scholarly journals Discrete Atomic Transform-Based Lossy Compression of Three-Channel Remote Sensing Images with Quality Control

2021 ◽  
Vol 14 (1) ◽  
pp. 125
Author(s):  
Victor Makarichev ◽  
Irina Vasilyeva ◽  
Vladimir Lukin ◽  
Benoit Vozel ◽  
Andrii Shelestov ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Signal To Noise Ratio ◽  
Remote Sensing Data ◽  
Lossy Compression ◽  
Total Probability ◽  
Correct Classification ◽  
Absolute Deviation ◽  
Multispectral Data ◽  
Wide Range ◽  
Different Depths

Lossy compression of remote sensing data has found numerous applications. Several requirements are usually imposed on methods and algorithms to be used. A large compression ratio has to be provided, introduced distortions should not lead to sufficient reduction of classification accuracy, compression has to be realized quickly enough, etc. An additional requirement could be to provide privacy of compressed data. In this paper, we show that these requirements can be easily and effectively realized by compression based on discrete atomic transform (DAT). Three-channel remote sensing (RS) images that are part of multispectral data are used as examples. It is demonstrated that the quality of images compressed by DAT can be varied and controlled by setting maximal absolute deviation. This parameter also strictly relates to more traditional metrics as root mean square error (RMSE) and peak signal-to-noise ratio (PSNR) that can be controlled. It is also shown that there are several variants of DAT having different depths. Their performances are compared from different viewpoints, and the recommendations of transform depth are given. Effects of lossy compression on three-channel image classification using the maximum likelihood (ML) approach are studied. It is shown that the total probability of correct classification remains almost the same for a wide range of distortions introduced by lossy compression, although some variations of correct classification probabilities take place for particular classes depending on peculiarities of feature distributions. Experiments are carried out for multispectral Sentinel images of different complexities.

scholarly journals Preface: Remote Sensing for Flood Mapping and Monitoring of Flood Dynamics

2019 ◽  
Vol 11 (8) ◽  
pp. 943 ◽  
Author(s):  
Alessio Domeneghetti ◽  
Guy J.-P. Schumann ◽  
Angelica Tarpanelli
Keyword(s):  
Remote Sensing ◽  
Remote Sensing Data ◽  
Flood Mapping ◽  
Special Issue ◽  
Sensing Data ◽  
Wide Range ◽  
Flood Monitoring ◽  
Novel Processing ◽  
Flood Dynamics ◽  
Processing Techniques

This Special Issue is a collection of papers that focus on the use of remote sensing data and describe methods for flood monitoring and mapping. These articles span a wide range of topics; present novel processing techniques and review methods; and discuss limitations and challenges. This preface provides a brief overview of the content.

scholarly journals Lossy Compression of Multichannel Remote Sensing Images with Quality Control

2020 ◽  
Vol 12 (22) ◽  
pp. 3840
Author(s):  
Vladimir Lukin ◽  
Irina Vasilyeva ◽  
Sergey Krivenko ◽  
Fangfang Li ◽  
Sergey Abramov ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Classification Accuracy ◽  
Real Life ◽  
Remote Sensing Data ◽  
Original Data ◽  
Lossy Compression ◽  
Compressed Images ◽  
Training Methodology ◽  
Neural Network Classifiers

Lossy compression is widely used to decrease the size of multichannel remote sensing data. Alongside this positive effect, lossy compression may lead to a negative outcome as making worse image classification. Thus, if possible, lossy compression should be carried out carefully, controlling the quality of compressed images. In this paper, a dependence between classification accuracy of maximum likelihood and neural network classifiers applied to three-channel test and real-life images and quality of compressed images characterized by standard and visual quality metrics is studied. The following is demonstrated. First, a classification accuracy starts to decrease faster when image quality due to compression ratio increasing reaches a distortion visibility threshold. Second, the classes with a wider distribution of features start to “take pixels” from classes with narrower distributions of features. Third, a classification accuracy might depend essentially on the training methodology, i.e., whether features are determined from original data or compressed images. Finally, the drawbacks of pixel-wise classification are shown and some recommendations on how to improve classification accuracy are given.

scholarly journals Simulation of the microwave emission of multi-layered snowpacks using the Dense Media Radiative transfer theory: the DMRT-ML model

2013 ◽  
Vol 6 (4) ◽  
pp. 1061-1078 ◽  
Author(s):  
G. Picard ◽  
L. Brucker ◽  
A. Roy ◽  
F. Dupont ◽  
M. Fily ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Radiative Transfer ◽  
Thermal Emission ◽  
Remote Sensing Data ◽  
Microwave Emission ◽  
Alpine Regions ◽  
Wide Range ◽  
Dense Media ◽  
Wet Snow ◽  
Snow Conditions

Abstract. DMRT-ML is a physically based numerical model designed to compute the thermal microwave emission of a given snowpack. Its main application is the simulation of brightness temperatures at frequencies in the range 1–200 GHz similar to those acquired routinely by space-based microwave radiometers. The model is based on the Dense Media Radiative Transfer (DMRT) theory for the computation of the snow scattering and extinction coefficients and on the Discrete Ordinate Method (DISORT) to numerically solve the radiative transfer equation. The snowpack is modeled as a stack of multiple horizontal snow layers and an optional underlying interface representing the soil or the bottom ice. The model handles both dry and wet snow conditions. Such a general design allows the model to account for a wide range of snow conditions. Hitherto, the model has been used to simulate the thermal emission of the deep firn on ice sheets, shallow snowpacks overlying soil in Arctic and Alpine regions, and overlying ice on the large ice-sheet margins and glaciers. DMRT-ML has thus been validated in three very different conditions: Antarctica, Barnes Ice Cap (Canada) and Canadian tundra. It has been recently used in conjunction with inverse methods to retrieve snow grain size from remote sensing data. The model is written in Fortran90 and available to the snow remote sensing community as an open-source software. A convenient user interface is provided in Python.

scholarly journals BENCHMARKING DEEP LEARNING FRAMEWORKS FOR THE CLASSIFICATION OF VERY HIGH RESOLUTION SATELLITE MULTISPECTRAL DATA

2016 ◽  
Vol III-7 ◽  
pp. 83-88 ◽  
Author(s):  
M. Papadomanolaki ◽  
M. Vakalopoulou ◽  
S. Zagoruyko ◽  
K. Karantzalos
Keyword(s):  
Remote Sensing ◽  
Deep Learning ◽  
High Resolution ◽  
Remote Sensing Data ◽  
Multispectral Data ◽  
Sensing Data ◽  
Multispectral Remote Sensing ◽  
High Level ◽  
Learning Frameworks

In this paper we evaluated deep-learning frameworks based on Convolutional Neural Networks for the accurate classification of multispectral remote sensing data. Certain state-of-the-art models have been tested on the publicly available SAT-4 and SAT-6 high resolution satellite multispectral datasets. In particular, the performed benchmark included the <i>AlexNet</i>, <i>AlexNet-small</i> and <i>VGG</i> models which had been trained and applied to both datasets exploiting all the available spectral information. Deep Belief Networks, Autoencoders and other semi-supervised frameworks have been, also, compared. The high level features that were calculated from the tested models managed to classify the different land cover classes with significantly high accuracy rates <i>i.e.</i>, above 99.9%. The experimental results demonstrate the great potentials of advanced deep-learning frameworks for the supervised classification of high resolution multispectral remote sensing data.

scholarly journals Derivation of Spatially Distributed Thermal Comfort Levels in Jordan as Investigated From Remote Sensing, GIS Tools and Computational Methods

2021 ◽  
Author(s):  
ibrahim M. oroud
Keyword(s):  
Remote Sensing ◽  
Thermal Comfort ◽  
Remote Sensing Data ◽  
Dead Sea ◽  
Discrete Point ◽  
Jordan Valley ◽  
Comfort Levels ◽  
Gis Tools ◽  
Wide Range ◽  
Elevation Data

Abstract Thermal comfort is usually calculated using discrete point measurements. This procedure is not suitable to study thermal comfort for inhabited areas with rugged terrains where climate gradient is high. The wide availability of remote sensing data and GIS tools have revolutionized data management, processing and visualization. The present paper implemented digital elevation data, GIS tools and a computational algorithm to generate spatially continuous maps of climatological elements which were employed to derive thermal comfort levels across Jordan. Results show detailed information of the spatial distribution of the degree of thermal comfort in winter and summer across the country which cannot be resolved using discrete point measurements. It is shown that the mountainous areas in the country, where most urban centers are situated, experience “slightly warm” to “warm” indoor apparent temperatures in summer. The Jordan Valley and the desert experience high indoor apparent temperatures in summer. Cold conditions prevail over most parts of the country, with the heating degree days ranging from 2100 in the southern mountains to values close to zero near the Dead Sea area. The presented procedure demonstrated that the very low levels of ambient vapor pressure is an important atmospheric forcing contributing to the widespread cold conditions prevailing over the desert areas in winter. The efficiency of direct evaporative cooling systems to achieve thermal comfort in the various parts of the country is investigated. The procedure presented can be used over regional scales with different levels of spatial resolutions for a wide range of climatological studies.

scholarly journals Prediction of the Kiwifruit Decline Syndrome in Diseased Orchards by Remote Sensing

2020 ◽  
Vol 12 (14) ◽  
pp. 2194
Author(s):  
Francesco Savian ◽  
Marta Martini ◽  
Paolo Ermacora ◽  
Stefan Paulus ◽  
Anne-Katrin Mahlein
Keyword(s):  
Remote Sensing ◽  
Multispectral Imaging ◽  
Remote Sensing Data ◽  
Ground Truth ◽  
First Record ◽  
Temperature Data ◽  
Expert Assessment ◽  
Plant Vigour ◽  
Multispectral Data ◽  
Thermal Data

Eight years after the first record in Italy, Kiwifruit Decline (KD), a destructive disease causing root rot, has already affected more than 25% of the area under kiwifruit cultivation in Italy. Diseased plants are characterised by severe decay of the fine roots and sudden wilting of the canopy, which is only visible after the season’s first period of heat (July–August). The swiftness of symptom appearance prevents correct timing and positioning for sampling of the disease, and is therefore a barrier to aetiological studies. The aim of this study is to test the feasibility of thermal and multispectral imaging for the detection of KD using an unsupervised classifier. Thus, RGB, multispectral and thermal data from a kiwifruit orchard, with healthy and diseased plants, were acquired simultaneously during two consecutive growing seasons (2017–2018) using an Unmanned Aerial Vehicle (UAV) platform. Data reduction was applied to the clipped areas of the multispectral and thermal data from the 2017 survey. Reduced data were then classified with two unsupervised algorithms, a K-means and a hierarchical method. The plant vigour (canopy size and presence/absence of wilted leaves) and the health shifts exhibited by asymptomatic plants between 2017 and 2018 were evaluated from RGB data via expert assessment and used as the ground truth for cluster interpretation. Multispectral data showed a high correlation with plant vigour, while temperature data demonstrated a good potential use in predicting health shifts, especially in highly vigorous plants that were asymptomatic in 2017 and became symptomatic in 2018. The accuracy of plant vigour assessment was above 73% when using multispectral data, while clustering of the temperature data allowed the prediction of disease outbreak one year in advance, with an accuracy of 71%. Based on our results, the unsupervised clustering of remote sensing data could be a reliable tool for the identification of sampling areas, and can greatly improve aetiological studies of this new disease in kiwifruit.

A method for remote sensing image denoising based on structured dictionary learning and cloud computing

2020 ◽  
pp. 002072092093107
Author(s):  
Ru Yang ◽  
Zhentao Qin ◽  
Xiangyu Zhao
Keyword(s):  
Remote Sensing ◽  
Cloud Computing ◽  
Image Denoising ◽  
Dictionary Learning ◽  
Learning Algorithm ◽  
Signal To Noise Ratio ◽  
Remote Sensing Data ◽  
Remote Sensing Image ◽  
Multispectral Image ◽  
Structured Dictionary

With the emerging technology of remote sensing, a huge amount of remote sensing data is collected and stored in the remote sensin02222g platform, and the transmission and processing of data on the platform is extremely wasteful. It is essential to incorporate the speedy remote sensing processing services in an integrated cloud computing architecture. In order to improve the denoising ability of remote sensing image, a new structured dictionary-based method for multispectral image denoising based on cluster is proposed. This method incorporates both the locality of spatial and the correlation across spectrum of multispectral image. Remote sensing image is divided into different groups by clustering, and sparse representation coefficients of spatial and spectral and dictionary is obtained according to the dictionary learning algorithm. After threshold processing, the similar blocks are averaged and realized with multispectral remote sensing image denoising. The algorithm is applied to denoise the noisy remote sensing image of Maoergai area in the upper Minjiang which contain typical vegetation and soil is chosen as study area, simulation results show that higher peak-signal to noise ratio can be obtained as compared to other recent image denoising methods.

Evaluation of Lossy Compressed Mosaic for SPOT-6/7 Remote Sensing Data in SPACeMAP

2021 ◽  
Vol 5 (3) ◽  
pp. 271
Author(s):  
Agnes S Payani ◽  
Siti D Wahyuningsih ◽  
Gusti D Yudha ◽  
Nico Cendiana ◽  
Hanna Afida ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Compression Ratio ◽  
Signal To Noise Ratio ◽  
Remote Sensing Data ◽  
Large Data ◽  
Comparison Method ◽  
Portal System ◽  
Process Duration ◽  
Sensing Data ◽  
Mosaic Images

SPACeMAP is a remote-sensing data portal system owned by LAPAN used to distribute mosaic data of Medium-Resolution to Very-High-Resolution for Provincial Governments. The frequently arising problem is that mosaic images have very large data size, especially for SPOT-6/7 mosaic images. The increasing number of data and users may affect the data loading process on the portal so that mosaic data compression can be considered. SPACeMAP has the Image Compressor feature using the Tile and Line algorithms with a compression ratio (target rate) recommended for optics (15 to 20). This study aims to determine the best algorithm and target rate to get compressed mosaic SPOT-6/7 imagery. The comparison method was done qualitatively through visual comparison and quantitatively by using Compression Ratio (CR), Bit per Pixel (BPP), and Peak Signal to Noise Ratio (PSNR).  Results of the experiment show that, quantitatively, both Tile and Line algorithms give a different performance, depends on the zoom level and land cover characteristics. In terms of the qualitative result, the Tile algorithm gives better overall results compare to the Line algorithm. Quantitatively, both algorithms show good performance in the homogenous area. The target rate difference on the testing range does not affect process duration, nevertheless, the Line algorithm has a long process duration compare to the Tile algorithm. However, compression mosaics with lower or higher resolution remote sensing data may provide different results. Hence, this need be addressed on further studies.

scholarly journals Enhancement of Component Images of Multispectral Data by Denoising with Reference

2019 ◽  
Vol 11 (6) ◽  
pp. 611 ◽  
Author(s):  
Sergey Abramov ◽  
Mikhail Uss ◽  
Vladimir Lukin ◽  
Benoit Vozel ◽  
Kacem Chehdi ◽  
...  
Keyword(s):  
Remote Sensing ◽  
High Efficiency ◽  
Real Life ◽  
Remote Sensing Data ◽  
Nonlinear Transformations ◽  
High Quality ◽  
Multispectral Data ◽  
Sensing Data ◽  
Reference Images ◽  
Multispectral Remote Sensing

Multispectral remote sensing data may contain component images that are heavily corrupted by noise and the pre-filtering (denoising) procedure is often applied to enhance these component images. To do this, one can use reference images—component images having relatively high quality and that are similar to the image subject to pre-filtering. Here, we study the following problems: how to select component images that can be used as references (e.g., for the Sentinel multispectral remote sensing data) and how to perform the actual denoising. We demonstrate that component images of the same resolution as well as component images of a better resolution can be used as references. To provide high efficiency of denoising, reference images have to be transformed using linear or nonlinear transformations. This paper proposes a practical approach to doing this. Examples of denoising tests and real-life images demonstrate high efficiency of the proposed approach.

Sign in / Sign up

Export Citation Format

Share Document