scholarly journals Sea Ice Classification of SAR Imagery Based on Convolution Neural Networks

2021 ◽  
Vol 13 (9) ◽  
pp. 1734
Author(s):  
Salman Khaleghian ◽  
Habib Ullah ◽  
Thomas Kræmer ◽  
Nick Hughes ◽  
Torbjørn Eltoft ◽  
...  
Keyword(s):  
Sea Ice ◽  
Ad Hoc ◽  
Data Augmentation ◽  
Open Water ◽  
Classification Performance ◽  
Training Data ◽  
Optical Data ◽  
Sar Images ◽  
Water Classification ◽  
Sar Imagery

We explore new and existing convolutional neural network (CNN) architectures for sea ice classification using Sentinel-1 (S1) synthetic aperture radar (SAR) data by investigating two key challenges: binary sea ice versus open-water classification, and a multi-class sea ice type classification. The analysis of sea ice in SAR images is challenging because of the thermal noise effects and ambiguities in the radar backscatter for certain conditions that include the reflection of complex information from sea ice surfaces. We use manually annotated SAR images containing various sea ice types to construct a dataset for our Deep Learning (DL) analysis. To avoid contamination between classes we use a combination of near-simultaneous SAR images from S1 and fine resolution cloud-free optical data from Sentinel-2 (S2). For the classification, we use data augmentation to adjust for the imbalance of sea ice type classes in the training data. The SAR images are divided into small patches which are processed one at a time. We demonstrate that the combination of data augmentation and training of a proposed modified Visual Geometric Group 16-layer (VGG-16) network, trained from scratch, significantly improves the classification performance, compared to the original VGG-16 model and an ad hoc CNN model. The experimental results show both qualitatively and quantitatively that our models produce accurate classification results.

Early detection of the Weddell polynya re-opening using SAR imagery

2020 ◽  
Author(s):  
Adriano Lemos ◽  
Céline Heuzé
Keyword(s):  
Early Detection ◽  
Sea Ice ◽  
Open Water ◽  
Weddell Sea ◽  
Small Scale ◽  
Ice Thickness ◽  
Sar Images ◽  
Sea Ice Thickness ◽  
Sar Imagery ◽  
Microwave Sensors

<p>The sea ice thickness in the Weddell Sea during the austral winter normally exceeds 1 m, but in the case of a polynya, this thickness decreases to 10 cm or less. There are two theories as to why the Weddell Polynya opens: 1) comparatively warm oceanic water upwelling from its nominal depth of several hundred metres to the surface where it melts the sea ice from underneath; or 2) opening of a lead by a passing storm, lead which will then be maintained open either by the atmosphere or ocean and grow. The objective of this study is to estimate how long in advance the recent Weddell Polynya opening could have been detected by synthetic aperture radar (SAR) images due to the decrease of the sea ice thickness and/or early appearance of leads. We use high temporal and spatial resolution SAR images from the Sentinel-1 constellation (C-band) and ALOS2 (L-band) during the austral winters 2014-2018. We use an adapted version of the algorithm developed by Aldenhoff et al. (2018) to monitor changes in sea ice thickness over the polynya region. The algorithm detects the transition of the sea ice thickness through changes in small scale surface roughness and thus reduced backscatter, and allowing us to distinguish three different categories: ice, thin ice, and open water. The transition from ice to thin ice and then to open water indicates that the polynya is melted from under, whereas a direct transition from ice to open water will reveal leads. The high resolution and good coverage of the SAR imagery, and a combined effort of different satellites sensors (e.g. infrared and microwave sensors), opens the possibility of an early detection of Weddell Polynya opening.</p>

scholarly journals Operational algorithm for ice/water classification on dual-polarized RADARSAT-2 images

2016 ◽  
Author(s):  
Natalia Zakhvatkina ◽  
Anton Korosov ◽  
Stefan Muckenhuber ◽  
Stein Sandven ◽  
Mohamed Babiker
Keyword(s):  
Sea Ice ◽  
Texture Features ◽  
Open Water ◽  
Support Vector ◽  
Technical Problems ◽  
Additional Information ◽  
Franz Josef Land ◽  
Water Classification ◽  
Dual Polarized ◽  
Supervised Image Classification

Abstract. Synthetic aperture radar (SAR) data from RADARSAT-2 (RS2) taken in dual-polarization mode provide additional information for discriminating sea ice and open water compared to single-polarization data. We have developed a fully automatic algorithm to distinguish between open water (rough/calm) and sea ice based on dual-polarized RS2 SAR images. Several technical problems inherent in RS2 data were solved on the pre-processing stage including thermal noise reduction in HV-polarization channel and correction of angular backscatter dependency on HH-polarization. Texture features are used as additional information for supervised image classification based on Support Vector Machines (SVM) approach. The main regions of interest are the ice-covered seas between Greenland and Franz Josef Land. The algorithm has been trained using 24 RS2 scenes acquired during winter months in 2011 and 2012, and validated against the manually derived ice chart product from the Norwegian Meteorological Institute. Between 2013 and 2015, 2705 RS2 scenes have been utilised for validation and the average classification accuracy has been found to be 91 ± 4 %.

scholarly journals Delineation of Cocoa Agroforests Using Multiseason Sentinel-1 SAR Images: A Low Grey Level Range Reduces Uncertainties in GLCM Texture-Based Mapping.

2019 ◽  
Vol 8 (4) ◽  
pp. 179 ◽  
Author(s):  
Frederick N. Numbisi ◽  
Frieke M. B. Van Coillie ◽  
Robert De Wulf
Keyword(s):  
Optical Sensors ◽  
Spectral Characteristics ◽  
Texture Feature ◽  
Image Texture ◽  
Optical Data ◽  
Grey Level ◽  
Sar Images ◽  
Quantization Level ◽  
Class Prediction ◽  
Sar Imagery

Delineating the cropping area of cocoa agroforests is a major challenge in quantifying the contribution of land use expansion to tropical deforestation. Discriminating cocoa agroforests from tropical transition forests using multispectral optical images is difficult due to the similarity of the spectral characteristics of their canopies. Moreover, the frequent cloud cover in the tropics greatly impedes optical sensors. This study evaluated the potential of multiseason Sentinel-1 C-band synthetic aperture radar (SAR) imagery to discriminate cocoa agroforests from transition forests in a heterogeneous landscape in central Cameroon. We used an ensemble classifier, Random Forest (RF), to average the SAR image texture features of a grey level co-occurrence matrix (GLCM) across seasons. We then compared the classification performance with results from RapidEye optical data. Moreover, we assessed the performance of GLCM texture feature extraction at four different grey levels of quantization: 32 bits, 8 bits, 6 bits, and 4 bits. The classification’s overall accuracy (OA) from texture-based maps outperformed that from an optical image. The highest OA (88.8%) was recorded at the 6 bits grey level. This quantization level, in comparison to the initial 32 bits in the SAR images, reduced the class prediction error by 2.9%. The texture-based classification achieved an acceptable accuracy and revealed that cocoa agroforests have considerably fragmented the remnant transition forest patches. The Shannon entropy (H) or uncertainty provided a reliable validation of the class predictions and enabled inferences about discriminating inherently heterogeneous vegetation categories.

scholarly journals Urban Intersection Classification: A Comparative Analysis

Sensors ◽  
2021 ◽  
Vol 21 (18) ◽  
pp. 6269
Author(s):  
Augusto Luis Ballardini ◽  
Álvaro Hernández Saz ◽  
Sandra Carrasco Limeros ◽  
Javier Lorenzo ◽  
Ignacio Parra Alonso ◽  
...  
Keyword(s):  
Ad Hoc ◽  
Data Augmentation ◽  
Comprehensive Evaluation ◽  
Temporal Integration ◽  
Individual Performance ◽  
Training Data ◽  
Real World Data ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Integration Schemes

Understanding the scene in front of a vehicle is crucial for self-driving vehicles and Advanced Driver Assistance Systems, and in urban scenarios, intersection areas are one of the most critical, concentrating between 20% to 25% of road fatalities. This research presents a thorough investigation on the detection and classification of urban intersections as seen from onboard front-facing cameras. Different methodologies aimed at classifying intersection geometries have been assessed to provide a comprehensive evaluation of state-of-the-art techniques based on Deep Neural Network (DNN) approaches, including single-frame approaches and temporal integration schemes. A detailed analysis of most popular datasets previously used for the application together with a comparison with ad hoc recorded sequences revealed that the performances strongly depend on the field of view of the camera rather than other characteristics or temporal-integrating techniques. Due to the scarcity of training data, a new dataset is created by performing data augmentation from real-world data through a Generative Adversarial Network (GAN) to increase generalizability as well as to test the influence of data quality. Despite being in the relatively early stages, mainly due to the lack of intersection datasets oriented to the problem, an extensive experimental activity has been performed to analyze the individual performance of each proposed systems.

scholarly journals Extraction of Sea Ice Cover by Sentinel-1 SAR Based on SVM with Unsupervised Generation of Training Data

2020 ◽  
Author(s):  
Xiaoming Li ◽  
Yan Sun ◽  
Qiang Zhang
Keyword(s):  
Machine Learning ◽  
Sea Ice ◽  
Learning Algorithm ◽  
Texture Features ◽  
Open Water ◽  
Ice Cover ◽  
Training Data ◽  
Support Vector ◽  
Training Samples

In this paper, we focus on developing a novel method to extract sea ice cover (i.e., discrimination/classification of sea ice and open water) using Sentinel-1 (S1) cross-polarization (vertical-horizontal, VH or horizontal-vertical, HV) data in extra wide (EW) swath mode based on the machine learning algorithm support vector machine (SVM). The classification basis includes the S1 radar backscatter coefficients and texture features that are calculated from S1 data using the gray level co-occurrence matrix (GLCM). Different from previous methods where appropriate samples are manually selected to train the SVM to classify sea ice and open water, we proposed a method of unsupervised generation of the training samples based on two GLCM texture features, i.e. entropy and homogeneity, that have contrasting characteristics on sea ice and open water. We eliminate the most uncertainty of selecting training samples in machine learning and achieve automatic classification of sea ice and open water by using S1 EW data. The comparison shows good agreement between the SAR-derived sea ice cover using the proposed method and a visual inspection, of which the accuracy reaches approximately 90% - 95% based on a few cases. Besides this, compared with the analyzed sea ice cover data Ice Mapping System (IMS) based on 728 S1 EW images, the accuracy of extracted sea ice cover by using S1 data is more than 80%.

scholarly journals A New Multispectral Data Augmentation Technique Based on Data Imputation

2021 ◽  
Vol 13 (23) ◽  
pp. 4875
Author(s):  
Álvaro Acción ◽  
Francisco Argüello ◽  
Dora B. Heras
Keyword(s):  
Remote Sensing ◽  
Data Augmentation ◽  
Matrix Completion ◽  
Computational Cost ◽  
High Energy ◽  
Classification Performance ◽  
Training Data ◽  
High Spectral Resolution ◽  
Data Imputation ◽  
Imputation Methods

Deep Learning (DL) has been recently introduced into the hyperspectral and multispectral image classification landscape. Despite the success of DL in the remote sensing field, DL models are computationally intensive due to the large number of parameters they need to learn. The high density of information present in remote sensing imagery with high spectral resolution can make the application of DL models to large scenes challenging. Methods such as patch-based classification require large amounts of data to be processed during the training and prediction stages, which translates into long processing times and high energy consumption. One of the solutions to decrease the computational cost of these models is to perform segment-based classification. Segment-based classification schemes can significantly decrease training and prediction times, and also offer advantages over simply reducing the size of the training datasets by randomly sampling training data. The lack of a large enough number of samples can, however, pose an additional challenge, causing these models to not generalize properly. Data augmentation methods are used to generate new synthetic samples based on existing data to increase the classification performance. In this work, we propose a new data augmentation scheme using data imputation and matrix completion methods for segment-based classification. The proposal has been validated using two high-resolution multispectral datasets from the literature. The results obtained show that the proposed approach successfully increases the classification performance across all the scenes tested and that data imputation methods applied to multispectral imagery are a valid means to perform data augmentation. A comparison of classification accuracy between different imputation methods applied to the proposed scheme was also carried out.

scholarly journals Open Source Algorithm for Detecting Sea Ice Surface Features in High Resolution Optical Imagery

2017 ◽  
Author(s):  
Nicholas C. Wright ◽  
Christopher M. Polashenski
Keyword(s):  
Sea Ice ◽  
Open Source ◽  
Surface Coverage ◽  
Open Water ◽  
Training Data ◽  
The Arctic ◽  
Source Distribution ◽  
Observation Area ◽  
Melt Ponds ◽  
Optical Imagery

Abstract. Snow, ice, and melt ponds cover the surface of the Arctic Ocean in fractions that change throughout the seasons. These surfaces control albedo and exert tremendous influence over the energy balance in the Arctic. Increasingly available m- to dm-scale resolution optical imagery captures the evolution of the ice and ocean surface state visually, but methods for quantifying coverage of key surface types from raw imagery are not yet well established. Here we present an open source system designed to provide a standardized, automated, and reproducible technique for processing optical imagery of sea ice. The method classifies surface coverage into three main categories: Snow and bare ice, melt ponds and submerged ice, and open water. The method is demonstrated on imagery from four sensor platforms and on imagery spanning from spring thaw to fall freeze-up. Tests show the classification accuracy of this method typically exceeds 96 %. To facilitate scientific use, we evaluate the minimum observation area required for reporting a representative sample of surface coverage. We provide an open source distribution of this algorithm and associated training data sets and suggest the community consider this a step towards standardizing optical sea ice imagery processing. We hope to encourage future collaborative efforts to improve the code base and to analyze large datasets of optical sea ice imagery.

Sign in / Sign up

Export Citation Format

Share Document