Automatic generation of image analysis programs
In this paper, we introduce a system that generates computer vision programs for a given task, which is specified by 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. We present an early proof-of-concept implementation that relies on a limited database 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 problem descriptions, which require more sophisticated planning strategies in order to compensate for rapidly increasing search spaces.
Keywordsautomatic programming inductive programming generate-and-search machine learning computer vision image analysis object detection
Unable to display preview. Download preview PDF.
- 2.N. Crossley, E. Kitzelmann, M. Hofmann, and U. Schmid, “Combining analytical and evolutionary inductive programming,” in Proc. 2nd Conf. on Artificial General Intelligence, AGI 2009 (Atlantis Press, Amsterdam-Paris, 2009), pp. 19–24.Google Scholar
- 4.T. D’Orazio, M. Leo, N. Mosca, P. Spagnolo, and P. L. Mazzeo, “A semiautomatic system for ground truth generation of soccer video sequences,” in Proc. 6th IEEE Int. Conf. on Advanced Video and Signal Based Surveillance, AVSS’ 09 (IEEE Computer Soc., Los Alamitos, 2009), pp. 559–564.Google Scholar
- 6.MVTec Software GmbH. HALCON 11 (Munich, 2012). http://www.halcon.com (Accessed Feb. 27, 2014).
- 7.M. Hoffmann, E. Kitzelmann, and U. Schmid, “A unifiying framework for analysis and evaluation of inductive programming systems,” in Proc. 2nd Conf. on Artificial General Intelligence, AGI 2009 (Atlantis Press, Amsterdam-Paris, 2009), pp. 55–60.Google Scholar
- 9.C.-W. Hsu, C.-C. Chang, and C.-J. Lin, “A practical guide to support vector classification,” Tech. Report (Department of Computer Science, National Taiwan Univ., July 2003). http://www.csie.ntu.edu.tw/cjlin/papers/guide/guide.pdf (Accessed Feb. 27, 2014).Google Scholar
- 14.J. Möhrmann, G. Heidemann, O. Siemoneit, C. Hubig, U.-P. Kaeppeler, and P. Levi. “Context generation with image based sensors: an interdisciplinary enquiry on technical and social issues and their implications for system design,” Proc. World Acad. Sci., Eng. Technol. 74, 1191–1197 (2010).Google Scholar
- 22.The MathWorks, Inc. MATLAB R2013b (Natick, 2013). http://www.mathworks.de/products/matlab (Accessed Feb. 27, 2014).
- 23.The MathWorks, Inc. Simulink R2013b (Natick, 2013). http://www.mathworks.de/products/simulink/ (Accessed Feb. 27, 2014).
- 25.J. Winn and M. Everingham, The PASCAL visual object classes challenge 2007 (VOC2007) annotation guidelines (2007). http://pascallin.ecs.soton.ac.uk/challenges/VOC/voc2007/guidelines.html (Accessed Feb. 27, 2014).Google Scholar