In this project, we develop a system that generates computer vision programs for a given task, which is specified in an intuitive manner (e.g. by defining regions of interest in a collection of example images). The system relies on a database of operators, which are combined by an automated planning approach in order to create executable programs. Our early proof–of–concept implementation that relies on a limited database to in order to solve simple tasks, such as finding players in a soccer video or cups on a table. Our experimental evaluation shows that the basic approach is working on relative simple scenarios. Future work will focus on integrating more complex prob lem descriptions, which require more sophisticated planning strategies in order to compensate for rapidly increasing search spaces.

Export as PDF, XML, TEX or BIB

Journal Articles
2014
[]		Automatic Generation of Image Analysis Programs (M Herrmann, C Mayer and B Radig), In Pattern Recognition and Image Analysis, Pleiades Publishing, volume 24, 2014.  [bibtex] [pdf] [doi] [pdf]
Conference and Workshop Papers
2013
[]		Automatic Generation of Image Analysis Programs (M Herrmann, C Mayer and B Radig), In 11th International Conference on Pattern Recognition and Image Analysis (PRIA-11-2013), The Russian Academy of Sciences, volume 1, 2013.  [bibtex]