Title :
GRAVA-a corpus based approach to the interpretation of aerial images
Author_Institution :
Oxford Univ., UK
Abstract :
Aerial imagery is an important component of military intelligence. However our ability to gather good quality aerial images from satellite and aircraft has far outstripped our ability to manually interpret them. The problem of interpreting aerial images is a multifaceted one. This paper provides an overview of key parts of a system that can robustly segment, label, and parse useful structure in the images in a way that mimics expert photo interpreters
Keywords :
image segmentation; GRAVA; aerial images interpretation; aircraft; corpus based approach; expert photo interpreters; image labelling; image segmentation; military intelligence; minimum description length; patchwork parsing; reflective agent architecture; satellite;
Conference_Titel :
Image Processing and Its Applications, 1999. Seventh International Conference on (Conf. Publ. No. 465)
Conference_Location :
Manchester
Print_ISBN :
0-85296-717-9
DOI :
10.1049/cp:19990378
