AIS-Based Evaluation of Target Detectors and SAR Sensors Characteristics for Maritime Surveillance

Ramona Pelich, Nicolas Longépé, Grégoire Mercier, Guillaume Hajduch, René Garello

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · 2014 · 111 citations · 12 references

Concepts

TL;DR

The paper investigates the performance of ship detectors that use adaptive threshold algorithms. The authors evaluate these detectors with a systematic methodology that compares detection rates and false alarms across large medium‑resolution SAR datasets (Radarsat‑2, CosmoSkymed ScanSAR) and AIS ground truth, while assessing the impact of SAR sensor characteristics such as incidence angle, polarization, frequency, spatial resolution, and vessel length. The study finds that the performance of adaptive‑threshold ship detectors varies with dataset characteristics, yielding distinct advantages and disadvantages across different SAR datasets.

Abstract

This paper studies the performances of different ship detectors based on adaptive threshold algorithms. The detection algorithms are based on various clutter distributions and assessed automatically with a systematic methodology. Evaluation using large datasets of medium resolution SAR images and AIS (automatic identification system) data as ground truths allows to evaluate the efficiency of each detector. Depending on the datasets used for testing, the detection algorithms offer different advantages and disadvantages. The systematic method used in discriminating real detected targets and false alarms in order to determine the detection rate, allows us to perform an appropriate and consistent comparison of the detectors. The impact of SAR sensors characteristics (incidence angle, polarization, frequency and spatial resolution) is fully assessed, the vessels' length being also considered. Experiments are conducted on Radarsat-2 and CosmoSkymed ScanSAR datasets and AIS data acquired by coastal stations.

References

12