17.2.7 Optical Flow -- Hierarchical, Multi-Grid, Multi-Scale Approaches

Terzopoulos, D.[Demetri],
Image Analysis Using Multigrid Relaxation Methods,
PAMI(8), No. 2, March 1986, pp. 129-139. Relaxation. BibRef 8603
Earlier:
Concurrent Multiple Relaxation,
DARPA85(156-162). BibRef
Earlier:
Multigrid Relaxation Methods and the Analysis of Lightness, Shading and Flow,
MIT AI Memo-803, October 1984.
WWW Version. See also Computation of Visible-Surface Representations, The. Use the constraints at other levels, simple description is that these are just included in the weighted sum. There are no references to the classical relaxation work, even if it does not do anything at the multiple levels. BibRef

Enkelmann, W.[Wilfried],
Investigation of Multigrid Algorithms for the Estimation of Optical Flow Fields in Image Sequences,
CVGIP(43), No. 2, August 1988, pp. 150-177.
WWW Version. BibRef 8808
Earlier: Motion86(81-87). Multiple resolution (cue the coarse directions to guide the smoothing at the finer resolutions) is used to improve the results. Some of the best real examples of optical flow results. BibRef

Hutchinson, J.[James], Koch, C., Luo, J., and Mead, C.,
Computing Motion Using Analog and Binary Resistive Networks,
Computer(21), No. 3, March 1988, pp. 52-63. BibRef 8803

Battiti, R., Amaldi, E., and Koch, C.,
Computing Optical Flow across Multiple Scales: An Adaptive Coarse-to-Fine Strategy,
IJCV(6), No. 2, June 1991, pp. 133-145.
Springer DOI Link BibRef 9106

Horiuchi, T., Bair, W., Bishofberger, B., Moore, A., Koch, C., and Lazzaro, J.,
Computing Motion Using Analog VLSI Vision Chips: An Experimental Comparison among Different Approaches,
IJCV(8), No. 3, 1992, pp. 203-216. BibRef 9200
Earlier: A5, A4, A2, A1, A3, A7, Only: "Different" was "Four": Motion91(312-324). BibRef

Harris, J.G., Koch, C., Staats, E., and Lou, J.,
Analog Hardware for Detecting Discontinuities in Early Vision,
IJCV(4), No. 3, 1990, pp. 211-223.
Springer DOI Link See also Analog Network for Continuous-Time Segmentation, An. BibRef 9000

Koch, C., Wang, H.T., Battiti, R., Mathur, B., and Ziomkowski, C.,
An Adaptive Multi-Scale Approach for Estimating Optical Flow: Computational Theory and Physiological Implementation,
Motion91(111-122). BibRef 9100

Dengler, J., Schmidt, M.,
The Dynamic Pyramid: A Model for Motion Analysis with Controlled Continuity,
PRAI(2), 1988, pp. 275-286. BibRef 8800

Dengler, J.,
Local Motion Estimation with the Dynamic Pyramid,
ICPR86(1289-1292). BibRef 8600

Dengler, J.,
Estimation of Discontinuous Displacement Vector Fields with the Minimum Description Length Criterion,
CVPR91(276-282).
IEEE Abstract. BibRef 9100
And: MIT AI Memo-1265, October 1990, Scale Space. BibRef

Hwang, S.H., Lee, S.U.,
A Hierarchical Optical Flow Estimation Algorithm Based on the Interlevel Motion Smoothness Constraint,
PR(26), No. 6, June 1993, pp. 939-952.
WWW Version. BibRef 9306

Luettgen, M.R., Karl, W.C., Willsky, A.S.,
Efficient Multiscale Regularization With Applications To The Computation Of Optical Flow,
IP(3), No. 1, January 1994, pp. 41-64.
IEEE DOI Link BibRef 9401

Anandan, P.,
Measuring Visual Motion from Image Sequences,
Ph.D.Thesis (CS), 1987, BibRef 8700 COINSU Mass. BibRef

Anandan, P.,
A Computational Framework and an Algorithm for the Measurement of Visual Motion,
IJCV(2), No. 3, January? 1989, pp. 283-310.
Springer DOI Link BibRef 8901
Earlier:
A Unified Perspective on Computational Techniques for the Measurement of Visual Motion,
ICCV87(219-230). BibRef
And: DARPA87(719-732). Scale Space. A continuation of the prior work. Use a hierarchical scale space approach to the process. BibRef

Meghabghab, G., Kandel, A.,
Hierarchical Analysis of Visual Motion,
SMC(22), 1992, pp. 813-820. BibRef 9200

Konrad, J., and Dubois, E.,
Bayesian Estimation of Motion Vector Fields,
PAMI(14), No. 9, September 1992, pp. 910-927.
IEEE Abstract.
WWW Version. BibRef 9209
Earlier:
Multigrid Bayesian Estimation of Image Motion Fields Using Stochastic Relaxation,
ICCV88(354-362).
IEEE Abstract. Relaxation. Generate dense vector fields. Multiple resolution approach. BibRef

Konrad, J.[Janusz], Dubois, E.[Eric],
A Comparison of Stochastic and Deterministic Solution Methods in Bayesian Estimation of 2-D Motion,
IVC(9), No. 4, August 1991, pp. 215-228.
WWW Version. BibRef 9108
Earlier: ECCV90(149-160).
Springer DOI Link Optical flow using MAP. Earlier note had: IVC(8), No. 4, November 1990, pp. 304-317. Newer is from current online listing. BibRef

Mitiche, A., Wang, Y.F., and Aggarwal, J.K.,
Experiments in Computing Optical Flow with the Gradient-Based, Multiconstraint Method,
PR(20), No. 2, 1987, pp. 173-179.
WWW Version. This paper presents results on camera acquired images using feature operators to derive image functions for the data. The method is a multiconstraint approach. BibRef 8700

Xie, K., van Eycken, L., Oosterlinck, A.,
Hierarchical Motion Estimation with Smoothness Constraints and Postprocessing,
OptEng(35), No. 1, January 1996, pp. 145-155. BibRef 9601

Song, S., Liao, M., Qin, J.,
Multiresolution Image Motion Detection and Displacement Estimation,
MVA(3), 1990, pp. 17-20. See also Multiresolution Image Dynamic Thresholding. BibRef 9000

Yang, Q., Ma, S.D.,
Intrinsic Multiscale Representation Using Optical Flow in the Scale-Space,
IP(8), No. 3, March 1999, pp. 444-447.
IEEE DOI Link BibRef 9903

Close, R.[Robert], Tamura, S.[Shinichi], Naito, H.[Hiroaki],
Estimation of motion from sequential images using integral constraints,
PR(28), No. 1, January 1995, pp. 1-9.
WWW Version. 0401
The equations which transform arbitrary integrals between sequential images are expressed as a function of the displacement field and intensity changes. The apparent displacement field is then computed by iterative projections onto the solution space of each linearized transformation equation. BibRef

Mahzoun, M.R.[Mohammad Reza], Kim, J.W.[Jin-Woo], Sawazaki, S.[Satoru], Okazaki, K.[Kozo], Tamura, S.[Shinichi],
A scaled multigrid optical flow algorithm based on the least RMS error between real and estimated second images,
PR(32), No. 4, April 1999, pp. 657-670.
WWW Version. BibRef 9904

Yacoob, Y.[Yaser], Davis, L.S.[Larry S.],
Temporal Multi-Scale Models for Flow and Acceleration,
IJCV(32), No. 2, September 1999, pp. 147-163.
WWW Version. BibRef 9909
Earlier: CVPR97(921-927).
IEEE Abstract.
WWW Version. 9704
Image acceleration. See also Learned Models for Estimation of Rigid and Articulated Human Motion from Stationary or Moving Camera. BibRef

Yacoob, Y.[Yaser], Davis, L.S.[Larry S.],
Temporal Multi-Scale Models for Image Motion Estimation,
DARPA97(135-142). BibRef 9700

Yacoob, Y.[Yaser], and Davis, L.S.[Larry S.],
Estimating Image Motion Using Temporal Multi-Scale Optical Flow and Acceleration,
MBR97(Chapter 2) Maryland. BibRef 9700

Kim, J.D.[Jong Dae], Mitra, S.K.[Sanjit K.],
A local relaxation method for optical flow estimation,
SP:IC(11), No. 1, November 1997, pp. 21-38.
WWW Version. BibRef 9711

Cohen, I.[Isaac], Herlin, I.[Isabelle],
Non Uniform Multiresolution Method for Optical Flow and Phase Portrait Models: Environmental Applications,
IJCV(33), No. 1, September 1999, pp. 29-49.
WWW Version. BibRef 9909
Earlier:
Optical Flow and Phase Portrait Methods for Environmental Satellite Image Sequences,
ECCV96(II:141-150).
Springer DOI Link BibRef
And: INRIARR 2819, March 1996.
HTML Version. BibRef
And:
A Motion Computation and Interpretation Framework for Oceanographic Satellite Images,
SCV95(13-18).
IEEE Top Reference.
HTML Version. INRIA. Regularization. Adaptive mesh for computations. BibRef

Herlin, I.[Isabelle], Cohen, I.[Isaac], and Bouzidi, S.[Sonia],
Detection and Tracking of Vortices on Oceanographic Images,
SCIA95(xx). BibRef 9500

Cohen, I.[Isaac],
Nonlinear Variational Method for Optical Flow Computation,
SCIA93(523-530). BibRef 9300

Alvarez, L.[Luis], Weickert, J.[Joachim], Sánchez, J.[Javier],
Reliable Estimation of Dense Optical Flow Fields with Large Displacements,
IJCV(39), No. 1, August 2000, pp. 41-56.
WWW Version. 0008
BibRef
Earlier:
A Scale-Space Approach to Nonlocal Optical Flow Calculations,
ScaleSpace99(235-246). See also Dense Disparity Map Estimation Respecting Image Discontinuities: A PDE and Scale-Space Based Approach. BibRef

Alvarez, L.[Luis], Deriche, R.[Rachid], Papadopoulo, T.[Théo], Sánchez, J.[Javier],
Symmetrical Dense Optical Flow Estimation with Occlusions Detection,
IJCV(75), No. 3, December 2007, pp. 371-385.
Springer DOI Link 0710
BibRef
Earlier: ECCV02(I: 721 ff.).
HTML Version. 0205
BibRef

Kim, J.D.[Jong-Dae], Kim, J.W.[Jong-Won],
Effective nonlinear approach for optical flow estimation,
SP(81), No. 10, October 2001, pp. 2249-2252.
HTML Version. 0110
BibRef

Wu, Y.T.[Yu-Te], Kanade, T.[Takeo], Li, C.C.[Ching-Chung], Cohn, J.F.[Jeffrey F.],
Image Registration Using Wavelet-Based Motion Model,
IJCV(38), No. 2, July 2000, pp. 129-152.
WWW Version. 0008
BibRef

Wu, Y.T.[Yu-Te], Kanade, T.[Takeo], Cohn, J.F.[Jeffrey F.], and Li, C.C.[Ching-Chung],
Optical Flow Estimation Using Wavelet Motion Model,
ICCV98(992-998).
IEEE DOI Link
PDF Version. BibRef 9800

Lefébure, M.[Martin], Cohen, L.D.[Laurent D.],
Image Registration, Optical Flow and Local Rigidity,
JMIV(14), No. 2, March 2001, pp. 131-147.
WWW Version.
PDF Version. 0106
BibRef
And: ScaleSpace01(xx-yy).
Postscript Version. 0106
BibRef
Earlier:
A Multiresolution Algorithm for Signal and Image Registration,
ICIP97(III: 252-255).
IEEE DOI Link BibRef

Lefébure, M.[Martin], Cohen, L.D.[Laurent D.],
Optical Flow and Image Registration: A New Local Rigidity Approach for Global Minimization,
EMMCVPR01(592-607).
Springer DOI Link 0205
BibRef

Irani, M.[Michal],
Multi-Frame Correspondence Estimation Using Subspace Constraints,
IJCV(48), No. 3, July-August 2002, pp. 173-194.
WWW Version. 0207
BibRef
Earlier:
Multi-Frame Optical Flow Estimation using Subspace Constraints,
ICCV99(626-633).
IEEE DOI Link Multi-frame constraints used to constrain the 2D correspondence. Variety of imaging models. See also Multiview Constraints on Homographies. BibRef

Garbe, C.S.[Christoph S.], Spies, H.[Hagen], Jähne, B.[Bernd],
Estimation of Surface Flow and Net Heat Flux from Infrared Image Sequences,
JMIV(19), No. 3, November 2003, pp. 159-174.
WWW Version. 0310
BibRef
Earlier:
Mixed OLS-TLS for the Estimation of Dynamic Processes with a Linear Source Term,
DAGM02(463 ff.).
HTML Version. 0303
BibRef

Kondermann, C.[Claudia], Mester, R.[Rudolf], Garbe, C.S.[Christoph S.],
A Statistical Confidence Measure for Optical Flows,
ECCV08(III: 290-301).
Springer DOI Link 0810
BibRef

Kondermann, C.[Claudia], Kondermann, D.[Daniel], Jähne, B.[Bernd], Garbe, C.S.[Christoph S.],
An Adaptive Confidence Measure for Optical Flows Based on Linear Subspace Projections,
DAGM07(132-141).
Springer DOI Link 0709
BibRef

Andres, B.[Björn], Hamprecht, F.A.[Fred A.], Garbe, C.S.[Christoph S.],
Selection of Local Optical Flow Models by Means of Residual Analysis,
DAGM07(72-81).
Springer DOI Link 0709
BibRef

Berkels, B.[Benjamin], Kondermann, C.[Claudia], Garbe, C.S.[Christoph S.], Rumpf, M.[Martin],
Reconstructing Optical Flow Fields by Motion Inpainting,
EMMCVPR09(388-400).
Springer DOI Link 0908
BibRef

Kondermann, C.[Claudia], Kondermann, D.[Daniel], Garbe, C.[Christoph],
Postprocessing of Optical Flows Via Surface Measures and Motion Inpainting,
DAGM08(xx-yy).
Springer DOI Link 0806
BibRef

Andres, B.[Bjorn], Kondermann, C.[Claudia], Kondermann, D.[Daniel], Kothe, U.[Ullrich], Hamprecht, F.A.[Fred A.], Garbe, C.S.[Christoph S.],
On errors-in-variables regression with arbitrary covariance and its application to optical flow estimation,
CVPR08(1-6).
IEEE DOI Link 0806
BibRef

Bruhn, A.[Andrés], Weickert, J.[Joachim], Schnörr, C.[Christoph],
Lucas/Kanade Meets Horn/Schunck: Combining Local and Global Optic Flow Methods,
IJCV(61), No. 3, February-March 2005, pp. 211-231.
WWW Version. 0412
BibRef
Earlier:
Combining the Advantages of Local and Global Optic Flow Methods,
DAGM02(454 ff.).
HTML Version. 0303
BibRef

Gong, H.F.[Hai-Feng], Pan, C.H.[Chun-Hong], Yang, Q.[Qing], Lu, H.Q.[Han-Qing], Ma, S.D.[Song-De],
Generalized optical flow in the scale space,
CVIU(105), No. 1, January 2007, pp. 86-92.
WWW Version. 0701
Scale space; Optical flow; Segmentation; Filtering BibRef

Chamorro-Martínez, J.[Jesús], Fernndez-Valdivia , J.,
A New Approach to Motion Pattern Recognition and Its Application to Optical Flow Estimation,
SMC-C(37), No. 1, January 2007, pp. 39-51.
IEEE DOI Link 0701
BibRef

Legrand, L., Dipanda, A., Marzani, F., Kardouchi, M.[Mustapha],
Using Fourier local magnitude in adaptive smoothness constraints in motion estimation,
PRL(28), No. 9, 1 July 2007, pp. 1019-1028.
WWW Version. 0704
Motion estimation; Optical flow; Motion discontinuities; Fourier transform; Markov random fields BibRef

Ring, D., Pitie, F.,
Feature-Assisted Sparse to Dense Motion Estimation Using Geodesic Distances,
IMVIP09(7-12).
IEEE DOI Link 0909
BibRef

Denman, S.[Simon], Fookes, C.[Clinton], Sridharan, S.[Sridha],
Improved Simultaneous Computation of Motion Detection and Optical Flow for Object Tracking,
DICTA09(175-182).
IEEE DOI Link 0912
BibRef

Niu, Y., Dick, A., Brooks, M.J.,
A new combination of local and global constraints for optical flow computation,
IVCNZ08(1-6).
IEEE DOI Link 0811
BibRef

Wilson, R.G.[Roland G.], Bowen, A.[Adam], Mullins, A.[Andrew], Rajpoot, N.[Nasir],
Estimation of a 3D motion field from a multi-camera array using a multiresolution Gaussian mixture model,
M2SFA208(xx-yy). 0810
BibRef

Wilson, R., Calway, A.D.,
Multiresolution Gaussian Mixture Models for Visual Motion Estimation,
ICIP01(II: 921-924).
IEEE Abstract. 0108
BibRef

Wilson, R.[Ronald],
MGMM: Multiresolution Gaussian Mixture Models for Computer Vision,
ICPR00(Vol I: 212-215).
IEEE DOI Link
HTML Version. 0009
BibRef

Ho, H.T.[Huy Tho], Goecke, R.[Roland],
Optical flow estimation using Fourier Mellin Transform,
CVPR08(1-8).
IEEE DOI Link 0806
BibRef

Koppel, D.[Dan], Tsai, C.M.[Chang-Ming], Wang, Y.F.[Yuan-Fang],
Regularizing optical-flow computation using tensor theory and complex analysis,
Tensor08(1-6).
IEEE DOI Link 0806
BibRef

Li, J.[Jian], Benton, C.P.[Christopher P.], Nikolov, S.G.[Stavri G.], Scott-Samuel, N.E.[Nicholas E.],
Adaptive Multiscale Optical Flow Estimation,
ICIP07(II: 509-512).
IEEE DOI Link 0709
BibRef

Florack, L.M.J.[Luc M.J.], Janssen, B.[Bart], Kanters, F.M.W.[Frans M.W.], Duits, R.[Remco],
Towards a New Paradigm for Motion Extraction,
ICIAR06(I: 743-754).
Springer DOI Link 0610
BibRef

van Dorst, P.[Pieter], Janssen, B.J.[Bart J.], Florack, L.M.J.[Luc M.J.], ter Haar Romeny, B.M.[Bart M.],
Optic Flow Using Multi-scale Anchor Points,
CAIP09(1104-1112).
Springer DOI Link 0909
BibRef

Janssen, B.J., Florack, L.M.J., Duits, R., ter Haar Romeny, B.M.,
Optic Flow from Multi-scale Dynamic Anchor Point Attributes,
ICIAR06(I: 767-779).
Springer DOI Link 0610
BibRef

Alvino, C., Tannenbaum, A., Yezzi, A.J., Curry, C.,
Multigrid Computation of Rotationally Invariant Non-Linear Optical Flow,
ICIP05(III: 1296-1299).
IEEE DOI Link 0512
BibRef

Yang, L.X.[Li-Xin], Sahli, H.,
A Nonlinear Multigrid Diffusion Model for Efficient Dense Optical Flow estimation,
ICIP05(I: 149-152).
IEEE DOI Link 0512
BibRef

Ramírez-Manzanares, A.[Alonso], Rivera, M.[Mariano], Kornprobst, P.[Pierre], Lauze, F.[François],
A Variational Approach for Multi-valued Velocity Field Estimation in Transparent Sequences,
SSVM07(227-238).
Springer DOI Link 0705
BibRef

Lauze, F., Kornprobst, P., Memin, E.,
A Course to Fine Multiscale Approach for Linear Least Squares Optical Flow Estimation,
BMVC04(xx-yy).
HTML Version. 0508
BibRef

Li, M., Kambhamettu, C., Stone, M.,
A General Framework for 2D Multiframe and 3D Surface-to-surface Motion Estimation,
BMVC04(xx-yy).
HTML Version. 0508
BibRef

Teng, C.H.[Chin-Hung], Lai, S.H.[Shang-Hong], Chen, Y.S.[Yung-Sheng], Hsu, W.H.[Wen-Hsing],
An accurate and adaptive optical flow estimation algorithm,
ICIP04(III: 1839-1842).
IEEE DOI Link 0505
BibRef

Adachi, E., Horiguchi, S.,
Multi-resolutional optical flow estimation with local optimization,
ICIP02(II: 257-260).
IEEE Abstract. 0210
BibRef

Wang, H.Y.[Hai-Yan], Ma, K.K.[Kai-Kuang],
Automatic video object segmentation via 3D structure tensor,
ICIP03(I: 153-156).
IEEE Abstract. 0312
BibRef
Earlier:
Accurate optical flow estimation using adaptive scale-space and 3d structure tensor,
ICIP02(II: 301-304).
IEEE Abstract. 0210
BibRef

Pedersen, K.S.[K. Steenstrup], Nielsen, M.,
Computing optic flow by scale-space integration of normal flow,
ScaleSpace01(xx-yy). 0106
BibRef

Maas, R.[Robert], ter Haar Romeny, B.M.[Bart M.], Viergever, M.A.[Max A.],
A Multiscale Taylor Series Approaches to Optic Flow and Stereo: A Generalization of Optic Flow Under the Aperture,
ScaleSpace99(519-524). BibRef 9900

George, M., Tjahjadi, T.,
Multiresolution Optical Flow Estimation using Adaptive Shifting,
ICIP99(III:717-721).
IEEE Abstract. BibRef 9900

Mendelsohn, J.[Jeffrey], Simoncelli, E.[Eero], Bajcsy, R.[Ruzena],
Discrete-time rigidity-constrained optical flow,
CAIP97(255-262).
WWW Version. 9709

HTML Version. And full paper:
Postscript Version. Structure from optic flow. BibRef

Johannesson, M., and Gokstorp, M.,
Video-rate Pyramid Optical Flow Computations on the Linear SIMD Array IVP,
CAMP95(xx). BibRef 9500

Gokstorp, M., Danielsson, P.E.,
Velocity tuned generalized Sobel operators for multiresolution computation of optical flow,
ICIP94(II: 765-769).
IEEE DOI Link 9411
BibRef

Colombo, C., del Bimbo, A., Santini, S.,
A Multilayer Massively Parallel Architecture for Optical Flow Computation,
ICPR92(IV:209-213).
IEEE DOI Link BibRef 9200

Bernard, C.,
Discrete Wavelet Analysis: A New Framework for Fast Optic Flow Computation,
ECCV98(II: 354).
WWW Version. BibRef 9800

Ríos, H.[Homero],
Computing image flow using a coarse-to-fine strategy for spatiotemporal filters,
CAIP93(355-362).
Springer DOI Link 9309
BibRef

Kories, R., Rehfeld, N., Zimmermann, G.,
Towards Autonomous Convoy Driving: Recognizing the Starting Vehicle in Front,
ICPR88(I: 531-535).
IEEE DOI Link
IEEE Top Reference. BibRef 8800

Kories, R., and Zimmermann, G.,
A Versatile Method for the Estimation of Displacement Vector Fields from Image Sequences,
Motion86(101-106). See also Investigation of Multigrid Algorithms for the Estimation of Optical Flow Fields in Image Sequences. BibRef 8600

Kories, R., Hecker, G., Zimmermann, G.,
On the Precision of a Feature Based Displacement Measurement,
ICPR86(1193-1196). BibRef 8600

Zimmermann, G., Kories, R.,
Image Sequence Processing as an Aid for Three-Dimensional Display,
ICPR86(821-824). BibRef 8600

Kories, R., Zimmermann, G.,
Motion Detection in Image Sequences: An Evaluation of Feature Detectors,
ICPR84(778-780). BibRef 8400
And:
A Class of Stable Feature Extractors for Time-Varying Imagery,
ICPR84(919). BibRef

Korn, A.F.[Axel F.], Kories, R.,
Motion Analysis in Natural Scenes Picked up by a Moving Optical Sensor,
ICPR80(1251-1254). BibRef 8000

Kories, R.,
Determination of Displacement Vector Fields for General Camera Motions,
PRIP81(115-117). BibRef 8100

Bergeron, C., and Dubois, E.,
Parametric Block Estimation of Motion and Application to Temporal Interpolation of Video Sequences,
ICPR90(II: 140-146).
IEEE DOI Link BibRef 9000

Glazer, F.,
Hierarchial Gradient-Based Motion Detection,
DARPA87(733-748). BibRef 8700
Earlier:
Computing Optic Flow,
IJCAI81(644-647). Gradient-based approaches only work with small motions, but is extended by using a hierarchical approach. This seems in keeping with the UMass approach. BibRef

Bandyopadhyay, A.,
A Multiple Channel Model for Perception of Optical Flow,
CVWS84(78-82). BibRef 8400

Burt, P.J., Yen, C., Xy, X.,
Local Correlation Measures for Motion Analysis: A Comparative Study,
PRIP82(269-274). BibRef 8200

Burt, P.J., Yen, C., Xy, X.,
Multi-Resolution Flow - Through Motion Analysis,
CVPR83(246-252). BibRef 8300

Chapter on Optical Flow Field Computations and Use continues in
Real-Time, Parallel Optic Flow Computation .