scholarly journals CONCEPTUAL FRAMEWORK OF COMBINED PIXEL AND OBJECT-BASED METHOD FOR DELINEATION OF DEBRIS-COVERED GLACIERS

2018 ◽  
Vol IV-5 ◽  
pp. 173-180 ◽  
Author(s):  
R. Sahu ◽  
R. D. Gupta
Keyword(s):  
High Spatial Resolution ◽  
Remote Sensing Data ◽  
Optical Data ◽  
New Approach ◽  
Shadow Area ◽  
Object Based ◽  
Thermal Data ◽  
Automatic Mapping ◽  
Glacier Mapping ◽  
Manual Correction

<p><strong>Abstract.</strong> Delineation of the glacier is an important task for understanding response of glaciers to climate. In Himalayan region, most of the glaciers are covered with debris. Supraglacial debris works as an obstacle for automatic mapping of glacier using remote sensing data. Different methods have been used to reduce this difficulty based on pixel-based and object-based approaches using optical data, thermal data and DEM. Pixel-based glacier mapping is a traditional method for delineation of the glacier but the object-based method has emerged as a new approach in cryosphere application leading to its successful application in different applications. All pixel-based methods require some degree of manual correction because these can’t be delineated automatically, especially in shadow area and debris covered part of the glacier. In the majority of studies, the object-based method has provided higher accuracy to delineate the debris-covered glacier. Spatially high spatial resolution satellite data is best suited for object-based image classification. In future, a combination of pixel-based method and object-based method can be attempted for delineation of the debris-covered glacier along with its critical analysis for suitability. The present paper critically reviews pixel-based and object-based methods as well as provides a framework for combined pixel and object-based method for delineation of debris-covered glacier.</p>

scholarly journals A Meta-Methodology for Improving Land Cover and Land Use Classification with SAR Imagery

2020 ◽  
Vol 12 (6) ◽  
pp. 961 ◽  
Author(s):  
Marinalva Dias Soares ◽  
Luciano Vieira Dutra ◽  
Gilson Alexandre Ostwald Pedro da Costa ◽  
Raul Queiroz Feitosa ◽  
Rogério Galante Negri ◽  
...  
Keyword(s):  
Remote Sensing Data ◽  
Data Classification ◽  
Test Site ◽  
Radar Data ◽  
Input Image ◽  
Optical Data ◽  
Land Use Classification ◽  
Object Based ◽  
Sar Imagery ◽  
Small Change

Per-point classification is a traditional method for remote sensing data classification, and for radar data in particular. Compared with optical data, the discriminative power of radar data is quite limited, for most applications. A way of trying to overcome these difficulties is to use Region-Based Classification (RBC), also referred to as Geographical Object-Based Image Analysis (GEOBIA). RBC methods first aggregate pixels into homogeneous objects, or regions, using a segmentation procedure. Moreover, segmentation is known to be an ill-conditioned problem because it admits multiple solutions, and a small change in the input image, or segmentation parameters, may lead to significant changes in the image partitioning. In this context, this paper proposes and evaluates novel approaches for SAR data classification, which rely on specialized segmentations, and on the combination of partial maps produced by classification ensembles. Such approaches comprise a meta-methodology, in the sense that they are independent from segmentation and classification algorithms, and optimization procedures. Results are shown that improve the classification accuracy from Kappa = 0.4 (baseline method) to a Kappa = 0.77 with the presented method. Another test site presented an improvement from Kappa = 0.36 to a maximum of 0.66 also with radar data.

scholarly journals ASSESSMENT OF LANDSLIDE-INDUCED MORPHOLOGY CHANGES USING AN OBJECT-BASED IMAGE ANALYSIS APPROACH: A CASE STUDY OF HÍTARDALUR, ICELAND

2019 ◽  
Vol XLII-3/W8 ◽  
pp. 109-114
Author(s):  
Z. Dabiri ◽  
D. Hölbling ◽  
L. Abad ◽  
D. Tiede
Keyword(s):  
Remote Sensing ◽  
Image Analysis ◽  
Remote Sensing Data ◽  
Optical Data ◽  
Sensing Data ◽  
Object Based Image Analysis ◽  
Object Based ◽  
Spatio Temporal ◽  
The Impact ◽  
Morphology Changes

<p><strong>Abstract.</strong> On July 7, 2018, a large landslide occurred at the eastern slope of the Fagraskógarfjall Mountain in Hítardalur valley in West Iceland. The landslide dammed the river, led to the formation of a lake and, consequently, to a change in the river course. The main focus of this research is to develop a knowledge-based expert system using an object-based image analysis (OBIA) approach for identifying morphology changes caused by the Hítardalur landslide. We use synthetic aperture radar (SAR) and optical remote sensing data, in particular from Sentinel-1/2 for detection of the landslide and its effects on the river system. We extracted and classified the landslide area, the landslide-dammed lake, other lakes and the river course using intensity information from S1 and spectral information from S2 in the object-based framework. Future research will focus on further developing this approach to support mapping and monitoring of the spatio-temporal dynamics of surface morphology in an object-based framework by combining SAR and optical data. The results can reveal details on the applicability of different remote sensing data for the spatio-temporal investigation of landslides, landslide-induced river course changes and lake formation and lead to a better understanding of the impact of large landslides on river systems.</p>

scholarly journals Mapping boreal peatland ecosystem types from multitemporal radar and optical satellite imagery

2017 ◽  
Vol 47 (4) ◽  
pp. 545-559 ◽  
Author(s):  
L.L. Bourgeau-Chavez ◽  
S. Endres ◽  
R. Powell ◽  
M.J. Battaglia ◽  
B. Benscoter ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Remote Sensing Data ◽  
Optical Data ◽  
Optical Remote Sensing ◽  
Fuel Loading ◽  
Alos Palsar ◽  
Upper Peninsula ◽  
Machine Learning Classification ◽  
Object Based ◽  
Accuracy Assessments

The ability to distinguish peatland types at the landscape scale has implications for inventory, conservation, estimation of carbon storage, fuel loading, and postfire carbon emissions, among others. This paper presents a multisensor, multiseason remote sensing approach to delineate boreal peatland types (wooded bog, open fen, shrubby fen, treed fen) using a combination of multiple dates of L-band (24 cm) synthetic aperture radar (SAR) from ALOS PALSAR, C-band (∼5.6 cm) from ERS-1 or ERS-2, and Landsat 5 TM optical remote sensing data. Imagery was first evaluated over a small test area of boreal Alberta, Canada, to determine the feasibility of using multisensor SAR and optical data to discriminate peatland types. Then object-based and (or) machine-learning classification algorithms were applied to 3.4 million ha of peatland-rich subregions of Alberta, Canada, and the 4.24 million ha region of Michigan’s Upper Peninsula where peatlands are less dominant. Accuracy assessments based on field-sampled sites show high overall map accuracies (93%–94% for Alberta and Michigan), which exceed those of previous mapping efforts.

scholarly journals Classification of Very-High-Spatial-Resolution Aerial Images Based on Multiscale Features with Limited Semantic Information

2021 ◽  
Vol 13 (3) ◽  
pp. 364
Author(s):  
Han Gao ◽  
Jinhui Guo ◽  
Peng Guo ◽  
Xiuwan Chen
Keyword(s):  
Deep Learning ◽  
Land Cover ◽  
Spatial Resolution ◽  
Large Scale ◽  
High Spatial Resolution ◽  
Training Data ◽  
Aerial Images ◽  
Rural Landscapes ◽  
Feature Representations ◽  
Object Based

Recently, deep learning has become the most innovative trend for a variety of high-spatial-resolution remote sensing imaging applications. However, large-scale land cover classification via traditional convolutional neural networks (CNNs) with sliding windows is computationally expensive and produces coarse results. Additionally, although such supervised learning approaches have performed well, collecting and annotating datasets for every task are extremely laborious, especially for those fully supervised cases where the pixel-level ground-truth labels are dense. In this work, we propose a new object-oriented deep learning framework that leverages residual networks with different depths to learn adjacent feature representations by embedding a multibranch architecture in the deep learning pipeline. The idea is to exploit limited training data at different neighboring scales to make a tradeoff between weak semantics and strong feature representations for operational land cover mapping tasks. We draw from established geographic object-based image analysis (GEOBIA) as an auxiliary module to reduce the computational burden of spatial reasoning and optimize the classification boundaries. We evaluated the proposed approach on two subdecimeter-resolution datasets involving both urban and rural landscapes. It presented better classification accuracy (88.9%) compared to traditional object-based deep learning methods and achieves an excellent inference time (11.3 s/ha).

scholarly journals Synergetic Use of Sentinel-1 and Sentinel-2 Data for Soil Moisture Mapping at Plot Scale

2018 ◽  
Vol 10 (8) ◽  
pp. 1285 ◽  
Author(s):  
Reza Attarzadeh ◽  
Jalal Amini ◽  
Claudia Notarnicola ◽  
Felix Greifeneder
Keyword(s):  
Soil Moisture ◽  
Optical Data ◽  
Estimation Accuracy ◽  
Support Vector ◽  
Practical Applications ◽  
Initial Stage ◽  
Object Based ◽  
Single Polarization ◽  
Selection Of

This paper presents an approach for retrieval of soil moisture content (SMC) by coupling single polarization C-band synthetic aperture radar (SAR) and optical data at the plot scale in vegetated areas. The study was carried out at five different sites with dominant vegetation cover located in Kenya. In the initial stage of the process, different features are extracted from single polarization mode (VV polarization) SAR and optical data. Subsequently, proper selection of the relevant features is conducted on the extracted features. An advanced state-of-the-art machine learning regression approach, the support vector regression (SVR) technique, is used to retrieve soil moisture. This paper takes a new look at soil moisture retrieval in vegetated areas considering the needs of practical applications. In this context, we tried to work at the object level instead of the pixel level. Accordingly, a group of pixels (an image object) represents the reality of the land cover at the plot scale. Three approaches, a pixel-based approach, an object-based approach, and a combination of pixel- and object-based approaches, were used to estimate soil moisture. The results show that the combined approach outperforms the other approaches in terms of estimation accuracy (4.94% and 0.89 compared to 6.41% and 0.62 in terms of root mean square error (RMSE) and R2), flexibility on retrieving the level of soil moisture, and better quality of visual representation of the SMC map.

scholarly journals Calibration of the depth invariant algorithm to monitor the tidal action of Rabigh City at the Red Sea Coast, Saudi Arabia

2020 ◽  
Vol 12 (1) ◽  
pp. 1666-1678
Author(s):  
Mohammed H. Aljahdali ◽  
Mohamed Elhag
Keyword(s):  
Remote Sensing ◽  
Saudi Arabia ◽  
Wind Speed ◽  
Red Sea ◽  
Remote Sensing Data ◽  
Microwave Remote Sensing ◽  
Optical Data ◽  
Mean Values ◽  
Sensing Data ◽  
The Mean

AbstractRabigh is a thriving coastal city located at the eastern bank of the Red Sea, Saudi Arabia. The city has suffered from shoreline destruction because of the invasive tidal action powered principally by the wind speed and direction over shallow waters. This study was carried out to calibrate the water column depth in the vicinity of Rabigh. Optical and microwave remote sensing data from the European Space Agency were collected over 2 years (2017–2018) along with the analog daily monitoring of tidal data collected from the marine station of Rabigh. Depth invariant index (DII) was implemented utilizing the optical data, while the Wind Field Estimation algorithm was implemented utilizing the microwave data. The findings of the current research emphasis on the oscillation behavior of the depth invariant mean values and the mean astronomical tides resulted in R2 of 0.75 and 0.79, respectively. Robust linear regression was established between the astronomical tide and the mean values of the normalized DII (R2 = 0.81). The findings also indicated that January had the strongest wind speed solidly correlated with the depth invariant values (R2 = 0.92). Therefore, decision-makers can depend on remote sensing data as an efficient tool to monitor natural phenomena and also to regulate human activities in fragile ecosystems.

An Adaptive Tracking Algorithm for Convection in Simulated and Remote Sensing Data

2021 ◽  
Vol 60 (4) ◽  
pp. 513-526
Author(s):  
Bhupendra A. Raut ◽  
Robert Jackson ◽  
Mark Picel ◽  
Scott M. Collis ◽  
Martin Bergemann ◽  
...  
Keyword(s):  
Simulated Data ◽  
Remote Sensing Data ◽  
Life Cycles ◽  
Tracking Algorithm ◽  
Two Dimensional ◽  
Computationally Efficient ◽  
Convective Systems ◽  
Object Based ◽  
Modular Platform ◽  
Convective Cells

AbstractA robust and computationally efficient object tracking algorithm is developed by incorporating various tracking techniques. Physical properties of the objects, such as brightness temperature or reflectivity, are not considered. Therefore, the algorithm is adaptable for tracking convection-like features in simulated data and remotely sensed two-dimensional images. In this algorithm, a first guess of the motion, estimated using the Fourier phase shift, is used to predict the candidates for matching. A disparity score is computed for each target–candidate pair. The disparity also incorporates overlapping criteria in the case of large objects. Then the Hungarian method is applied to identify the best pairs by minimizing the global disparity. The high-disparity pairs are unmatched, and their target and candidate are declared expired and newly initiated objects, respectively. They are tested for merger and split on the basis of their size and overlap with the other objects. The sensitivity of track duration is shown for different disparity and size thresholds. The paper highlights the algorithm’s ability to study convective life cycles using radar and simulated data over Darwin, Australia. The algorithm skillfully tracks individual convective cells (a few pixels in size) and large convective systems. The duration of tracks and cell size are found to be lognormally distributed over Darwin. The evolution of size and precipitation types of isolated convective cells is presented in the Lagrangian perspective. This algorithm is part of a vision for a modular platform [viz., TINT is not TITAN (TINT) and Tracking and Object-Based Analysis of Clouds (tobac)] that will evolve into a sustainable choice to analyze atmospheric features.

scholarly journals CubeSats Enable High Spatiotemporal Retrievals of Crop-Water Use for Precision Agriculture

2018 ◽  
Vol 10 (12) ◽  
pp. 1867 ◽  
Author(s):  
Bruno Aragon ◽  
Rasmus Houborg ◽  
Kevin Tu ◽  
Joshua B. Fisher ◽  
Matthew McCabe
Keyword(s):  
Remote Sensing ◽  
Eddy Covariance ◽  
Water Use ◽  
Spatial Resolution ◽  
Precision Agriculture ◽  
High Spatial Resolution ◽  
Assessment Tools ◽  
Optical Data ◽  
Crop Water ◽  
Crop Water Use

Remote sensing based estimation of evapotranspiration (ET) provides a direct accounting of the crop water use. However, the use of satellite data has generally required that a compromise between spatial and temporal resolution is made, i.e., one could obtain low spatial resolution data regularly, or high spatial resolution occasionally. As a consequence, this spatiotemporal trade-off has tended to limit the impact of remote sensing for precision agricultural applications. With the recent emergence of constellations of small CubeSat-based satellite systems, these constraints are rapidly being removed, such that daily 3 m resolution optical data are now a reality for earth observation. Such advances provide an opportunity to develop new earth system monitoring and assessment tools. In this manuscript we evaluate the capacity of CubeSats to advance the estimation of ET via application of the Priestley-Taylor Jet Propulsion Laboratory (PT-JPL) retrieval model. To take advantage of the high-spatiotemporal resolution afforded by these systems, we have integrated a CubeSat derived leaf area index as a forcing variable into PT-JPL, as well as modified key biophysical model parameters. We evaluate model performance over an irrigated farmland in Saudi Arabia using observations from an eddy covariance tower. Crop water use retrievals were also compared against measured irrigation from an in-line flow meter installed within a center-pivot system. To leverage the high spatial resolution of the CubeSat imagery, PT-JPL retrievals were integrated over the source area of the eddy covariance footprint, to allow an equivalent intercomparison. Apart from offering new precision agricultural insights into farm operations and management, the 3 m resolution ET retrievals were shown to explain 86% of the observed variability and provide a relative RMSE of 32.9% for irrigated maize, comparable to previously reported satellite-based retrievals. An observed underestimation was diagnosed as a possible misrepresentation of the local surface moisture status, highlighting the challenge of high-resolution modeling applications for precision agriculture and informing future research directions. .

scholarly journals AUTOMATIC MAPPING OF GLACIER BASED ON SAR IMAGERY BY BENEFITS OF FREELY OPTICAL AND THERMAL DATA

2015 ◽  
Vol XL-3/W2 ◽  
pp. 47-51
Author(s):  
L. Fang ◽  
L. Hoegner ◽  
U. Stilla
Keyword(s):  
Land Surface ◽  
Low Resolution ◽  
Glacier Surface ◽  
Thermal Data ◽  
Automatic Mapping ◽  
Resources Evaluation ◽  
Sar Imagery ◽  
Normalized Difference Snow Index ◽  
Occurrence Matrix

For many research applications like water resources evaluation, determination of glacier specific changes, and for calculation of the past and future contribution of glaciers to sea-level change, parameters about the size and spatial distribution of glaciers is crucial. In this paper, an automatic method for determination of glacier surface area using single track high resolution TerraSAR-X imagery by benefits of low resolution optical and thermal data is presented. Based on the normalized difference snow index (NDSI) and land surface temperature (LST) map generated from optical and thermal data combined with a surface slope data, a low resolution binary mask was derived used for the supervised classification of glacier using SAR imagery. Then, a set of suitable features is derived from the SAR intensity image, such as the texture information generated based on the gray level co-occurrence matrix (GLCM), and the intensity values. With these features, the glacier surface is discriminated from the background by Random Forests (RF) method.

Sign in / Sign up

Export Citation Format

Share Document