Abstract
It is of considerable benefit to combine information obtained from different satellite sensors to achieve advanced and improved characterization of sea ice conditions. However, it is also true that not all the information is relevant. It may be redundant, corrupted, or unnecessary for the given task, hence decreasing the performance of the algorithms. Therefore, it is crucial to select an optimal set of image attributes which provides the relevant information content to enhance the efficiency and accuracy of the image interpretation and retrieval of geophysical parameters. Comprehensive studies have been focused on the analysis of relevant features for sea ice analysis obtained from different sensors, especially synthetic aperture radar. However, the outcomes of these studies are mostly data and application-dependent and can, therefore, rarely be generalized. In this article, we employ a feature selection method based on graph Laplacians, which is fully automatic and easy to implement. The proposed approach assesses relevant information on a global and local level using two metrics and selects relevant features for different regions of an image according to their physical characteristics and observation conditions. In the recent study, we investigate the effectiveness of this approach for sea ice classification, using different multi-sensor data combinations. Experiments show the advantage of applying multi-sensor data sets and demonstrate that the attributes selected by our method result in high classification accuracies. We demonstrate that our approach automatically considers varying technical, sensor-specific, environmental, and sea ice conditions by employing flexible and adaptive feature selection method as a pre-processing step.
Highlights
In the last decades, sea ice research has become a focus of Earth observation, especially in the Arctic region where sea ice extent and volume are declining rapidly [1]
The most predominantly selected attribute for Radarsat-2/Landsat-8 was the maximum correlation coefficient derived from HV polarization (HV Maximum Correlation Coefficient (MCC)), that was chosen for Open Water, Nilas, Young Ice, and Thick first-year ice (FYI)
Our results show the ability of GKMI to process different combinations of data sets and the importance
Summary
Navigation in the polar seas, the knowledge about its type, concentration, thickness, deformation, and extent is extremely important for various activities such as marine transportation and offshore operations, and for stakeholders from the oil and gas industry, fisheries, and tourism, among others. In the case of remote sensing data, especially when dealing with complex scenes or considering modalities (i.e. various sensors characterized by different acquisition techniques) that are difficult to interpret such as sea ice SAR images, providing accurate labels is challenging even with the assistance of an expert. We use a recently developed graph-based method (referred to as GKMI) [22], that relies on information theory metrics to capture the most relevant attributes for different sea ice classes. It increases their separability (even if they are non-linearly separable) while preserving their physical interpretability It selects relevant attributes for separate zones of an image that might belong to different ice classes and/or are measured under different conditions (e.g., different radar incidence angles, varying sun elevation angles).
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.