A Shape Constraints Based Method to Recognize Ship Objects from High Spatial Resolution Remote Sensed Imagery

摘要: Automatically extracting moored ships from high spatial resolution remote sensed imagery is more difficult than offshore because their spectrum values and textures are very close to the harbor. For this reason, different routes designed applied extract two kinds of ships. Our whole method can be divided into three main steps: 1) water polygons with histogram segmentation, 2) holes in morphological operations as possible ships, ship identification salients sea along boundary, then 3) screen real out these shape constraints. A case study carried on Spot 5 validate our method.