|
With the rapid development of maritime transportation, marine environmental pollution has become more and more serious. In particular, oil leakage from ships is regarded as a major threat to marine environmental pollution. Synthetic Aperture Radar (SAR) imagery has become an important technology for marine environment monitoring because of its high resolution, wide coverage, and less influence by light and weather conditions. However, SAR images cannot provide realtime information about ships. The Automatic Identification System (AIS) can provide dynamic information about ships, such as real-time position, heading, speed, etc., helping to identify ships in the sea area. This study combined SAR imagery and AIS data to detect oil spills at sea and identify suspicious oil-discharging vessels. First, an improved U-Net model was adopted to detect oil spills and ships in SAR imagery. To achieve high detection performance, the U-Net was modified by using a lightweight MobileNetv3 backbone architecture, convolutional block attention module (CBAM), atrous spatial pyramid pooling (ASPP), and full-scale feature aggregation. Experimental results showed that the proposed U-Net model improved the detection accuracy of oil spills and reduced the misclassification between oil spills and look-alikes. Then, the AIS data corresponding to the SAR image was collected and the trajectories of ships passing near the SAR acquisition time can be screened out. The study compared AIS data with SAR detection results to look for the ship that was closest to the oil spill and whose navigation trajectory was almost parallel to the direction of the oil spill extension. Thus, it can be inferred that the ship was suspected of discharging oil pollution. Through experiments on oil pollution incidents, the effectiveness of combining SAR and AIS in tracking oil-discharging ships was verified.
|
