Abstract
Computer vision is an ever more important means for the navigation of UAVs. Here we propose a landmark recognition system looking for salient man-made infrastructure. An object-oriented structural system is preferred since it can utilize known properties of these objects such as part-of hierarchies, mutual geometric constraints of parts, generalization etc. The structure, available for use as landmark, will vary strongly with the region the UAV is supposed to navigate in. The structural knowledge can lose its meaning in two ways: 1) If the area contains a lot of non-intended structure fulfilling the demands modeled the system will start hallucinating lots of landmarks anywhere. 2) If the landmarks in the area do not fulfill the demands modeled they will not be detected. Up to a certain degree these semantics—or lack of meaning—can be investigated mathematically using probabilistic models. But the results from this are very optimistic. In reality the meaning breaks down much earlier. This contribution reports on an example: Testing a system, designed for a central European country (Germany), for use elsewhere (e.g., Russia or Turkey).
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
O. Aboutalib, B. Awalt, A. Fung, B. Thai, J. Leibs, T. J. Klausutis, R. Wehling, and M. Iames, “All Source Adaptive Fusion for Aided Navigation in Non-GPS Environment,” in SPIE XVI, Ed. by Z. Rahman, S. E. Reichenbach, and M. A. Neifeld (2007), Vol. 6575, pp. 8–13.
F. Bonin, A. Ortiz, and G. Oliver, “Visual Navigation for Mobile Robots: A Survey,” J. Intell. Robotic Syst. 53(3), 263–296 (2008).
A. Desolneux, L. Moisan, and J. M. Morel, From Gestalt Theory to Image Analysis (Springer Verlag, Berlin, 2008).
B. Draper, R. Collins, J. Brolio, A. Hanson, and E. Riseman, “The Schema System,” Int. J. Comput. Vision 2(3), 209–250 (1989).
C.-E. Guo, S. C. Zhu, and Y. N. Wu, “Modeling Visual Patterns by Integrating Descriptive and Generative Methods,” Int. J. Comput. Vision 53(1), 5–29 (2003).
Z. He, R. V. Iyer, and P. Chandler, “Vision-Based UAV Flight Control and Obstacle Avoidance,” in Proc. IEEE Am. Control Conf. (Minneapolis, June 2006), pp. 2166–2170.
K. Lütjen, “Ein Blackboard-basiertes Produktionssystem für die automatische Bildauswertung,” in Mustererkennung, Ed. by G. Hartmann (Springer, Berlin, 1986), pp. 164–168.
K. Marroitt and B. Meyer, Visual Language Theory (Springer Verlag, Berlin, 1998).
T. Matsuyama and V. S.-S. Hwang, Sigma a Knowledge-Based Image Understanding System (Plenum Press, New York, 1990).
E. Michaelsen, “Über Koordinaten Grammatiken zur Bildverarbeitung und Szenenanalyse,” Dissertation (Technische Fakultät, Friedrich-Alexander-Universität, Erlangen-Nürnberg, 1998), Available from: http://www.exemichaelsen.de/Michaelsen-Diss.pdf.
E. Michaelsen, L. Doktorski, and M. Arens, “Shortcuts in Production Systems—A Way to Include Clustering in Structural Pattern Recognition,” in Proc. PRIA-9-2008 (Lobachevsky State University, Nizhni Novgorod, 2008), vol. 2, pp. 30–38.
E. Michaelsen, M. Arens, and L. Doktorski, “Interaction of Control and Knowledge in a Structural Recognition System,” in Proc. 32nd German Conf. on Artificial Intelligence (KI-2009), Ed. by B. Mertsching, M. Hund, and M. Z. Aziz (Springer, Berlin, 2009), pp. 73–90.
E. Michaelsen, U. Stilla, U. Soergel, and L. Doktorski, “Extraction of Building Polygons from SAR Images: Grouping and Decision-Level in the GESTALT System,” Pattern Recogn. Lett. 31(10), 1071–1076 (2010).
E. Michaelsen and K. Jaeger, “A GOOGLE-Earth Based Test Bed for Structural Image-Based UAV Navigation,” in Proc. 12th Int. Conf. on Information Fusion (Seattle, July 6–9, 2009), pp. 340–346.
E. Michaelsen, L. Doktorski, and K. Lütjen, “An Accumulating Interpreter for Cognitive Vision Production Systems,” Pattern Recogn. Image Anal. 21(3), 410 (2011).
M. Nagao and T. Matsuyama, A Structural Analysis of Complex Aerial Photographs (Plenum Press, New York, 1980).
U. Stilla and E. Michaelsen, “Semantic Modeling of Man-Made Objects by Production Nets,” in Automatic Extraction of Man-Made Objects from Aerial and Space Images (II), Ed. by A. Gruen, E. P. Baltsavias, and O. Henricsson (Birkhaeuser, Basel, 1997), pp. 43–52.
S. J. Wallace, M. J. Hatcher, G. Priestnall, R. D. Morton, “Research into the Framework for Automatic Linear Feature Identification and Extraction,” in Automatic Extraction of Man-Made Objects from Aerial and Space Images (III), Ed. by E. P. Baltsavias, A. Gruen, and L. van Gool (Balkema, Lisse, 2001), pp. 381–390.
Author information
Authors and Affiliations
Corresponding author
Additional information
The article is published in the original.
Eckart Michaelsen, born in 1958 in Stade Germany, received diploma in Mathematics from the Leopold-Franzens University, Innsbruck, Austria in 1987 and Dr. eng. from the Friedrich-Alexander University, Erlangen-Nurnberg, Germany in 1998. He works as researcher in the IOSB-Fraunhofer in Ettlingen, Germany. He has published more than 70 papers in various international journals, conferences and workshops. Currently he is co-chair of the IAPR-TC7 (Pattern Recognition in Remote Sensing).
Klaus Jäger, born in 1956 in Lörrach Germany, received diploma in Physics from the University Fridericiana, Karlsruhe, Germany in 1986. He works as researcher in the Fraunhofer IOSB in Ettlingen, Germany. His main interests are sensor fusion and automatic object recognition for unmanned aerial vehicles. He has published more than 30 papers in various international conferences, workshops and journals.
Leo Doktorski. Born 1952. Received diploma in Mathematics from the Rostov-on-Don State University in 1974 and Dr. rer. nat. (Kandidat Nauk) degree also from the Rostov-on-Don State University in 1978. He works as researcher in the IOSB-Fraunhofer in Ettlingen, Germany. He has published more than 40 papers in various journals, conferences and workshops.
Dr. Michael Arens received his diploma in computer science and his Doctorate from the University of Karlsruhe (TH) in 2001 and 2004, respectivly. Since 2006 he is working at the Fraunhofer Institute of Optronics, System Technologies and Image Exploitation (IOSB). Presently, he is head of a research group concerned with Video-based Situation Recognition.
Dimitri Roschkowski, born 1984 in Kiev Ukraine, is currently student at the University of Karlsruhe (KIT). His main interests are IT and Physical Security and pattern recognition. He has published more than 15 articles about Industry Data Security.
Rights and permissions
About this article
Cite this article
Michaelsen, E., Jäger, K., Roschkowski, D. et al. On the semantics of object-oriented landmark recognition. Pattern Recognit. Image Anal. 22, 44–53 (2012). https://doi.org/10.1134/S1054661812010270
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1054661812010270