Overview on Image Sequence Analysis

  • Hans-Hellmut Nagel
Part of the NATO ASI Series book series (volume 2)

Abstract

Attempts to concisely describe dynamic phenomena recorded by image sequences tend to model the depicted scene as a configuration of objects which exhibit well defined (sequences of) state transitions. Current research in image sequence analysis is concerned with the design of computer-internal representations for objects and associated dynamic phenomena.

One goal is the ability to automatically extract an adequate description for a specific image sequence by generally applicable concepts, representational tools, and procedures. A framework is suggested which decomposes this task for motion-related phenomena into subproblems. The recent literature is presented within this framework to emphasize the common aspects of and the relations between various published approaches.

Keywords

Brittle Convolution Cross Correlation Remote Sensing Editing 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Abe et al. 81
    A Plot Understanding System on Reference to Both Image and Language N. Abe, I. Soga, and S. Tsuji, IJCAI-81, pp. 77–84Google Scholar
  2. Aggarwal and Badler 80.
    Special Issue on Motion and Time-Varying Imagery (November 1980) J.K. Aggarwal and N.I. Badler (eds.) IEEE Trans. Pat. Anal. Machine Intel. PAMI-2, No. 6Google Scholar
  3. Aggarwal et al. 81a
    Correspondence Processes in Dynamic Scene Analysis J.K. Aggarwal, L.S. Davis, and W.N. Martin Proc. IEEE 69 (1981) 562–572CrossRefGoogle Scholar
  4. Aggarwal et al. 81b
    Survey: Representation Methods for Three-Dimensional Objects J.K. Aggarwal, L.S. Davis, W.N. Martin, and J.W. Roach in L.N. Kanal and A. Rosenfeld (eds.) Progress in Pattern Recognition vol. 1, pp. 377–391 North-Holland Publ. Co., Amsterdam New York Oxford 1981Google Scholar
  5. Agin 81.
    Hierarchical Representation of Three-Dimensional Objects Using Verbal Models G.J. Agin IEEE Trans. Pat. Anal. Machine Intel. PAMI-3 (1981) 197–204CrossRefGoogle Scholar
  6. Asada et al. 80
    Three Dimensional Motion Interpretation for the Sequence of Line Drawings M. Asada, M. Yachida, and S. Tsuji, ICPR-80, pp. 1266–1273Google Scholar
  7. Asada et al. 82
    Understanding of Three-Dimensional Motions in Blocks World M. Asada, M. Yachida, and S. Tsuji IEEE Trans. Pat. Anal. Machine Intel. PAMI-4 (1982) (to appear)Google Scholar
  8. Badler 75.
    Temporal Scene Analysis: Conceptual Descriptions of Object Movements N.I. Badler, Technical Report No. 80, February 1975 Dept. Computer Science, University of TorontoGoogle Scholar
  9. Barnard and Thompson 80.
    Disparity Analysis of Images S.T. Barnard and W.B. Thompson IEEE Trans. Pat. Anal. Machine Intel. PAMI-2 (1980) 333–340CrossRefGoogle Scholar
  10. Baumgart 74.
    Geometric Modeling for Computer Vision B.G. Baumgart, STAN-CS-74-463 (October 1974) Computer Science Dept., Stanford University, Stanford/CAGoogle Scholar
  11. Baumgart 75.
    A Polyhedron’ Representation for Computer Vision B.L.Baumgart, Proc. NCC, AFIPS 44 (1975) 589–596CrossRefGoogle Scholar
  12. Bergmann 82.
    Displacement Estimation Based on the Correlation of Image Segments H.C. Bergmann, Proc. IEE International Conference on Electronic Image Processing, University of York/UK, July 26–28, 1982 see also this volumeGoogle Scholar
  13. Bers et al. 80
    Object Detection in Image Sequences K.H. Bers, M. Bohner, and H. Gerlach, ICPR-80, pp. 1317–1319Google Scholar
  14. Birk and Kelley 81.
    An Overview of the Basic Research Needed to Advance the State of Knowledge in Robotics J.R. Birk and R.B. Kelley IEEE Trans. Systems, Man, and Cybernetics SMC-11 (1981) 574–579Google Scholar
  15. Bonde and Nagel 79.
    Oeriving a 3-D Description of a Moving Rigid Object from Monocular TV-Frame Sequences T. Bonde and H.-H. Nagel, WCATVI-79, pp. 44–45Google Scholar
  16. Bouthemy and Benveniste 82.
    Atmospheric Disturbances Tracking in Satellite Images P. Bouthemy and A. Benveniste, preprint (July 1982) IRISA, Campus de Beaulieu, 35042 Rennes Cedex, FranceGoogle Scholar
  17. Boxberger et al. 81
    Einsatz der Nahbereichsphotogrammetrie in der Tierbeobachtung J. Boxberger, T. Jungbluth, M. Stephani, H. Auernhammer, und A. Zips Schriftenreihe der Landtechnik Weihenstephan Institut fuer Landtechnik, Bayer. Landesanstalt fuer Landtechnik Freising-Weihenstephan 1981Google Scholar
  18. Bruss and Horn 81.
    Passive Navigation A.R. Bruss and B.K.P. Horn AI-Memo 645 (August 1981), MIT, Cambridge/MAGoogle Scholar
  19. Cafforio 82.
    Remarks on the Differential Method for the Estimation of Movement in Television Images C. Cafforio, Signal Processing 4 (1982) 45–52CrossRefGoogle Scholar
  20. Cafforio and Rocca 76.
    Methods for Measuring Small Displacements of Television Images C. Cafforio and F. Rocca IEEE Trans. Information Theory IT-22 (1976) 573–579CrossRefGoogle Scholar
  21. Cafforio and Rocca 79.
    Tracking Moving Objects in Television Images C. Cafforio and F. Rocca, Signal Processing 1 (1979) 133–140CrossRefGoogle Scholar
  22. Cheng and Huang 81.
    Image Recognition by Matching Relational Structures J.K. Cheng and T.S. Huang, IEEE PRIP-81, pp. 542–547Google Scholar
  23. Clarkson 81.
    A Procedure for Camera Calibration with Image Sequences K.L. Clarkson Proc. Image Understanding Workshop, L.S. Baumann (ed.), April 1981, pp. 175–177, Science Applications, Inc., Arlington/VAGoogle Scholar
  24. Clocksin 80.
    Perception of Surface Slant and Edge Labels from Optical Flow: A Computational Approach W.F. Clocksin, Perception 9 (1980) 253–269CrossRefGoogle Scholar
  25. Darmon 82.
    A Recursive Method to Apply the Hough Transform to a Set of Moving Objects, C.A. Darmon Proc. Int. Conf. Acoustics, Speech, and Signal Processing Paris, May 3–5, 1982, pp. 825–829Google Scholar
  26. Davis and Yam 80.
    A Generalized Hough-like Transformation for Shape Recognition L.S. Davis and S. Yam TR-134 (February 1980), Department of Computer Science University of Texas at Austin, Austin/TXGoogle Scholar
  27. Dinse et al. 81
    Untersuchung von Verschiebungsvektorfeldern in Bildfolgen T.Dinse, W. Enkelmann, und H.-H. Nagel in B. Radig (Hrsgb.) Modelle und Strukturen 4. DAGM Symposium Hamburg 6.-8. Oktober 1981 Informatik-Fachberichte 49 pp. 69–75 Springer Verlag Berlin-Heidelberg-New York 1981Google Scholar
  28. Donkoh 80.
    Computer Analysis Helps Train Athletes S.Donkoh, CIPS Review (July/August 1980) 14–15Google Scholar
  29. Dreschler 81.
    Ermittlung markanter Punkte auf den Bildern bewegter Objekte und Berechnung einer 3D-Beschreibung auf dieser Grundlage L. Dreschler, Dissertation (Juni 1981) Fachbereich Informatik der Universitaet HamburgGoogle Scholar
  30. Dreschler and Nagel 78.
    Using “Affinity” for Extracting Images of Moving Objects from TV-Frame Sequences, L. Dreschler and H.-H. Nagel IfI-HH-B-44/78 (February 1978) Fachbereich Informatik, Universitaet HamburgGoogle Scholar
  31. Dreschler and Nagel 81.
    Volumetric Model and 3D-Trajectory of a Moving Car Derived from Monocular TV-Frame Sequences of a Street Scene L. Dreschler and H.-H. Nagel, IJCAI-81, pp. 692–697 see also Computer Graphics and Image Processing Fall 1982 (in press)Google Scholar
  32. Dreschler and Nagel 82.
    On the Selection of Critical Points and Local Curvature Extrema of Region Boundaries for Interframe Matching I. Dreschler and H.-H. Nagel ICPR-82 (in press); see also this volume.Google Scholar
  33. Duda and Hart 73.
    Pattern Classification and Scene Analysis R.O. Duda and P.E. Hart, John Wiley _Sons, New York, 1973MATHGoogle Scholar
  34. Fan and Fu 81.
    Tree Translation and its Application to Traffic Image Sequence Analysis T.I. Fan and K.S. Fu, IEEE PRIP-81, pp. 184–188Google Scholar
  35. Fennema and Thompson 79.
    Velocity Determination in Scenes Containing Several Moving Objects, C.L. Fennema and W.B. Thompson Computer Graphics and Image Processing 9 (1979) 301–315CrossRefGoogle Scholar
  36. Ferrie et al. 82
    Cell Tracking: A Modeling and Minimization Approach F.P. Ferrie, M.D. Levine, and S.W. Zucker IEEE Trans. Pat. Anal. Machine Intel. PAMI-4 (1982) 277–291CrossRefGoogle Scholar
  37. Flinchbaugh and Chandrasekaran 81.
    A Theory of Spatio-Temporal Aggregation for Vision B.E. Flinchbaugh and B. Chandrasekaran Artificial Intelligence 17 (1981) 387–407CrossRefGoogle Scholar
  38. Gilbert et al. 80
    A Real-Time Video Tracking System A.L. Gilbert, M.K. Giles, G.M. Flachs, R.B. Rogers, and Y. Hsun U IEEE Trans. Pat. Anal. Machine Intel. PAMI-2 (1980) 47–56CrossRefGoogle Scholar
  39. Grimson 81a.
    A Computer Implementation of a Theory of Human Stereo Vision W.E.L. Grimson Phil. Trans. Royal Society of London B 292 (1981) 217–253CrossRefGoogle Scholar
  40. Grimson 81b.
    A Computational Theory of Visual Surface Interpolation W.E.L. Grimson, AI-Memo 613 (June 1981) Artificial Intelligence Laboratory, MIT, Cambridge/MAGoogle Scholar
  41. Haass 81.
    Cloud Tracking from Satellite Pictures U.L. Haass, Ph.D. Dissertation (Spring 1981) Electrical Engineering Department Colorado State University, Fort Collins/COGoogle Scholar
  42. Hall et al. 80
    The Selection of Critical Subsets for Signal, Image, and Scene Matching E.L. Hall, D.L. Davies, and M.E. Casey IEEE Trans. Pat. Anal. Machine Intel. PAMI-2 (1980) 313–322CrossRefGoogle Scholar
  43. Hannah 80.
    Bootstrap Stereo M.J. Hannah Proc. Image Understanding Workshop, L.S. Baumann (ed.) April 1980, pp. 201–208, Science Applications, Inc., Arlington/VAGoogle Scholar
  44. Hartley et al. 78
    Preliminary Studies into the CAO of Pedestrian Circulation Areas M.G. Hartley, R.C. Waterfall, and A.J. Fisher Universities Transport Study Group. Ninth Annual Conference, City University, London January 1978, pp. 693–700Google Scholar
  45. Hirzinger et al. 80
    Automated TV-Tracking of Moving Objects -the OFVLR-Tracker and Related Approaches G. Hirzinger, K. Landzettel, and W. Snyder, ICPR-80, pp. 1255–1261Google Scholar
  46. Horn and Schunck 81.
    Determining Optical Flow B.K.P. Horn and B.G. Schunck Artificial Intelligence 17 (1981) 185–203CrossRefGoogle Scholar
  47. Huang et al. 82
    Interframe Coding with General Two-Dimensional Motion Compensation T.S. Huang, Y.P. Hsu, and R.Y. Tsai, Proc. Int. Conf. Acoustics, Speech, and Signal Processing, Paris, May 3–5, 1982, pp. 464–466Google Scholar
  48. Inigo and McVey 81.
    CCD Implementation of a Three-Dimensional Video-Tracking Algorithm R.M. Inigo and E.S. McVey IEEE Trans. Pat. Anal. Machine Intel. PAMI-3 (1981) 230–240CrossRefGoogle Scholar
  49. Jacobus et al. 80
    Motion Detection and Analysis by Matching Graphs of Intermediate-Levels Primitives C.J. Jacobus, R.T. Chien, and J.M. Selander IEEE Trans. Pat. Anal. Machine Intel. PAMI-2 (1980) 495–510Google Scholar
  50. Jain 81.
    Extraction of Motion Information from Peripheral Processes R. Jain IEEE Trans. Pat. Anal. Machine Intel. PAMI-3 (1981) 489–503CrossRefGoogle Scholar
  51. Jain and Nagel 79.
    On the Analysis of Accumulative Difference Pictures from Image Sequences of Real World Scenes R. Jairi and H.-H. Nagel IEEE Trans. Pat. Anal. Machine Intel. PAMI-1 (1979) 206–214CrossRefGoogle Scholar
  52. Jain et al. 79
    Segmentation through the Detection of Changes due to Motion R. Jain, W.N. Martin, and J.K. Aggarwal Computer Graphics and Image Processing 11 (1979) 13–34CrossRefGoogle Scholar
  53. Jayaramamurthy and Jain 81.
    Segmentation of Textured Dynamic Scenes S.N. Jayaramamurthy and R. Jain, IEEE PRIP-81, pp. 91–93Google Scholar
  54. Kitchen and Rosenfeld 80.
    Gray-Level Corner Detection L. Kitchen and A. Rosenfeld, TR-887 (April 1980) Computer Science Center, University of Maryland, College Park/MDGoogle Scholar
  55. Kories 81.
    Determination of Displacement Vector Fields for General Camera Motions R. Kories, IEEE PRIP-81, pp. 115–117Google Scholar
  56. Kraasch et al. 79
    Automatische Dreidimensionale Beschreibung bewegter Gegenstaende R. Kraasch, B. Radig, W. Zach in: Angewandte Szenenanalyse, J.P. Foith (ed.) Informatik Fachberichte 20, pp. 208–215 Springer Verlag, Berlin-Heidelberg-New York 1979CrossRefGoogle Scholar
  57. Landgrebe 81.
    Analysis Technology for Land Remote Sensing D.A. Landgrebe, Proc. IEEE 69 (1981) 628–642, especially p. 638CrossRefGoogle Scholar
  58. Lawton 81.
    Optic Flow Field Structure and Processing Image Motion O.T. Lawton, IJCAI-81, pp. 700–703Google Scholar
  59. Longuet-Higgins 81.
    A Computer Algorithm for Reconstructing a Scene from Two Projections H.C. Longuet-Higgins, Nature 293 (September 1981) 133–135CrossRefGoogle Scholar
  60. Lucas and Kanade 81.
    An Iterative Image Registration Technique with an Application to Stereo Vision B.D. Lucas and T. Kanade, IJCAI-81, pp. 674–679Google Scholar
  61. Marburger et al. 81
    Natural Language Dialogue about Moving Objects in an Automatically Analyzed Traffic Scene H. Marburger, B. Neumann, and H.-J. Novak, IJCAI-81, pp. 49–51Google Scholar
  62. Marr 76.
    Early Processing of Visual Information D. Marr, Phil. Trans. Royal Society of London B 275 (1976) 483–524CrossRefGoogle Scholar
  63. Marr 78.
    Representing Visual Information -a Computational Approach D. Marr, in Computer Vision Systems, pp. 61–80 A.R. Hanson and E.M. Riseman (eds.), Academic Press New York 1978Google Scholar
  64. Marr and Hildreth 80.
    Theory of Edge Detection D. Marr and E. Hildreth Proc. Royal Society of London B 207 (1980) 187–217CrossRefGoogle Scholar
  65. Marr and Nishihara 76.
    Representation and Recognition of the Spatial Organization of Three-Dimensional Shapes D. Marr and H.K. Nishihara, A.I.-Memo 377 (August 1976) Artificial Intelligence Laboratory, MIT, Cambridge/MAGoogle Scholar
  66. Marr and Nishihara 78.
    Representation and Recognition of the Spatial Organization of Three Dimensional Shapes O. Marr and H.K. Nishihara, Proc. Royal Society B 200 (1978) 269–294CrossRefGoogle Scholar
  67. Marr and Vaina 80.
    Representation and Recognition of the Movements of Shapes D. Marr and L. Vaina, AI-Memo 597 (October 1980) Artificial Intelligence Laboratory, MIT, Cambridge/MAGoogle Scholar
  68. Martin and Aggarwal 81a.
    Occlusion in Dynamic Scene Analysis, W.N. Martin and J.K. Aggarwal in Digital Image Processing, J.C. Simon and R.M. Haralick (eds.) D. Reidel Publ. Co., Dordrecht/Holland and Boston/MA 1981 pp. 579–590Google Scholar
  69. Martin and Aggarwal 81b.
    Occluding Contours in Dynamic Scenes W.N. Martin and J.K. Aggarwal, IEEE PRIP-81, pp. 189–192Google Scholar
  70. Martin and Aggarwal 82.
    Dynamic Scenes and Object Descriptions W.N. Martin and J.K. Aggarwal, Proc. Int. Conf. Acoustics, Speech, and Signal Processing, Paris, May 3–5, 1982, pp. 859–862Google Scholar
  71. May and Wolf 82.
    Picture Coding with Motion Analysis for Low Rate Transmission F. May and W. Wolf Proc. ICC ’82 vol. 1, Philadelphia/PA, June 1982Google Scholar
  72. Mayhew and Frisby 81.
    Psychophysical and Computational Studies towards a Theory of Human Stereopsis J.E.W. Mayhew and J.P. Frisby Artificial Intelligence 17 (1981) 349–385CrossRefGoogle Scholar
  73. Moravec 79.
    Visual Mapping by a Robot Rover H.P. Moravec, IJCAI-79, pp. 598–600Google Scholar
  74. Moravec 80.
    Obstacle Avoidance and Navigation in the Real World by a Seeing Robot Rover H.P. Moravec, Ph.D. Thesis, Department of Computer Science STAN-CS-80-813, Stanford University available, too, as CMU-RI-TR-3 (September 1980) Robotics Institute, Carnegie-Mellon University, Pittsburgh/PAGoogle Scholar
  75. Morgenthaler and Rosenfeld 81.
    Multidimensional Edge Detection by Hypersurface Fitting D.G. Morgenthaler and A. Rosenfeld IEEE Trans. Pat. Anal. Machine Intel. PAMI-3 (1981) 482–486CrossRefGoogle Scholar
  76. Mounts 69.
    A Video Encoding System with Conditional Picture-Element Replenishment F.W. Mounts, Bell System Techn. J. 48 (1969) 2545–2554Google Scholar
  77. Nagel 78a.
    Formation of an Object Concept by Analysis, of Systematic Time Variations in the Optically Perceptible Environment H.-H. Nagel Computer Graphics and Image Processing 7 (1978) 149–194CrossRefGoogle Scholar
  78. Nagel 78b.
    Analysis Techniques for Image Sequences H.-H. Nagel, IJCPR-78, pp. 186–211Google Scholar
  79. Nagel 80.
    From Digital Picture Processing to Image Analysis H.-H. Nagel Proc. International Conference on Image Analysis and Processing V. Cantoni (ed.), Pavia/Italy, October 22–24, 1980, pp. 27–40Google Scholar
  80. Nagel 81a.
    On the Derivation of 3D Rigid Point Configurations from Image Sequences H.-H. Nagel, IEEE PRIP-81, pp. 103–108Google Scholar
  81. Nagel 81b.
    Image Sequence Analysis: What Can We Learn from Applications? H.-H. Nagel, in Image Sequence Analysis, pp. 19–228 T.S. Huang (ed.), Springer Verlag Berlin-Heidelberg-New York 1981Google Scholar
  82. Nagel 82a.
    Displacement Vectors Derived from Second Order Intensity Variations in Image Sequences H.-H. Nagel Computer Graphics and Image Processing 1982 (in press)Google Scholar
  83. Nagel 82b.
    On Change Detection and Displacement Vector Estimation in Image Sequences, H.-H. Nagel Pattern Recognition Letters, October 1982 (in press)Google Scholar
  84. Nagel and Enkelmann 82.
    Investigation of Second Order Greyvalue Variations to Estimate Corner Point Displacements H.-H. Nagel and W. Enkelmann, ICPR-82 (in press)Google Scholar
  85. Nagel and Neumann 81.
    On 3D Reconstruction from Two Perspective Views H.-H. Nagel and B. Neumann, IJCAI-81, pp. 661–663Google Scholar
  86. Nagel and Rekers 82.
    Moving Object Masks Based on an Improved Likelihood Test H.-H. Nagel and G. Rekers, ICPR-82 (in press)Google Scholar
  87. Netravali and Robbins 80.
    Motion-Compensated Coding: Some New Results A.N. Netravali and J.D. Robbins Bell System Technical J. 59 (1980) 1735–1745Google Scholar
  88. Neumann 80.
    Motion Analysis of Image Sequences for Object Grouping and Reconstruction B. Neumann, ICPR-80, pp. 1262–1265Google Scholar
  89. Neumann 81.
    3D-Information aus mehrfachen Ansichten B. Neumann, in B. Radig (Hrsgb.) Modelle und Strukturen 4. DAGM Symposium Hamburg 6.-8. Oktober 1981 Informatik-Fachberichte 49 pp. 93–111 Springer Verlag Berlin-Heidelberg-New York 1981Google Scholar
  90. Neumann 82.
    Towards Natural Language Description of Real-World Image Sequences B. Neumann, 12. Jahrestagung der Gesellschaft fuer Informatik 1982 Informatik-Fachberichte, (in press) Springer-Verlag Berlin-Heidelberg-New York 1982Google Scholar
  91. O’Rourke 81.
    Motion Detection Using Hough Technique J. O’Rourke, IEEE PRIP-81, pp. 82–87Google Scholar
  92. O’Rourke and Badler 80.
    Model-Based Image Analysis of Human Motion Using Constraint Propagation, J. O’Rourke and N.I. Badler IEEE Trans. Pat. Anal. Machine Intel. PAMI-2 (1980) 522–536Google Scholar
  93. Okada 79.
    SUPP: Understanding Moving Picture Patterns Based on Linguistic Knowledge N. Okada, IJCAI-79, pp. 690–692Google Scholar
  94. Okada 80.
    Conceptual Taxonomy of Japanese Verbs for Understanding Natural Language and Picture Patterns N. Okada, Proc. COLING-80. pp. 127–135 see, too, Conceptual Taxonomy of Japanese Verbs and Sentence Production from Picture Pattern Sequences Technical Report, Information Science and Systems Engineering Oita University, Oita 870-11/Japan (December 1980)Google Scholar
  95. Prager 79.
    Segmentation of Static and Dynamic Scenes J.M. Prager, COINS Technical Report 79-7 (May 1979) Computer and Information Science University of Massachusetts, Amherst/MAGoogle Scholar
  96. Prazdny 80.
    Egomotion and Relative Depth Map from Optical Flow K. Prazdny, Biological Cybernetics 36 (1980) 87–102MATHMathSciNetCrossRefGoogle Scholar
  97. Prazdny 81a.
    Determining the Instantaneous Direction of Motion from Optical Flow Generated by a Curvilinearly Moving Observer K. Prazdny Computer Graphics and Image Processing 17 (1981) 238–248CrossRefGoogle Scholar
  98. Prazdny 81b.
    A Simple Method for Recovering Relative Depth Map in the Case of a Translating Sensor K. Prazdny, IJCAI-81, pp. 698–699Google Scholar
  99. Price and Reddy 79.
    Matching Segments of Images, K. Price and R. Reddy IEEE Trans. Pat. Anal. Machine Intel. PAMI-1 (1979) 110–116CrossRefGoogle Scholar
  100. Radig 81a.
    Inferential Region Extraction in TV-Sequences B. Radig, IJCAI-81, pp. 719–721Google Scholar
  101. Radig 81b.
    Image Region Extraction of Moving Objects B.M. Radig, in Image Sequence Analysis, pp. 311–354 T.S. Huang (ed.), Springer Verlag Berlin-Heidelberg-New York 1981Google Scholar
  102. Radig et al. 80
    Matching Symbolic Descriptions for 3-D Reconstruction of Simple Moving Objects B. Radig, R. Kraasch, and W. Zach, ICPR-80, pp. 1081–1084Google Scholar
  103. Ranade and Rosenfeld 80.
    Point Pattern Matching by Relaxation S. Ranade and A. Rosenfeld, Pattern Recognition 12 (1980) 269–275CrossRefGoogle Scholar
  104. Rashid 80.
    Towards a System for the Interpretation of Moving Light Displays R.F. Rashid IEEE Trans. Pat. Anal. Machine Intel. PAMI-2 (1980) 574–581Google Scholar
  105. Requicha and Voelcker 82.
    Solid Modeling: A Historical Summary and Contemporary Assessment A.A.G. Requicha and H.B. Voelcker IEEE Computer Graphics and Applications 2, No. 2 (March 1982) 9–24CrossRefGoogle Scholar
  106. Roach and Aggarwal 79.
    Computer Tracking of Objects Moving in Space J. Roach and J.K. Aggarwal IEEE Trans. Pat. Anal. Machine Intel. PAMI-1 (1979) 127–135CrossRefGoogle Scholar
  107. Roach and Aggarwal 80.
    Determining the Movement of Objects from a Sequence of Images J.W. Roach and J.K. Aggarwal IEEE Trans. Pat. Anal. Machine Intel. PAMI-2 (1980) 554–562Google Scholar
  108. Rocca 69.
    Television Bandwidth Compression Utilizing Frame-to-Frame Correlation and Movement Compensation F. Rocca Symposium on Picture Bandwidth Compression MIT, Cambridge/MA, April 1969, T.S. Huang and O.J. Tretiak (eds.) Gordon and Breach, New York 1972, pp. 675–693Google Scholar
  109. Schalkoff 79.
    Algorithms for a Real-Time Automatic Video Tracking System R.J. Schalkoff, Ph.D. Thesis (May 1979) Dept. Electrical Engineering, Univ. of Virginia, Charlottesville/VAGoogle Scholar
  110. Schalkoff and McVey 79.
    Algorithm Development for Real-Time Automatic Video Tracking Systems R.J. Schalkoff and E.S. McVey Proc. 3rd International Computer Software and Applications Conference, Chicago/IL, November 1979, pp. 504–511 see also IEEE Trans. Pat. Anal. Machine Intel. PAMI-4 (1982) 2–10Google Scholar
  111. Schank and Abelson 77.
    Scripts, Plans, Goals, and Understanding R.C. Schank and R.P. Abelson Lawrence Erlbaum Associates, Publishers, Hillsdale/NJ 1977MATHGoogle Scholar
  112. Schoffa and Mayer 81.
    Merkmalsreduzierung mit Fourier-Deskriptoren bei elektrischen Potentialkarten des Herzens G. Schoffa und R. Mayer in B. Radig (Hrsgb.) Modelle und Strukturen 4. DAGM Symposium Hamburg 6.-8. Oktober 1981 Informatik-Fachberichte 49 pp. 248–254 Springer Verlag Berlin-Heidelberg-New York 1981Google Scholar
  113. Schoffa et al. 80
    Image Processing in Body Surface Mapping G. Schoffa, R. Mayer, and W. Postweiler Suppl. Mikroskopie (Wien) 37 (1980) 444–447Google Scholar
  114. Schwidefsky and Ackermann 76.
    Photogrammetrie , K. Schwidefsky und F. Ackermann B.G. Teubner, Stuttgart/FR Germany 1976Google Scholar
  115. Schunck and Horn 81.
    Constraints on Optical Flow Computation B.G. Schunck and B.K.P. Horn, IEEE PRIP-81, pp. 205–210Google Scholar
  116. Shafer and Kanade 82.
    Using Shadows in Finding Surface Orientation S.A. Shafer and T. Kanade CMU-CS--81-100 -(January 1982), Computer Science Department Carnegie-Mellon University, Pittsburgh/PAGoogle Scholar
  117. Shani 80.
    A 3-D Model-Driven System for the Recognition of Abdominal Anatomy from CT Scans U. Shani, ICPR-80, pp. 585–591; see also TR-82 (August 1981) Computer Science Department, University of Rochester, Rochester/NYGoogle Scholar
  118. Sloan and Hrechanyk 81.
    Surface Reconstruction from Sparse Data K.R. Sloan and L.M. Hrechanyk, IEEE PRIP-81, pp. 45–48Google Scholar
  119. Snyder 81.
    Computer Analysis of Time-Varying Images, W.E. Snyder (ed.) Special issue IEEE Computer 14, No. 8 (August 1981)Google Scholar
  120. Snyder et al. 80
    Image Modeling, the Continuity Assumption and Tracking W.E. Snyder, S.A. Rajala, and G. Hirzinger ICPR-80, pp. 1111–1114Google Scholar
  121. Stevens 78.
    Computation of Locally Parallel Structure K.A. Stevens Proc. Image Understanding Workshop, L.S. Baumann (ed.) Pittsburgh/PA, November 14–15, 1978, pp. 92–102 Science Applications, Inc., Arlington/VA 22209 see also: Biological Cybernetics 29 (1978) 19–28Google Scholar
  122. Stockman et al. 82
    Matching Images to Models for Registration and Object Detection via Clustering G. Stockman, S. Kopstein, and S. Benett IEEE Trans. Pat. Anal. Machine Intel. PAMI-4 (1982) 229–241CrossRefGoogle Scholar
  123. Taccardi et al. 78
    Body-Surface Mapping of Heart Potentials B. Taccardi, L. De Ambroggi, and C. Viganotti in: The Theoretical Basis of Electrocardiology C.V. Nelson and D.B. Geselowitz (eds.) Clarendon Press, Oxford 1976, pp. 436–466Google Scholar
  124. Thompson 80.
    Combining Motion and Contrast for Segmentation W.B. Thompson IEEE Trans. Pat. Anal. Machine Intel. PAMI-2 (1980) 543–549Google Scholar
  125. Thompson et al. 81
    Relaxation Labeling Using Staged Updating W.B. Thompson, K.M. Mutch, J.K. Kearney, and R.L. Madarasz IEEE PRIP-81, pp. 449–451Google Scholar
  126. Tsai and Huang 81.
    Uniqueness and Estimation of Three-Dimensional Motion Parameters of Rigid Objects with Curved Surfaces R.Y. Tsai and T.S. Huang Report R-921 (October 1981), Coordinated Science Laboratory University of Illinois at Urbana-Champaign see also T.S. Huang, this volumeGoogle Scholar
  127. Tsotsos 81.
    Temporal Event Recognition: An Application to Left Ventricular Performance J.K. Tsotsos, IJCAI-81, pp. 900–907Google Scholar
  128. Tsotsos et al. 80
    A Framework for Visual Motion Understanding J.K. Tsotsos, J. Mylopoulos, H.D. Covvey, and S.W. Zucker IEEE Trans. Pat. Anal. Machine Intel. PAMI-2 (1980) 563–573Google Scholar
  129. Tsuji et al. 77
    Understanding a Simple Cartoon Film by a Computer Vision System S. Tsuji, A. Morizono, and S. Kuroda, IJCAI-77, pp. 609–610Google Scholar
  130. Tsuji et al. 80
    Tracking and Segmentation of Moving Objects in Dynamic Line Images S. Tsuji, M. Osada, and M. Yachida IEEE Trans. Pat. Anal. Machine Intel. PAMI-2 (1980) 516–522Google Scholar
  131. Udupa et al. 82
    Boundary Detection in Multidimensions J.K. Udupa, S.N. Srihari, and G.T. Herman IEEE Trans. Pat. Anal. Machine Intel. PAMI-4 (1982) 41–50CrossRefGoogle Scholar
  132. Ullman 79.
    The Interpretation of Visual Motion S. Ullman, The MIT Press, Cambridge/Mass., 1979Google Scholar
  133. Wallace and Mitchell 80.
    Analysis of Three-Dimensional Movement Using Fourier Descriptors T.P. Wallace and O.R. Mitchell IEEE Trans. Pat. Anal. Machine Intel. PAMI-2 (1980) 583–588Google Scholar
  134. Ward and Chien 80.
    Analysis of Time-Varying Imagery Through the Representation of Position and Shape Changes M.O. Ward and Y.T. Chien, ICPR-80, pp. 1236–1238Google Scholar
  135. Ward and Chien 81.
    Occlusion Analysis in Time-Varying Imagery M.O. Ward and Y.T. Chien, IEEE PRIP-81, pp. 504–507Google Scholar
  136. Webb 81.
    Shape and Structure from Motion of Objects J.A. Webb, Ph.D. Dissertation (December 1981) University of Texas at Austin, Austin/TXGoogle Scholar
  137. Webb and Aggarwal 80.
    Observing Jointed Objects J.A. Webb and J.K. Aggarwal, ICPR-80, pp. 1246–1250Google Scholar
  138. Webb and Aggarwal 81.
    Structure from Motion of Rigid and Jointed Objects J.A. Webb and J.K. Aggarwal, IJCAI-81, pp. 686–691Google Scholar
  139. Westphal 82.
    Photometric Stereo for Moving Objects H. Westphal, this volume; see also ICPR-82 (in press)Google Scholar
  140. Westphal and Nagel 81.
    Zur Ermittlung gekruemmter Oberflaechen bewegter Objekte aus Bildfolgen H. Westphal und H.-H. Nagel in B. Radig (Hrsgb.) Modelle und Strukturen 4. DAGM Symposium Hamburg 6.-8. Oktober 1981 Informatik-Fachberichte 49, pp. 123–129 Springer Verlag Berlin-Heidelberg-New York 1981Google Scholar
  141. Williams 80.
    Depth from Camera Motion in a Real World Scene T.D. Williams IEEE Trans. Pat. Anal. Machine Intel. PAMI-2 (1980) 511–516Google Scholar
  142. Yachida 81.
    Determining Velocity Map by 3-D Iterative Estimation M. Yachida, IJCAI-81, pp. 716–718Google Scholar
  143. Yachida et al. 81
    Automatic Analysis of Moving Images M. Yachida, M. Asada, and S. Tsuji IEEE Trans. Pat. Anal. Machine Intel. PAMI-3 (1981) 12–20CrossRefGoogle Scholar
  144. Yakimovsky 76.
    Boundary and Object Detection in Real World Images Y. Yakimovsky, J. ACM 23 (1976) 599–618MATHMathSciNetCrossRefGoogle Scholar
  145. Yalamanchili et al. 80
    Oifferencing Operations for the Segmentation of Moving Objects in Dynamic Scenes S. Yalamanchili, W.N. Martin, and J.K. Aggarwal ICPR-80, pp. 1239–1242; see also IEEE PRIP-81, pp. 211–216 and Computer Graphics and Image Processing 18 (1982) 188–201CrossRefGoogle Scholar
  146. Yam and Davis 80.
    Image Registration Using Generalized Hough Transforms S. Yam and L.S. Davis TR- 80-7 (December 1980), Computer Sciences Department University of Texas at Austin, Austin/TXGoogle Scholar
  147. Yam and Davis 81.
    Image Registration Using Generalized Hough Transforms S. Yam and L.S. Davis, IEEE PRIP-81, pp. 526–533Google Scholar
  148. Zucker and Hummel 81.
    A Three-Dimensional Edge Operator S.W. Zucker and R.A. Hummel IEEE Trans. Pat. Anal. Machine Intel. PAMI-3 (1981) 324–331CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1983

Authors and Affiliations

  • Hans-Hellmut Nagel
    • 1
  1. 1.Fachbereich InformatikUniversität HamburgHamburg 13FR Germany

Personalised recommendations