Charles R. Dyer

View Synthesis

The goal of this work is to develop basic tools for controlling in real-time, either autonomously or interactively, a virtual camera of a real environment. The input is a set of images or video streams, acquired from fixed or mobile cameras around a site, and the output is a panoramic visualization of the scene in which a virtual, user-controlled camera can be moved through the environment. With this technology a user could interactively navigate through a real environment, controlling a customized path of views of the site that are not predetermined by the input images. The main research question is how to adaptively combine a set of basis images to synthesize new views of the scene without 3D models or 3D scene reconstruction as an intermediate step. Recently we have developed an innovative technique, which we call view morphing, that takes two basis images and interpolates a continuous range of in-between images corresponding to views on the linear path connecting the two camera centers.

Visual Exploration

Computer vision researchers have recently started to investigate how to actively control the image acquisition process by controlling camera parameters. We have been studying how to purposefully control the position and orientation of a camera in order to dynamically adjust viewpoint based on the appearance of a three-dimensional scene. The use of real-time viewpoint-control behaviors is important for solving tasks such as exploring an unknown object in order to find specific surface markings, building a global model of an unknown shape, or recognizing an object.

By coordinating simple observer behaviors that change the appearance of surfaces in a well-defined way, we simplify the image computations required, make precise the global progress of an algorithm, and eliminate the need for accurate differential measurements of the camera motion. We believe that this active approach of moving towards viewpoints that are closely related to the geometry of the viewed objects is a very important and general one. We have used this approach to develop provably-correct algorithms for (1) moving to a side view of a surface of revolution in order to recover its shape, and (2) reconstructing the global surface of an unknown smooth, arbitrarily-shaped object.

Visualization

In the area of visualization we have developed mapping techniques capable of generating displays of all possible data objects defined in a user's algorithm, without the need for user-defined, type-specific graphics display procedures. This capability for displaying arbitrary combinations of an algorithm's data objects in a common frame of reference, coupled with interactive control of algorithm execution, provides a powerful way to understand algorithm behavior, especially interactive visual experiments with scientific data analysis algorithms. We have implemented a system called VIS-AD for experimenting with these techniques and have used it for visualizing intermediate and final results of data analysis algorithms for problems such as discriminating clouds in satellite images.

Klinger A and Dyer CR. Experiments on picture representation using regular decomposition. Computer Graphics and Image Processing 5:68-105, 1976.

Weszka J, Dyer CR and Rosenfeld A. A comparative study of texture measures for terrain classification. IEEE Trans. Systems, Man, and Cybernetics 6:269-285, 1976.

Dyer CR and Rosenfeld A. Fourier texture features: suppression of aperture effects. IEEE Trans. Systems, Man, and Cybernetics 6:703-705, 1976.

Dyer CR and Rosenfeld A. Thinning algorithms for grayscale pictures. IEEE Trans. Pattern Analysis and Machine Intelligence 1:88-89, 1979.

Hong T, Dyer CR and Rosenfeld A. Texture primitive extraction using an edge-based approach. IEEE Trans. Systems, Man, and Cybernetics 10:659-675, 1980.

Dyer C, Rosenfeld A and Samet A. Region representation: boundary codes from quadtrees. Comm. ACM 23:171-179, 1980.

Dyer CR, Hong T and Rosenfeld A. Texture classification using gray level cooccurrence based on edge maxima. IEEE Trans. Systems, Man, and Cybernetics 10:158-163, 1980.

Dyer CR. One-way bounded cellular automata. Information and Control 44:261-281, 1980.

Dyer CR. Computing the Euler number of an image from its quadtree. Computer Graphics and Image Processing 13:270-276, 1980.

Dyer CR. A fast parallel algorithm for the closest pair problem. Information Processing Letters 49-52, 1980.

Dyer CR and Rosenfeld A. Propagation algorithms for framing rectangle construction. Pattern Recognition 12:211-215, 1980.

Dyer CR. Relation of one-way parallel/sequential automata to two-dimensional finite-state automata. Information Sciences 23:25-30, 1981.

Dyer CR and Rosenfeld A. Parallel image processing by memory-augmented cellular automata. IEEE Trans. Pattern Analysis and Machine Intelligence 3:29-41, 1981.

Dyer CR and Rosenfeld A. Triangle cellular automata. Information and Control48:54-69, 1981.

Dyer CR. The space efficiency of quadtrees. Computer Graphics and Image Processing 19:335-348, 1982.

Dyer CR. Gauge inspection using Hough transforms. IEEE Trans. Pattern Analysis and Machine Intelligence 5:621-623, 1983.

Cibulskis JM and Dyer CR. An analysis of node linking in overlapped pyramids. IEEE Trans. Systems, Man, and Cybernetics 14:424-436, 1984.

Ho S-B and Dyer CR. Shape smoothing using medial axis properties. IEEE Trans. Pattern Analysis and Machine Intelligence 8:512-520, 1986.

Neveu CF, Dyer CR and Chin RT. 2-D object recognition using multi-resolution models. Computer Vision, Graphics and Image Processing 34:52-65, 1986.

Chin RT and Dyer CR. Model-based recognition in robot vision. ACM Computing Surveys 18:67-108, 1986.

Augusteijn MF and Dyer CR. Recognition and recovery of the three-dimensional orientation of planar point patterns. Computer Vision, Graphics and Image Processing 36:76-99, 1986.

Korn MR and Dyer CR. 3-D multi-view object representations for model-based object recognition. Pattern Recognition 20:91-103, 1987.

Stewart CV and Dyer CR. Scheduling algorithms for PIPE (Pipelined Image-Processing Engine). J. Parallel and Distributed Computing 5:131-153, 1988.

Plantinga H and Dyer CR. Visibility, occlusion, and the aspect graph. Int. J. of Computer Vision 5:137-160, 1990.

Bowyer KW and Dyer CR. Aspect graphs: an introduction and survey of recent results. Int. J. of Imaging Systems and Technologies 2:315-328, 1990.

Faugeras O, Mundy J, Ahuja N, Dyer CR, Pentland A, Jain R, Ikeuchi K and Bowyer K. Why aspect graphs are not (yet) practical for computer vision. Computer Vision, Graphics and Image Processing: Image Understanding. 55:212-218, 1992.

Seales WB and Dyer CR. Viewpoint from occluding contour. Computer Vision, Graphics and Image Processing: Image Understanding 55:198-211, 1992.

Wah B, Huang T, Joshi A, Moldovan D, Aloimonos J, Bajcsy R, Ballard D, DeGroot D, DeJong K, Dyer C, Fahlman S, Grishman R, Hirschman L, Korf R, Levinson S, Miranker D, Morgan N, Nirenburg S, Poggio T, Riseman E, Stanfill C, Stolfo S, Tanimoto S and Weems C. Report on workshop on high performance computing and communications for grand challenge applications: Computer vision, speech and natural language processing, and artificial intelligence. IEEE Trans. Knowledge and Data Engineering. 5:138-154, 1993.

Eggert DW, Bowyer KW, Dyer CR, Christensen HI and Goldgof DB. The scale space aspect graph. IEEE Trans. Pattern Analysis and Machine Intelligence 15:1114-1130, 1993.

Allmen M and Dyer CR. Computing spatiotemporal relations for dynamic perceptual organization. Computer Vision, Graphics and Image Processing: Image Understanding 58:338-351, 1993.

Kutulakos KN and Dyer CR. Recovering shape by purposive viewpoint adjustment. Int. J. Computer Vision 12:113-136, 1994.

Hibbard W, Paul BE, Battaiola AL, Santek DA, Voidrot-Martinez M-F, and Dyer CR. Interactive visualization of computations in the earth and space sciences. IEEE Computer 27(7):65-72, 1994.

Kutulakos KN and Dyer CR. Global surface reconstruction by purposive control of observer motion. Artificial Intelligence 78(1-2):147-177, 1995.

Seitz SM and Dyer CR. View-invariant analysis of cyclic motion. Int. J. Computer Vision 25(3):231-251, 1997.

Fleming MG, Steger C, Zhang J, Gao J, Cognetta AB, Pollak I and Dyer CR. Techniques for a structural analysis of dermatoscopic imagery. Computerized Medical Imaging and Graphics 22(5):375-89, 1998 (Sept-Oct)

Book Chapters

McCormick BH, Kent EW, and Dyer CR. A cognitive architecture for computer vision, in Fifth Generation Computer Systems, Moto-Oka T, ed.., p. 245-264. North-Holland, Amsterdam: 1982.

Dyer CR. Pyramid algorithms and machines, in Multicomputers and Image Processing: Algorithms and Programs, Preston K and Uhr L, eds., p. 409-420. Academic Press, New York: 1982.

McCormick BH, Kent EW and Dyer CR. A visual analyzer for real-time interpretation of time-varying imagery, in Multi-computers and Image Processing: Algorithms and Programs, Preston K and Uhr L, eds., p. 453-464. Academic Press, New York: 1982.

Cibulskis JM and Dyer CR. Node linking strategies in pyramids for image segmentation, in Multi-resolution Image Processing and Analysis, Rosenfeld A., ed., p. 109-120. Springer-Verlag, Berlin: 1984.

Dyer CR and Clarke MJ: VLSI architectures for curve detection, in VLSI for Pattern Recognition and Image Processing, Fu KS, ed., p. 157-173. Springer-Verlag, New York: 1984.

Kjell BP and Dyer CR. Segmentation of textured images by pyramid linking, in Pyramidal Systems for Computer Vision, Cantoni V and Levialdi S, eds., p. 273-288. Springer-Verlag, Berlin: 1986.

Dyer CR. Multi-scale image understanding, in Parallel Computer Vision, Uhr. L., ed., p. 171-213. Academic Press, New York: 1987.

Verghese G, Gale KL and Dyer CR. Real time, parallel motion tracking of three-dimensional objects from spatiotemporal sequences, in Parallel Algorithms for Machine Intelligence and Vision, Kumar V, Gopalakrishnan P and Kanal L eds., p. 310-339. Springer-Verlag, New York: 1990.

Stewart CV and Dyer CR. Parallel simulation of a connectionist stereo algorithm on a shared-memory multi-processor, in Parallel Algorithms for Machine Intelligence and Vision, Kumar V, Gopalakrishnan P and Kanal L eds., p. 340-359. Springer-Verlag, New York: 1990.

Dyer CR and Rosenfeld A. Thinning algorithms for grayscale pictures, in Fuzzy Models for Pattern Recognition: Methods That Search for Structures in Data, Bezdek JC and Pal SK, eds., p. 347-348. IEEE Press, Piscataway, NJ: 1992.

Bowyer KW and Dyer CR. Three-dimensional shape representation, in Handbook of Pattern Recognition and Image Processing: Computer Vision, Young TY ed., p. 17-51. Academic Press, New York: 1994.

Hibbard W, Dyer CR and Paul B. The VIS-AD data model: Integrating metadata and polymorphic display with a scientific programming language, in Database Issues for Data Visualization (Lecture Notes in Computer Science No. 871), Lee JP and Grinstein G, eds., p. 37-68. Springer-Verlag, New York: 1994.

Hibbard W, Dyer CR and Paul BE. Interactivity and the dimensionality of data displays, in Perceptual Issues in Visualization, Grinstein G and Levkowitz H, eds., p. 75-82. Springer-Verlag, Berlin: 1995.

Yu L and Dyer CR. Shape recovery from stationary surface contours by controlled observer motion, in Advances in Image Understanding: A Festscrift for Azriel Rosenfeld, Bowyer K and Ahuja N, eds., p. 177-193. IEEE Computer Society Press, Los Alamitos, CA: 1996.

Seitz SM and Dyer CR. Cyclic motion analysis using the period trace, in Motion-Based Recognition, Shah M and Jain R, eds., p. 61-85. Kluwer, Boston: 1997.