Application de l'algèbre à la géométrie

Bourdon, Pierre Louis Marie

Object recognition and scene classification from multispectral and multisensor pixels (Part 1)

Bibliographic data

Monograph

Persistent identifier:: 856473650

Author:: Baltsavias, Emmanuel P.

Title:: Fusion of sensor data, knowledge sources and algorithms for extraction and classification of topographic objects

Sub title:: Joint ISPRS/EARSeL Workshop ; 3 - 4 June 1999, Valladolid, Spain

Scope:: III, 209 Seiten

Year of publication:: 1999

Place of publication:: Coventry

Publisher of the original:: RICS Books

Identifier (digital):: 856473650

Illustration:: Illustrationen, Diagramme, Karten

Language:: English

Usage licence:: Attribution 4.0 International (CC BY 4.0)

Publisher of the digital copy:: Technische Informationsbibliothek Hannover

Place of publication of the digital copy:: Hannover

Year of publication of the original:: 2016

Document type:: Monograph

Collection:: Earth sciences

Chapter

Title:: TECHNICAL SESSION 7 APPLICATIONS IN FORESTRY

Document type:: Monograph

Structure type:: Chapter

Chapter

Title:: A LOCAL CORRELATION APPROACH FOR THE FUSION OF REMOTE SENSING DATA WITH DIFFERENT SPATIAL RESOLUTIONS IN FORESTRY APPLICATIONS. J. Hill, C. Diemer, O. Stöver, Th. Udelhoven

Document type:: Monograph

Structure type:: Chapter

Information of the distribution P: Ip = Ep |log: dl = S sex p(x)log2 55) Kullback-Leibler divergence: D(PI|Q) = Ep [log 25] =X, p(2)logs q(x) p(x) q(x) Table 5: Information and Kullback-Leibler divergence. the binary relation is D(P'||Q') — 9.97, and hence the rela- tive error or inefficiency of the distribution Q' of these pairs is 128% if P' is unknown. Finally, the distribution of the (partial) building models P", which is shown in the captions of Figures 4 and 5, is with 7p, = 1.2 much more com- pact than the previously considered distributions. But, the Kullback-Leibler divergence D(P"||Q") — 1.5 of P" and its corresponding uniform distributions Q" denotes an relative error or inefficiency of 2596. This comparably small error is due to the huge number of saddleback buildings in the test data. Notice the binary relations of the building atoms sup- port the learned building models, e.g. consider the number of adjacent tertiary node pairs (hv* h, hv* h), which occur in each building model several times. 5 CONCLUSIONS The graph-based generalization approach EXRES which learns a statistical distribution of previously unknown graph- based patterns has been depicted and shown by three appli- cations: learning of the binary relations of pairs of adjacent building atoms (tertiary nodes and faces), and (partial) three- dimensional building models. As result the generalized data are up to 182% more compact and informative compared with non-available a priori knowl- edge. The evaluation is based on the idea of preferring com- pact information and thus does not make any assumption about the underlying data. The generalized model knowl- edge represent the distribution of most relevant sub-patterns for three-dimensional building reconstruction from images. ACKNOWLEDGMENTS The inspiration by A. B. Cremers is gratefully acknowledged. The author expresses his thanks to E. Gülch and W. Forstner, Institute of Photogrammetry, Bonn, for their cooperation of building acquisition from aerial images and fruitful discus- sions. REFERENCES Baltsavias, E., W. Eckstein, E. Gülch, M. Hahn, D. Stall- mann, K. Tempfli, and R. Welch (Eds.) (1997). Pro- ceedings of the joint ISPRS commission lII/IV work- shop "3D Reconstruction and Modeling of Topo- graphic Objects" - Integration of multiple information sources and image understanding, Enschede, N.L. ITC. Blumer, A., A. Ehrenfeucht, D. Haussler, and M. War- muth (1987). Occam's Razor. Information Processing Letters 24, 371 — 380. Braun, C., T. Kolbe, F. Lang, W. Schickler, V. Steinhage, A. B. Cremers, W. Fórstner, and L. Plümer (1995). 324 Models for Photogrammetric Building Reconstruction. Computers & Graphics 19(1), 109 — 118. Bylander, T., D. Allemang, M. Tanner, and J. Josephson (1991). The Computational Complexity of Abduction. Artificial Intelligence 49, 25 — 60. Englert, R. (1995). Inducing Integrity Constraints from Knowledge Bases. In |. Wachsmuth, C.-R. Rollinger, and W. Brauer (Eds.), Proceedings of the 19th Annual German Conference on Artificial Intelligence, Volume 981 of Lecture Notes in Artificial Intelligence, Berlin, Germany, pp. 77 — 88. Springer. Englert, R. (1997). Handling Irregularities of 3D Build- ing Data During Surface Computation. In N. Thal- mann and V. Skála (Eds.), Proceedings of the Fifth International Conference in Central Europe on Com- puter Graphics and Visualization, Volume l, University of West Bohemia Press, Plzen, CR, pp. 104 - 113. Englert, R., A. B. Cremers, and J. Seelmann-Eggebert (1998). Recognition of Polymorphic Patterns in Pa- rameterized Graphs for 3D Building Reconstruction. International Journal COMPUTING — Archives for In- formatics and Numerical Computation [Suppl.] (12). to appear Summer 1998. Englert, R. and E. Gülch (1996). A One-Eye Stereo System for the Acquisition of Complex 3D-Building Structures. GEO-INFORMATION-SYSTEMS, Journal for Spatial Information and Decision Making 9(4), 16 — 21. Fischer, A., T. Kolbe, and F. Lang (1997). Integration of 2D and 3D Reasoning for Building Reconstruction Using a Generic Hierarchical Model. In W. Forstner and L. Plümer (Eds.), Semantic Modeling for the Ac- quisition of Topographic Information from Images and Maps, Proceedings of SMATI'97, Basel, Switzerland, pp. 159 — 180. Birkhäuser. Grün, A., O. Kübler, and P. Agouris (Eds.) (1995). Au- tomatic Extraction of Man-Made Objects from Aerial and Space Images, Basel, Switzerland. Birkhäuser. Jónsson, B. (1972). Topics in Universal Algebra. Lecture Notes in Mathematics. Berlin, Germany: Springer- Verlag. Lang, F. and W. Fôrstner (1996). Surface Reconstruction of Man-Made Objects Using Polymorphic Mid-Level Features and Generic Scene Knowledge. ZPF 6, 193 — 201. McEliece, R. (1977). The Theory of Information and Cod- ing. Encyclopedia of Mathematics and its Applications. Massachusetts, U.S.A.: Addison-Wesley. Merziger, G. (1992). Approaches to Abductive Reasoning — An Overview —. Technical Report Report DFKI-RR- 92-08, DFKI, Saarbrücken, Germany. Peng, Y. and J. Reggia (1990). Abductive Inference Mod- els for Diagnostic Problem-Solving. Symbolic Compu- tation. N.Y., U.S.A.: Springer-Verlag. Rissanen, J. (1983). A Universal Prior for Integers and Estimation by Minimum Description Length. Ann. Stat. 11, 416 - 431. Schenk, T. (1995). A Layered Abduction Model of Building Recognition. In A. Grün, O. Kübler, and P. Agouris (Eds.), Automatic Extraction of Man-Made Objects from Aerial and Space Images, Basel, Switzerland, pp. 117 — 123. Birkhäuser.

Access restriction

Copyright

Metadata: Object recognition and scene classification from multispectral and multisensor pixels (Part 1)

Monograph

Chapter

Chapter

Table of contents

Cite and reuse

Volume

Chapter

Image

Image fragment

Citation links

Citation recommendation