra, many previous studies have reconstructed HS spectra from multispectral (MS) signals (which can be obtained from cheaper, lower spectral resolution sensors). However, most of these techniques assume that the MS bands are known apriori and do not optimize the MS bands to produce more accurate reconstructions. In this paper, we propose a new end-to-end fully convolutional residual neural network architecture that simultaneously learns both the MS bands and the transformation to reconstruct HS spectra from MS signals by analyzing large quantity of HS data. The learned band can be implemented in hardware to obtain an MS sensor that collects data that is best to reconstruct HS spectra using the learned transformation. Using a diverse set of real-world datasets, we show how the proposed approach of optimizing MS bands along with the transformation can drastically increase the reconstruction accuracy. Additionally, we also investigate the prospects of using reconstructed HS spectra for land cover classification.

scholarly journals A Surrogate Model Based on Artificial Neural Network for RF Radiation Modelling with High-Dimensional Data

2020 ◽  
Vol 17 (7) ◽  
pp. 2586 ◽  
Author(s):  
Xi Cheng ◽  
Clément Henry ◽  
Francesco P. Andriulli ◽  
Christian Person ◽  
Joe Wiart
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Uncertainty Quantification ◽  
Network Architecture ◽  
High Dimensional Data ◽  
High Dimensional ◽  
Attractive Alternative ◽  
Neural Network Architecture ◽  
Radiation Modelling ◽  
Artificial Neural

This paper focuses on quantifying the uncertainty in the specific absorption rate values of the brain induced by the uncertain positions of the electroencephalography electrodes placed on the patient’s scalp. To avoid running a large number of simulations, an artificial neural network architecture for uncertainty quantification involving high-dimensional data is proposed in this paper. The proposed method is demonstrated to be an attractive alternative to conventional uncertainty quantification methods because of its considerable advantage in the computational expense and speed.

Real-Time Video Scaling Based on Convolution Neural Network Architecture

2017 ◽  
Vol 7 (2) ◽  
pp. 381
Author(s):  
S Safinaz ◽  
AV Ravi kumar
Keyword(s):  
Neural Network ◽  
High Resolution ◽  
Real Time ◽  
Network Architecture ◽  
High Efficiency ◽  
Super Resolution ◽  
Reconstruction Error ◽  
Convolution Neural Network ◽  
Neural Network Architecture ◽  
Video Frames

In recent years, video super resolution techniques becomes mandatory requirements to get high resolution videos. Many super resolution techniques researched but still video super resolution or scaling is a vital challenge. In this paper, we have presented a real-time video scaling based on convolution neural network architecture to eliminate the blurriness in the images and video frames and to provide better reconstruction quality while scaling of large datasets from lower resolution frames to high resolution frames. We compare our outcomes with multiple exiting algorithms. Our extensive results of proposed technique RemCNN (Reconstruction error minimization Convolution Neural Network) shows that our model outperforms the existing technologies such as bicubic, bilinear, MCResNet and provide better reconstructed motioning images and video frames. The experimental results shows that our average PSNR result is 47.80474 considering upscale-2, 41.70209 for upscale-3 and 36.24503 for upscale-4 for Myanmar dataset which is very high in contrast to other existing techniques. This results proves our proposed model real-time video scaling based on convolution neural network architecture’s high efficiency and better performance.

scholarly journals PlanetScope Radiometric Normalization and Sentinel-2 Super-Resolution (2.5 m): A Straightforward Spectral-Spatial Fusion of Multi-Satellite Multi-Sensor Images Using Residual Convolutional Neural Networks

2020 ◽  
Vol 12 (15) ◽  
pp. 2366
Author(s):  
Nicolas Latte ◽  
Philippe Lejeune
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Network Architecture ◽  
State Of The Art ◽  
Super Resolution ◽  
Neural Network Architecture ◽  
Research Areas ◽  
Novel Method ◽  
Spatial Fusion ◽  
Sentinel 2

Sentinel-2 (S2) imagery is used in many research areas and for diverse applications. Its spectral resolution and quality are high but its spatial resolutions, of at most 10 m, is not sufficient for fine scale analysis. A novel method was thus proposed to super-resolve S2 imagery to 2.5 m. For a given S2 tile, the 10 S2 bands (four at 10 m and six at 20 m) were fused with additional images acquired at higher spatial resolution by the PlanetScope (PS) constellation. The radiometric inconsistencies between PS microsatellites were normalized. Radiometric normalization and super-resolution were achieved simultaneously using state-of–the-art super-resolution residual convolutional neural networks adapted to the particularities of S2 and PS imageries (including masks of clouds and shadows). The method is described in detail, from image selection and downloading to neural network architecture, training, and prediction. The quality was thoroughly assessed visually (photointerpretation) and quantitatively, confirming that the proposed method is highly spatially and spectrally accurate. The method is also robust and can be applied to S2 images acquired worldwide at any date.

The adaptive control of a four-degrees-of-freedom stereo camera head

1992 ◽  
Vol 337 (1281) ◽  
pp. 315-326 ◽  
Keyword(s):  
Neural Network ◽  
Adaptive Control ◽  
Network Architecture ◽  
Degrees Of Freedom ◽  
Ground Plane ◽  
High Dimensional ◽  
Network Architectures ◽  
Neural Network Architecture ◽  
Subsumption Architecture ◽  
Head Positions

The paper describes the use of biologically plausible neural network architectures to address some of the issues associated with the use of stereopsis under variable camera geometry. We report an implementation of a layered (subsumption) architecture for the adaptive control of microsaccadic tracking, and show experimental results demonstrating the use of lattice filter predictors for trajectory modelling. A rather simple, but seemingly adequate, neural network architecture for representing high-dimensional surface approximations ( piluts) is evaluated as a method of encoding the predictive stereo mapping of the ground plane for different head positions.

scholarly journals Large receptive field networks for accurate high-scale image super-resolution

2021 ◽  
Author(s):  
George Seif
Keyword(s):  
Neural Network ◽  
Receptive Field ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Super Resolution ◽  
Neural Network Architecture ◽  
High Scale ◽  
One Dimensional ◽  
Image Super Resolution ◽  
And Performance

This thesis presents a novel convolutional neural network architecture for high-scale image super-resolution. In particular, we introduce two separate modifications that can be made to the convolutional layers in the network: one-dimensional kernels and dilated kernels. We show how both of these methods can be used to expand the receptive field and performance of super-resolution networks, without increasing the number of trainable parameters or network depth. We show that these modifications can easily be integrated into any convolutional neural network to improve performance. Our methods are especially effective for the challenging high scale super-resolution due to the expanded network receptive field. We conduct extensive empirical evaluations to demonstrate the effectiveness of our methods, showing strong improvements over the state-of-the-art.

scholarly journals Large receptive field networks for accurate high-scale image super-resolution

2021 ◽  
Author(s):  
George Seif
Keyword(s):  
Neural Network ◽  
Receptive Field ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Super Resolution ◽  
Neural Network Architecture ◽  
High Scale ◽  
One Dimensional ◽  
Image Super Resolution ◽  
And Performance

This thesis presents a novel convolutional neural network architecture for high-scale image super-resolution. In particular, we introduce two separate modifications that can be made to the convolutional layers in the network: one-dimensional kernels and dilated kernels. We show how both of these methods can be used to expand the receptive field and performance of super-resolution networks, without increasing the number of trainable parameters or network depth. We show that these modifications can easily be integrated into any convolutional neural network to improve performance. Our methods are especially effective for the challenging high scale super-resolution due to the expanded network receptive field. We conduct extensive empirical evaluations to demonstrate the effectiveness of our methods, showing strong improvements over the state-of-the-art.

Video Super Resolution by Neural Network: A Theoretical Aspect

2020 ◽  
Vol 17 (9) ◽  
pp. 4202-4206
Author(s):  
Mrunmayee V. Daithankar ◽  
Sachin D. Ruikar
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Super Resolution ◽  
Theoretical Aspect ◽  
Neural Network Architecture ◽  
Enhanced Resolution ◽  
Resolution Improvement ◽  
The Neural Networks ◽  
New Generation ◽  
Practical Feasibility

The paper explores literature on the video super resolution by neural network, with all essential basics related to it. The extensive applicability and need of enhanced resolution becomes attraction for researchers. The limitations of traditional methods gives rise to the new generation of neural network based super resolution. The neural networks are well known for parallel and fast computation of data. But embedding a neural network with challenging super resolution era has come up with benefits as well as drawbacks. Still the researchers are working on the challenges like, limited practical feasibility and utility, accuracy at the time cost, complexity, etc. This paper is useful for new researchers to get information about the basics of super resolution and neural network, relative study of learning processes, comparative summarization of neural network architecture used for resolution improvement.

scholarly journals Automatic Mapping of Center Pivot Irrigation Systems from Satellite Images Using Deep Learning

2020 ◽  
Vol 12 (3) ◽  
pp. 558 ◽  
Author(s):  
Marciano Saraiva ◽  
Églen Protas ◽  
Moisés Salgado ◽  
Carlos Souza
Keyword(s):  
Network Architecture ◽  
Cloud Platform ◽  
Neural Network Architecture ◽  
Irrigation Systems ◽  
Center Pivot ◽  
Very High Spatial Resolution ◽  
Automatic Mapping ◽  
Global Concern ◽  
Freshwater Use ◽  
Very High

The availability of freshwater is becoming a global concern. Because agricultural consumption has been increasing steadily, the mapping of irrigated areas is key for supporting the monitoring of land use and better management of available water resources. In this paper, we propose a method to automatically detect and map center pivot irrigation systems using U-Net, an image segmentation convolutional neural network architecture, applied to a constellation of PlanetScope images from the Cerrado biome of Brazil. Our objective is to provide a fast and accurate alternative to map center pivot irrigation systems with very high spatial and temporal resolution imagery. We implemented a modified U-Net architecture using the TensorFlow library and trained it on the Google cloud platform with a dataset built from more than 42,000 very high spatial resolution PlanetScope images acquired between August 2017 and November 2018. The U-Net implementation achieved a precision of 99% and a recall of 88% to detect and map center pivot irrigation systems in our study area. This method, proposed to detect and map center pivot irrigation systems, has the potential to be scaled to larger areas and improve the monitoring of freshwater use by agricultural activities.

scholarly journals Balancing Two-Player Stochastic Games with Soft Q-Learning

2018 ◽  
Author(s):  
Jordi Grau-Moya ◽  
Felix Leibfried ◽  
Haitham Bou-Ammar
Keyword(s):  
Network Architecture ◽  
Stochastic Games ◽  
Decision Makers ◽  
High Dimensional ◽  
Neural Network Architecture ◽  
Rational Agents ◽  
Q Learning ◽  
Zero Sum Games ◽  
Team Games ◽  
Zero Sum

Within the context of video games the notion of perfectly rational agents can be undesirable as it leads to uninteresting situations, where humans face tough adversarial decision makers. Current frameworks for stochastic games and reinforcement learning prohibit tuneable strategies as they seek optimal performance. In this paper, we enable such tuneable behaviour by generalising soft Q-learning to stochastic games, where more than one agent interact strategically. We contribute both theoretically and empirically. On the theory side, we show that games with soft Q-learning exhibit a unique value and generalise team games and zero-sum games far beyond these two extremes to cover a continuous spectrum of gaming behaviour. Experimentally, we show how tuning agents' constraints affect performance and demonstrate, through a neural network architecture, how to reliably balance games with high-dimensional representations.

Sign in / Sign up

Export Citation Format

Share Document