Towards Automation of Satellite-Based Radar Imagery for Iceberg Surveillance - Machine Learning of Ship and Iceberg Discrimination

Abstract Drifting icebergs can threaten navigation and marine operations and are prevalent in a number of regions that have active oil and gas exploration and development. Satellite synthetic aperture radar (SAR) is naturally applicable to map and monitor icebergs and sea ice due its ability to capture images day or night, as well as through cloud, fog and various wind conditions. There are several notable examples of its use to support operations, including Grand Banks, Barents Sea, offshore Greenland and Kara Sea. New constellations of satellites and the increasing volume of satellite data becoming available present a new paradigm for ice surveillance, in terms of persistence, reliability and cost. To fully extract the value of the data from these constellations, automation and cloud-based processing must be implemented. This will allow more timely and efficient processing, lowering monitoring costs by at least an order of magnitude. The increase in data persistence and processing capability allows large regions to be monitored daily for ice incursions, thus increasing safety and efficiency during offshore operations in those regions. The process of automating SAR-based iceberg surveillance involves creating a process flow that is robust and requires limited human intervention. The process flow involves land-masking, target detection, target discrimination and product dissemination. Land masking involves the removal of high-clutter land from the imagery to eliminate false detection from these locations. Target detection usually involves an adaptive threshold to separate true targets from the background ocean clutter. A constant false alarm rate (CFAR) is a standard technique used in radar image processing for this purpose. Target discrimination involves an examination of the distinct features of a target to determine if they match the features of icebergs, vessels or other ‘false alarms’ (e.g., marine wildlife, clutter). The final stage is the production of an output surveillance product, which can be a standard iceberg chart (e.g., MANICE) or something that can be ingested into a GIS system (e.g., ESRI shapefile, Google KML). The target discrimination phase is one of the most important phases because it provides feedback to operations about the presence of targets of interest (icebergs and vessels). The authors have used computer vision techniques successfully to train target classifiers. Standard techniques usually result in classifier accuracies of between 85%-95%, depending on the resolution of the SAR (higher resolutions produce more accurate results) and the availability of multiple polarizations. To see if new machine learning techniques could be applied to increase classifier accuracy, a dataset of 5000 ship and iceberg targets were extracted from Sentinel-1 multi-channel data (HH,HV). The images were collected in several regions (Greenland, Grand Banks, and Strait of Gibraltar). Validation either came by way of supporting information from the offshore operations, or was inferred by location. An online machine learning competition was hosted by Kaggle, a company that conducts online competitions on behalf of their clients. The detection data were made available by Kaggle to the broad internet community. Kaggle has a loyal following of data scientists who regularly participate in Kaggle competitions. The competition was hosted over a three-month period; over 3300 teams participated in the competition. The competition produced an improved classifier over standard computer vision techniques; the top three competitors had 4-5 stage classifiers that increased classification accuracy by approximately 5%.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.