Image Parsing: Unifying Segmentation, Detection, and Recognition
International Journal of Computer Vision
A Knowledge Based Classification for Urban Mapping Using High Resolution Remote Sensing Data
DICTA '07 Proceedings of the 9th Biennial Conference of the Australian Pattern Recognition Society on Digital Image Computing Techniques and Applications
Hi-index | 0.00 |
Target recognition based on knowledge is a hot topic in remote sensing field. However, due to the deficiency of knowledge organization and usage, existing algorithms have a great limitation in applicability and extensibility. Therefore, a framework of target recognition based on knowledge is proposed in the paper. Building on the decomposition and semantic description of the identification algorithm, the framework fulfills the work of mission planning and algorithm invoking in the way of symbol reasoning. Besides it provides the universal way of knowledge representation and knowledge application by means of building the correlation between target and algorithm. The experimental results demonstrate the validity of the proposed framework.