Washington Business Office, Riverside Research Institute, Arlington, VA 22202, USA.
Sensors (Basel). 2023 Feb 22;23(5):2424. doi: 10.3390/s23052424.
As commercial geospatial intelligence data becomes more widely available, algorithms using artificial intelligence need to be created to analyze it. Maritime traffic is annually increasing in volume, and with it the number of anomalous events that might be of interest to law enforcement agencies, governments, and militaries. This work proposes a data fusion pipeline that uses a mixture of artificial intelligence and traditional algorithms to identify ships at sea and classify their behavior. A fusion process of visual spectrum satellite imagery and automatic identification system (AIS) data was used to identify ships. Further, this fused data was further integrated with additional information about the ship's environment to help classify each ship's behavior to a meaningful degree. This type of contextual information included things such as exclusive economic zone boundaries, locations of pipelines and undersea cables, and the local weather. Behaviors such as illegal fishing, trans-shipment, and spoofing are identified by the framework using freely or cheaply accessible data from places such as Google Earth, the United States Coast Guard, etc. The pipeline is the first of its kind to go beyond the typical ship identification process to help aid analysts in identifying tangible behaviors and reducing the human workload.
随着商业地理空间情报数据的广泛普及，需要创建使用人工智能的算法来对其进行分析。海上交通量每年都在增加，执法机构、政府和军队可能会对异常事件的数量感兴趣。本工作提出了一种数据融合管道，该管道使用人工智能和传统算法的混合来识别海上船舶并对其行为进行分类。使用可视光谱卫星图像和自动识别系统 (AIS) 数据的融合过程来识别船舶。此外，还将融合后的数据与有关船舶环境的其他信息进一步集成，以在一定程度上帮助对每艘船舶的行为进行分类。这种上下文信息包括专属经济区边界、管道和海底电缆的位置以及当地天气等内容。该框架使用 Google Earth、美国海岸警卫队等地方的免费或廉价获取的数据来识别非法捕鱼、转运和欺骗等行为。该管道是同类产品中的首创，超越了典型的船舶识别流程，有助于帮助分析人员识别有形行为并减少人工工作量。
