Cooperative Vision Integration Through Data-Parallel Neural Computations

The authors describe a neural network approach for combining processing of multiple early vision modules. Energy functions for coupling the computation of intensity contours, optical flow, and stereo disparity are defined. Hopfield neural networks are used for function minimization with deterministic annealing to avoid spurious local minima. Vision integration schemes are developed by extending the work of T.A. Poggio et al. (1988) to include cooperative interactions between different vision modules and the Hebbian adaptation of vision module coupling on a massively parallel computer consisting of 4096 processing elements operated in a single-instruction-multiple-data mode. Simple experiments assess the performance of various integration approaches. The resulting algorithms facilitate fast, robust image segmentation. >

[1]  James J. Clark,et al.  Data Fusion for Sensory Information Processing Systems , 1990 .

[2]  Ren C. Luo,et al.  Multisensor integration and fusion in intelligent systems , 1989, IEEE Trans. Syst. Man Cybern..

[3]  Heinrich H. Bülthoff,et al.  Integration of Visual Modules , 1992 .

[4]  T Poggio,et al.  Parallel integration of vision modules. , 1988, Science.

[5]  David G. Luenberger,et al.  Linear and nonlinear programming , 1984 .

[6]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[7]  Daphna Weinshall,et al.  Integration of vision modules and labeling of surface discontinuities , 1989, IEEE Trans. Syst. Man Cybern..

[8]  Dennis Parkinson,et al.  Massively parallel computing with the DAP , 1990 .

[9]  Yi Liu,et al.  Integration of stereo vision and optical flow by using an energy-minimization approach , 1989 .

[10]  H. Barrow,et al.  RECOVERING INTRINSIC SCENE CHARACTERISTICS FROM IMAGES , 1978 .

[11]  Federico Girosi,et al.  Parallel and Deterministic Algorithms from MRFs: Surface Reconstruction , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  C Koch,et al.  Analog "neuronal" networks in early vision. , 1986, Proceedings of the National Academy of Sciences of the United States of America.

[13]  John N. Tritsiklis.  A comparison of Jacobi and Gauss-Seidel parallel iterations , 1989 .

[14]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Azriel Rosenfeld,et al.  Computer Vision , 1988, Adv. Comput..

[16]  T. Poggio,et al.  III-Posed problems early vision: from computational theory to analogue networks , 1985, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[17]  M. Bertero,et al.  Ill-posed problems in early vision , 1988, Proc. IEEE.

[18]  Jin Luo,et al.  Computing motion using analog and binary resistive networks , 1988, Computer.

[19]  Anand Rangarajan,et al.  Generalized graduated nonconvexity algorithm for maximum a posteriori image estimation , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[20]  Andrew Blake,et al.  Visual Reconstruction , 1987, Deep Learning for EEG-Based Brain–Computer Interfaces.

[21]  W. Eric L. Grimson,et al.  Binocular shading and visual surface reconstruction , 1984, Comput. Vis. Graph. Image Process..

[22]  T. Poggio,et al.  Visual Integration and Detection of Discontinuities: The Key Role of Intensity Edges , 1987 .

[23]  M. J. Daily.  SELF-CALIBRATION OF A MULTI-CAMERA VISION SYSTEM , 1990, 1990 Conference Record Twenty-Fourth Asilomar Conference on Signals, Systems and Computers, 1990..

[24]  C Koch,et al.  A two-dimensional analog VLSI circuit for detecting discontinuities in early vision. , 1990, Science.

[25]  John Y. Aloimonos,et al.  Unification and integration of visual modules: an extension of the Marr Paradigm , 1989 .

[26]  David W. Murray,et al.  A parallel approach to the picture restoration algorithm of Geman and Geman on an SIMD machine , 1986, Image Vis. Comput..

[27]  Tomaso A. Poggio,et al.  Extensions of a Theory of Networks for Approximation and Learning , 1990, NIPS.

[28]  Scott T. Toborg.  A 3-D wafer scale architecture for early vision processing , 1990, [1990] Proceedings of the International Conference on Application Specific Array Processors.