Automation in the logistic process of vessel transport could be improved using satellite and drone imagery. As an example, finding the location of a point of interest on the surface of the water, such as a human, a buoy, a small ship without AIS or a cetacean, could be used for collision avoidance and search-and-rescue applications. The location could then be used for path planning and logistics. There are a wide variety of objects that can be found on the surface of water. However, there are no studies on the location and differentiation of these objects. This study suggests integrating six datasets from different sources, such as drone and satellite imagery, to validate the concept of mixing different data sources while maintaining adequate detection performance for different objects at the surface of water. Four models (YOLOv8s, YOLOv8m, YOLOv10m and Faster R-CNN:R50-FPN in the Detectron2 framework) were used to validate the feasibility of detecting four different objects (cetacean, small boat, buoy, human, and water (background)) under different conditions. This project will be integrated into an overall system that improves maritime safety and operations.