scholarly journals NN-Based Prediction of Sentinel-1 SAR Image Filtering Efficiency

Geosciences ◽  
2019 ◽  
Vol 9 (7) ◽  
pp. 290 ◽  
Author(s):  
Rubel ◽  
Lukin ◽  
Rubel ◽  
Egiazarian
Keyword(s):  
Neural Network ◽  
Image Quality ◽  
Real Life ◽  
Remote Sensing Data ◽  
Radar Data ◽  
Quality Metrics ◽  
Radar Images ◽  
Filtering Efficiency ◽  
Trained Neural Network ◽  
Synthetic Aperture Radars

Images acquired by synthetic aperture radars are degraded by speckle that prevents efficient extraction of useful information from radar remote sensing data. Filtering or despeckling is a tool often used to improve image quality. However, depending upon image and noise properties, the quality of improvement can vary. Besides, a quality can be characterized by different criteria or metrics, where visual quality metrics can be of value. For the case study of discrete cosine transform (DCT)based filtering, we show that improvement of radar image quality due to denoising can be predicted in a simple and fast way, especially if one deals with particular type of radar data such as images acquired by Sentinel-1. Our approach is based on application of a trained neural network that, in general, might have a different number of inputs (features). We propose a set of features describing image and noise statistics from different viewpoints. From this set, that contains 28 features, we analyze different subsets and show that a subset of the 13 most important and informative features leads to a very accurate prediction. Test image generation and network training peculiarities are discussed. The trained neural network is then tested using different verification strategies. The results of the network application to test and real-life radar images are presented, demonstrating good performance for a wide set of quality metrics.

Conjugate Gradient Trained Neural Network for Intelligent Sensing of Manhole Gases to Avoid Human Fatality

2014 ◽  
pp. 257-280
Author(s):  
Paramartha Dutta ◽  
Varun Kumar Ojha
Keyword(s):  
Neural Network ◽  
Conjugate Gradient ◽  
Learning Algorithm ◽  
Real Life ◽  
Nonlinear Problems ◽  
Pipeline System ◽  
Neural Network Learning ◽  
Pattern Recognition Problem ◽  
Artificial Neural Network Ann ◽  
Trained Neural Network

Computational Intelligence offers solution to various real life problems. Artificial Neural Network (ANN) has the capability of solving highly complex and nonlinear problems. The present chapter demonstrates the application of these tools to provide solutions to the manhole gas detection problem. Manhole, the access point across sewer pipeline system, contains various toxic and explosive gases. Hence, predetermination of these gases before accessing manholes is becoming imperative. The problem is treated as a pattern recognition problem. ANN, devised for solving this problem, is trained using a supervised learning algorithm. The conjugate gradient method is used as an alternative of back propagation neural network learning algorithm for training of the ANN. The chapter offers comprehensive performance analysis of the learning algorithm used for the training of ANN followed by discussion on the methods of presenting the system result. The authors discuss different variants of Conjugate Gradient and propose two new variants of it.

scholarly journals Neural-network fusion processing and inverse mapping to combine multi-sensor satellite data and to analyze significant features

2021 ◽  
Author(s):  
Gunjan Joshi ◽  
Ryo Natsuaki ◽  
Akira Hirose
Keyword(s):  
Neural Network ◽  
Satellite Data ◽  
Optical Sensors ◽  
Remote Sensing Data ◽  
Activation Function ◽  
Significant Feature ◽  
Unknown Parameters ◽  
Inverse Mapping ◽  
Observation Area ◽  
Synthetic Aperture Radars

<div>In the last decade, the increase in the number of active and passive earth observation satellites has provided us with more remote sensing data. This fact has led to increased interests in the field of fusion of the different satellite data since some of the satellites have properties complementary to one another. Fusion techniques can improve the estimation in areas of interest (AOIs) by using complementary information and inferring unknown parameters. However, when the observation area is large, extensive human labor and domain expertise are required for processing and analysis. Thus, we propose a neural network which combines and analyzes the data obtained from synthetic aperture radars (SAR) and optical sensors. The neural network employs a modified logarithmic activation function, unlike conventional networks, to realize inverse mapping for significant feature analysis based on dynamics consistent with its forward processing. In this paper, we focus on earthquake damage detection by dealing with the data of the 2018 Sulawesi earthquake in Indonesia. The fusion-based results show increased classification accuracy compared to the results of independent sensors. We further attempt to understand which input features are the significant contributors for which classification outputs by inverse-mapping in the data fusion neural network. We observe that inverse mapping shows reasonable explanations in a consistent manner. It also indicates contributions of features different from straightforward counterparts, namely pre- and post-seismic features, in the detection of particular classes.</div>

scholarly journals The use of remote-sensing data for mass-balance studies at Mýrdalsjökull ice cap, Iceland

2006 ◽  
Vol 52 (179) ◽  
pp. 565-573 ◽  
Author(s):  
Julia Jaenicke ◽  
Christoph Mayer ◽  
Kilian Scharrer ◽  
Ulrich Münzer ◽  
Agúst Gudmundsson
Keyword(s):  
Mass Balance ◽  
Satellite Images ◽  
Inverse Function ◽  
Remote Sensing Data ◽  
Late Summer ◽  
Radar Data ◽  
Synthetic Aperture Radar Data ◽  
Envisat Asar ◽  
Radar Images ◽  
Optical Satellite Images

AbstractA series of satellite images of Mýrdalsjökull, Iceland, was analyzed in view of their value for mass-balance investigations. A combination of optical satellite images from the ASTER sensor and synthetic aperture radar data from ERS-2 and Envisat ASAR proved very useful. The glacier margin of Mýrdalsjökull was delineated on ASTER images from summer and winter 2004. With a time series of summer ASAR images it was possible to monitor the temporal and spatial development of the transient snowline (TSL) throughout the year 2004, as well as the firn line (FL) at the end of the balance year. An ‘inverse’ function was applied to visually enhance detail in the radar imagery. Winter radar images were not useful for mass-balance observations because of frequent surface melting, which prevented the transparency of the snow cover for C-band microwaves. Interannual mass-balance fluctuations were observed by comparing three radar images acquired in late summer 1998, 1999 and 2004 respectively. These fluctuations follow the same trend as the annual mean air temperature which shows a strong increasing trend between 1999 and 2004. An accumulation-area ratio of <0.43 was determined for 2004, indicating clear negative mass-balance conditions. Monitoring the TSL-FL with radar summer images for mass-balance studies, rather than the equilibrium line (EL), is suggested for large ice caps in maritime climates.

scholarly journals Neural-network fusion processing and inverse mapping to combine multi-sensor satellite data and to analyze significant features

2021 ◽  
Author(s):  
Gunjan Joshi ◽  
Ryo Natsuaki ◽  
Akira Hirose
Keyword(s):  
Neural Network ◽  
Satellite Data ◽  
Optical Sensors ◽  
Remote Sensing Data ◽  
Activation Function ◽  
Significant Feature ◽  
Unknown Parameters ◽  
Inverse Mapping ◽  
Observation Area ◽  
Synthetic Aperture Radars

<div>In the last decade, the increase in the number of active and passive earth observation satellites has provided us with more remote sensing data. This fact has led to increased interests in the field of fusion of the different satellite data since some of the satellites have properties complementary to one another. Fusion techniques can improve the estimation in areas of interest (AOIs) by using complementary information and inferring unknown parameters. However, when the observation area is large, extensive human labor and domain expertise are required for processing and analysis. Thus, we propose a neural network which combines and analyzes the data obtained from synthetic aperture radars (SAR) and optical sensors. The neural network employs a modified logarithmic activation function, unlike conventional networks, to realize inverse mapping for significant feature analysis based on dynamics consistent with its forward processing. In this paper, we focus on earthquake damage detection by dealing with the data of the 2018 Sulawesi earthquake in Indonesia. The fusion-based results show increased classification accuracy compared to the results of independent sensors. We further attempt to understand which input features are the significant contributors for which classification outputs by inverse-mapping in the data fusion neural network. We observe that inverse mapping shows reasonable explanations in a consistent manner. It also indicates contributions of features different from straightforward counterparts, namely pre- and post-seismic features, in the detection of particular classes.</div>

A Hybrid Case Based Reasoning Model for Classification in Internet of Things (IoT) Environment

2018 ◽  
Vol 30 (4) ◽  
pp. 104-122 ◽  
Author(s):  
Saroj Kr Biswas ◽  
Debashree Devi ◽  
Manomita Chakraborty
Keyword(s):  
Neural Network ◽  
Back Propagation ◽  
Real Life ◽  
Imbalanced Data ◽  
Back Propagation Neural Network ◽  
Feature Weighting ◽  
Case Based Reasoning ◽  
Proposed Model ◽  
Weighting Problem ◽  
Trained Neural Network

This article describes how the enormous size of data in IoT needs efficient data mining model for information extraction, classification and mining hidden patterns from data. CBR is a learning, mining and problem-solving approach which solves a problem by relating past similar solved problems. One issue with CBR is feature weight to measure the similarity among cases to mine similar past cases. NN's pruning is a popular method, which extracts feature weights from a trained neural network without losing much generality of the training set by using four mechanisms: sensitivity, activity, saliency and relevance. However, training NN with imbalanced data leads the classifier to get biased towards the majority class. Therefore, this article proposes a hybrid CBR model with RUS and cost sensitive back propagation neural network in IoT environment to deal with the feature weighting problem in imbalance data. The proposed model is validated with six real-life datasets. The experimental results show that the proposed model is better than other feature weighting methods.

scholarly journals Computer Vision in Precipitation Nowcasting: Applying Image Quality Assessment Metrics for Training Deep Neural Networks

Atmosphere ◽  
2019 ◽  
Vol 10 (5) ◽  
pp. 244 ◽  
Author(s):  
Quang-Khai Tran ◽  
Sa-kwang Song
Keyword(s):  
Neural Network ◽  
Computer Vision ◽  
Image Quality ◽  
Quality Assessment ◽  
Image Quality Assessment ◽  
Mean Squared Error ◽  
Neural Network Models ◽  
Common Mean ◽  
Radar Images ◽  
Squared Error

This paper presents a viewpoint from computer vision to the radar echo extrapolation task in the precipitation nowcasting domain. Inspired by the success of some convolutional recurrent neural network models in this domain, including convolutional LSTM, convolutional GRU and trajectory GRU, we designed a new sequence-to-sequence neural network structure to leverage these models in a realistic data context. In this design, we decreased the numbers of channels in high abstract recurrent layers rather than increasing them. We formulated the task as a problem of encoding five radar images and predicting 10 steps ahead at the pixel level, and found that using only the common mean squared error can misguide the training and mislead the testing. Especially, the image quality of last predictions usually degraded rapidly. As a solution, we employed some visual image quality assessment techniques including Structural Similarity (SSIM) and multi-scale SSIM to train our models. Experimental results show that our structure was more tolerant to increasing uncertainty in the data, and the use of image quality metrics can significantly reduce the blurry image issue. Moreover, we found that using SSIM was very effective and a combination of SSIM with mean squared error and mean absolute error yielded the best prediction quality.

Prediction of Lee filter performance for Sentinel-1 SAR images

2020 ◽  
Vol 2020 (9) ◽  
pp. 371-1-371-7
Author(s):  
Oleksii Rubel ◽  
Vladimir Lukin ◽  
Andrii Rubel ◽  
Karen Egiazarian
Keyword(s):  
Neural Network ◽  
Complex Structure ◽  
Remote Sensing Data ◽  
Visual Quality ◽  
Synthetic Aperture ◽  
Spectral Features ◽  
Sar Images ◽  
Filter Performance ◽  
Efficient Processing ◽  
Trained Neural Network

Synthetic aperture radar (SAR) images are corrupted by a specific noise-like phenomenon called speckle that prevents efficient processing of remote sensing data. There are many denoising methods already proposed including well known (local statistic) Lee filter. Its performance in terms of different criteria depends on several factors including image complexity where it sometimes occurs useless to process complex structure images (containing texture regions). We show that performance of the Lee filter can be predicted before starting image filtering and which can be done faster than the filtering itself. For this purpose, we propose to apply a trained neural network that employs analysis of image statistics and spectral features in a limited number of scanning windows. We show that many metrics including visual quality metrics can be predicted for SAR images acquired by Sentinel-1 sensor recently put into operation.

scholarly journals Selection of Lee Filter Window Size Based on Despeckling Efficiency Prediction for Sentinel SAR Images

2021 ◽  
Vol 13 (10) ◽  
pp. 1887
Author(s):  
Oleksii Rubel ◽  
Vladimir Lukin ◽  
Andrii Rubel ◽  
Karen Egiazarian
Keyword(s):  
Real Life ◽  
Block Size ◽  
Window Size ◽  
Prediction Errors ◽  
Sar Images ◽  
Scanning Window ◽  
Common Opinion ◽  
Filtering Efficiency ◽  
Trained Neural Network ◽  
Selection Of

Radar imaging has many advantages. Meanwhile, SAR images suffer from a noise-like phenomenon called speckle. Many despeckling methods have been proposed to date but there is still no common opinion as to what the best filter is and/or what are its parameters (window or block size, thresholds, etc.). The local statistic Lee filter is one of the most popular and best-known despeckling techniques in radar image processing. Using this filter and Sentinel-1 images as a case study, we show how filter parameters, namely scanning window size, can be selected for a given image based on filter efficiency prediction. Such a prediction can be carried out using a set of input parameters that can be easily and quickly calculated and employing a trained neural network that allows determining one or several criteria of filtering efficiency with high accuracy. The statistical analysis of the obtained results is carried out. This characterizes improvements due to the adaptive selection of the filter window size, both potential and based on prediction. We also analyzed what happens if, due to prediction errors, erroneous decisions are undertaken. Examples for simulated and real-life images are presented.

No-Reference Image Quality Assessment Based on Multi-Order Gradients Statistics

2020 ◽  
Vol 64 (1) ◽  
pp. 10505-1-10505-16
Author(s):  
Yin Zhang ◽  
Xuehan Bai ◽  
Junhua Yan ◽  
Yongqi Xiao ◽  
C. R. Chatwin ◽  
...  
Keyword(s):  
Neural Network ◽  
Image Quality ◽  
Quality Assessment ◽  
Image Quality Assessment ◽  
Assessment Method ◽  
Image Distortion ◽  
Image Feature ◽  
Reference Image ◽  
Gradient Magnitude ◽  
Distortion Type

Abstract A new blind image quality assessment method called No-Reference Image Quality Assessment Based on Multi-Order Gradients Statistics is proposed, which is aimed at solving the problem that the existing no-reference image quality assessment methods cannot determine the type of image distortion and that the quality evaluation has poor robustness for different types of distortion. In this article, an 18-dimensional image feature vector is constructed from gradient magnitude features, relative gradient orientation features, and relative gradient magnitude features over two scales and three orders on the basis of the relationship between multi-order gradient statistics and the type and degree of image distortion. The feature matrix and distortion types of known distorted images are used to train an AdaBoost_BP neural network to determine the image distortion type; the feature matrix and subjective scores of known distorted images are used to train an AdaBoost_BP neural network to determine the image distortion degree. A series of comparative experiments were carried out using Laboratory of Image and Video Engineering (LIVE), LIVE Multiply Distorted Image Quality, Tampere Image, and Optics Remote Sensing Image databases. Experimental results show that the proposed method has high distortion type judgment accuracy and that the quality score shows good subjective consistency and robustness for all types of distortion. The performance of the proposed method is not constricted to a particular database, and the proposed method has high operational efficiency.

Sign in / Sign up

Export Citation Format

Share Document