For ocean remote sensing, target positioning over large areas of sea surface can be challenging, and traditional methods that rely on control points data may not be applicable in such cases. AIS data are commonly used as auxiliary data source of ocean remote sensing, which contains a wealth of attribute information of target. High-precision position information for a large number of targets is provided by the AIS equipped with differential GPS. AIS can be used as dynamic control points on the sea surface to contribute to target positioning in remote sensing image, meeting the on-orbit real-time positioning requirements of ocean remote sensing. This paper proposes a method for on-orbit target positioning and identification through the data fusion of optical image and AIS data. Firstly, the target position information provided by AIS is the broadcasted position over a period of time, while remote sensing image provide the instantaneous captured position. Therefore, it is necessary to calibrate the two types of data in terms of time and space. Then, the grid matching algorithm is used to establish the corresponding relationships between the same targets from the two different datasets, thereby achieving data fusion. Finally, target positioning is achieved over large areas of sea surface. In addition, the identification of target can also be facilitated by remote sensing image with the aid of AIS data, enabling precise positioning of abnormal target while obtaining their image information. In this paper, 5-meter resolution Jilin-1 satellite image and AIS data are used as data sources. The results show that, compared with the original data, the positioning error values calculated by this method are between 5-20 meters, with a reduction of over 70% in the RMSE value.
|