Satellite detection of moving objects in a maritime environment

Description

There is a growing need for coverage detection of large maritime areas, mainly in the exclusive economic zone (EEZ). Since physically accessing such a large area is practically impossible, satellite-based sensors offer an efficient and cost-effective solution. However, detection of moving vessels with satellite sensors is a challenging problem. Satellite imagery is expensive, covers a very small area, and can be acquired only at predefined acquisition opportunities.

All civilian ships are required to transmit an Automatic Identification System (AIS) signal, which indicates the vessel’s position and identification parameters. However, since this information is unreliable, total maritime awareness is achieved through the integration and analysis of visual data from electro-optic (EO) and SAR satellites, enabling visual identification of vessels instead of relying only on cooperative vessel AIS transmission. The time it takes from vessel transmission of an AIS signal until it can be analyzed in ground segment (known as a data cycle) is typically over one hour. On the other hand, current commercial satellite mission planning may take several hours. Therefore, in order to task a satellite to detect a moving vessel with no additional aids after three hours, you must cover a very large area (about 17,000 sq km). This will end up costing US$150,000–$200,000 per ship, which is not affordable. At the same time, manually choosing relevant satellite imagery is equivalent to looking for a needle in a haystack: one satellite image is commonly of size 50–100 sq km (i.e., less than 1% of the total area’s size).

Natalie Fridman dives into this challenging problem and shares ISI’s AI-based solution along with successful examples of detecting maritime vessels with ISI’s satellites. Natalie focuses on efficient ways to decrease the search area for the vessel by using vessel behavior prediction to increase the probability of acquiring relevant information from the satellite imagery. Reduction of position uncertainty leads to a much more economical solution. Using a multiagent system, ISI developed a prediction algorithm for the vessel behavior and selection algorithm, which recommends the best satellite and observation window for a given mission. Deep learning enables the system to autonomously detect vessels in existing satellite imagery, and by correlating this detection with various other sensors, it can detect uncooperative vessels as well.