17.5.2 Optical Flow Field -- Multiple Flows, Transparent Layers, Motion Layers

Beck, J.,
Perception of Transparency in Man and Machine,
CVGIP(31), No. 2, August 1985, pp. 127-138. BibRef 8508

Brill, M.H.,
Perception of Transparency in Man and Machine: A Comment on Beck,
CVGIP(35), No. 2, August 1986, pp. 270-271. BibRef 8608

Brill, M.H.,
Physical and Informational Constraints on the Perception of Transparency and Translucency,
CVGIP(28), No. 3, December 1984, pp. 356-362. BibRef 8412

Beck, J.,
The Perception of Transparency: A Reply to Brill,
CVGIP(35), No. 2, August 1986, pp. 272-273. BibRef 8608

Irani, M.[Michal], Rousso, B.[Benny], Peleg, S.[Shmuel],
Computing Occluding and Transparent Motions,
IJCV(12), No. 1, February 1994, pp. 5-16. BibRef 9402
Earlier:
Detecting and Tracking Multiple Moving Objects Using Temporal Integration,
ECCV92(282-287).
WWW Version. Find the dominant object, eliminate it from the data. Find the next one. BibRef

Wang, J.Y.A.[John Y.A.], Adelson, E.H.[Edward H.],
Representing Moving Images with Layers,
IP(3), No. 5, September 1994, pp. 625-638.
WWW Version. BibRef 9409
And: Vismod228, 1993.
HTML Version. and
Postscript Version. BibRef
And: Vismod279, 1994.
HTML Version. and
Postscript Version. Data compression using optic flow. Each layer is an intensity map, with transparancy. Ordered in depth. BibRef

Adelson, E.H.[Edward H.],
Layered Representations for Vision and Video,
RVS95(xx). Mosaicing. BibRef 9500

Wang, J.Y.A., Adelson, E.H., Desai, U.,
Apply Mid-Level Vision Techniques for Video Data Compression and Manipulation,
Vismod263, 1994.
HTML Version. and
Postscript Version. BibRef 9400

Adelson, E.H., Wang, J.Y.A., Niyogi, S.A.,
Mid-level vision: new directions in vision and video,
ICIP94(II: 21-25).
WWW Version. 9411 BibRef

Wang, J.Y.A., and Adelson, E.H.,
Layered Representation for Motion Analysis,
CVPR93(361-366).
IEEE Abstract. IEEE Top Reference. Award, Louguet-Higgins. BibRef 9300
And: Vismod221, 1993.
HTML Version. and
Postscript Version. Optical Flow, Multiple Motion. Estimate affine parameters within a subregion, group the motion estimates to find objects. BibRef

Wang, J.Y.A., Adelson, E.H.,
Spatio-Temporal Segmentation of Video Data,
Vismod262, 1994.
HTML Version. and
Postscript Version. BibRef 9400

Adelson, E.H.[Edward H.], and Weiss, Y.[Yair],
A Unified Mixture Framework for Motion Segmentation: Incorporating Spatial Coherence and Estimating the Number of Models,
CVPR96(321-326).
IEEE Abstract. IEEE Top Reference.
WWW Version. BibRef 9600
And:
Perceptually Organized EM: A Framework for Motion Segmentation That Combines Information about Form and Motion,
Vismod-315, 1995.
HTML Version. and
Postscript Version. BibRef

Darrell, T.J., Pentland, A.P.,
Cooperative Robust Estimation Using Layers of Support,
PAMI(17), No. 5, May 1995, pp. 474-487.
IEEE Abstract. IEEE Top Reference.
WWW Version. BibRef 9505
And: Vismod163, 1991.
HTML Version. and
Postscript Version. Kalman Filter. Segmentation and motion for multiple motions. Regions based on homogeneous motions rather than only on connectivity. BibRef

Darrell, T.J., Pentland, A.P.,
Robust Estimation of a Multi-Layered Motion Representation,
Motion91(173-178). BibRef 9100

Darrell, T.J., and Simoncelli, E.P.,
'Nulling' Filters and the Separation of Transparent Motions,
CVPR93(738-739).
IEEE Abstract. IEEE Top Reference. BibRef 9300
And:
On the Use of Nulling Filters to Separate Transparent Motions,
Vismod-198, 1992.
HTML Version. and
Postscript Version. BibRef
And:
Separation of Transparent Motion into Layers Using Velocity-Tuned Mechanisms,
Vismod-244, 1993.
HTML Version. and
Postscript Version. The different motions are treated as separate layers of smooth motions rather than smoothing across the boundaries or detecting the boundaries. BibRef

Huang, Y.[Yan], Palaniappan, K.[Kannappan], Zhuang, X.H.[Xin-Hua], Cavanaugh, J.E.[Joseph E.],
Optic Flow Field Segmentation and Motion Estimation Using a Robust Genetic Partitioning Algorithm,
PAMI(17), No. 12, December 1995, pp. 1177-1190.
IEEE Abstract. IEEE Top Reference.
WWW Version. The problem is that with multiple motions (or noise), global depth reconstructions do not work. BibRef 9512

Black, M.J., Anandan, P.,
The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow-Fields,
CVIU(63), No. 1, January 1996, pp. 75-104.
WWW Version.
HTML Version. Code:
HTML Version. Code, Optic Flow. BibRef 9601
Earlier:
A Framework for the Robust Estimation of Optical Flow,
ICCV93(231-236).
WWW Version. BibRef
Earlier:
Robust Dynamic Motion Estimation Over Time,
CVPR91(296-302).
IEEE Abstract. IEEE Top Reference.
HTML Version. BibRef
And:
The Robust Estimation of Multiple Motions: Affine and Piecewise-Smooth Flow-Fields,
TR Xerox PARC, December 1993. Motion, Many Frames. Incremental tracking system using multiple resolutions. BibRef

Black, M.J., Anandan, P.,
A Model for the Detection of Motion over Time,
ICCV90(33-37).
WWW Version.
HTML Version. BibRef 9000

Black, M.J.[Michael J.],
Robust Incremental Optical Flow,
Ph.D.Thesis, Yale Univ. September 1992.
HTML Version. BibRef 9209

Black, M.J.[Michael J.], and Anandan, P.,
Constraints for the Early Detection of Discontinuity from Motion,
AAAI-90(1060-1066).
HTML Version. Yale University BibRef 9000

Sharma, R., Aloimonos, Y.,
Early Detection of Independent Motion from Active Control of Normal Image Flow Patterns,
SMC-B(26), No. 1, February 1996, pp. 42-52.
IEEE Top Reference. BibRef 9602

Tian, T.Y.[Tina Yu], Shah, M.[Mubarak],
Motion Estimation and Segmentation,
MVA(9), No. 1, 1996, pp. 32-42.
HTML Version. 9608 BibRef
Earlier:
Motion segmentation and estimation,
ICIP94(II: 785-789).
WWW Version. 9411 BibRef

Tian, T.Y.[Tina Yu], Shah, M.[Mubarak],
Recovering 3D Motion Of Multiple Objects Using Adaptive Hough Transform,
PAMI(19), No. 10, October 1997, pp. 1178-1183.
IEEE Abstract. IEEE Top Reference.
WWW Version. 9710 BibRef
Earlier:
Recovering 3D Motion and Structure of Multiple Objects Using Adaptive Hough Transform,
ICCV95(284-289).
WWW Version.
WWW Version. BibRef
Earlier:
Estimating 3D motion and shape of multiple objects using Hough transform,
ICPR94(A:658-660).
WWW Version. 9410Segment multiple flows using two perspective views and 3D rigidity. Only examine the 2D translation space, but vote in the 5D motion space.. BibRef

Black, M.J.[Michael J.], and Jepson, A.D.[Allan D.],
Estimating Optical-Flow in Segmented Images Using Variable-Order Parametric Models with Local Deformations,
PAMI(18), No. 10, October 1996, pp. 972-986.
IEEE Abstract. IEEE Top Reference.
WWW Version.
HTML Version. 9611Motion of planar regions plus local deformation. See also Design and Use of Linear Models for Image Motion Analysis. BibRef

Ju, S.[Shanon], Black, M.J.[Michael J.], and Jepson, A.D.[Allan D.],
Skin and Bones: Multi-layer, Locally Affine, Optical Flow and Regularization with Transparency,
CVPR96(307-314).
IEEE Abstract. IEEE Top Reference.
WWW Version. BibRef 9600

Ju, X.[Xuan],
Estimating Image Motion in Layers: The 'Skin and Bones' Model,
Ph.D.Thesis, Department of Computer Science, University of Toronto, 1998.
PDF Version. BibRef 9800

Jepson, A.D., and Black, M.J.,
Mixture Models for Optical Flow Computation,
CVPR93(760-761).
IEEE Abstract. IEEE Top Reference. BibRef 9300
And: RBCV-TR-93-44, April 1993.
HTML Version. Transparency, multiple motions. Patch models for motion and video. BibRef

Black, M.J.,
Recursive Non-Linear Estimation of Discontinuous Flow Fields,
ECCV94(A:138-145).
WWW Version. BibRef 9400

Choi, J.G., Kim, S.D.,
Multistage Segmentation of Optical-Flow Field,
SP(54), No. 2, October 1996, pp. 109-118. 9612 BibRef

Szeliski, R.[Richard], Shum, H.Y.[Heung-Yeung],
Motion Estimation With Quadtree Splines,
PAMI(18), No. 12, December 1996, pp. 1199-1210.
IEEE Abstract. IEEE Top Reference.
WWW Version. 9701 BibRef
Earlier: ICCV95(757-763).
WWW Version.
WWW Version. BibRef
And: DEC-CRL-95-1, March, 1995.
HTML Version. Adaptive windows to do multiple flow field computations. BibRef

Milanfar, P.,
Projection-Based, Frequency-Domain Estimation of Superimposed Translational Motions,
JOSA-A(13), No. 11, November 1996, pp. 2151-2162. 9611 BibRef

Milanfar, P.,
Motion from projection: a forward model,
ICIP98(II: 695-699).
WWW Version. 9810 BibRef

Milanfar, P.,
Two-Dimensional Matched Filtering for Motion Estimation,
IP(8), No. 3, March 1999, pp. 438-444.
WWW Version. BibRef 9903

Milanfar, P.,
A Model of the Effect of Image Motion in the Radon Transform Domain,
IP(8), No. 9, September 1999, pp. 1276-1281.
WWW Version. BibRef 9909

Robinson, D.[Dirk], Milanfar, P.[Peyman],
Fast Local and Global Projection-Based Methods for Affine Motion Estimation,
JMIV(18), No. 1, January 2003, pp. 35-54.
WWW Version. 0301 BibRef

Sim, D.G., Park, R.H.,
A Two-Stage Algorithm for Motion Discontinuity-Preserving Optical-Flow Estimation,
CVIU(65), No. 1, January 1997, pp. 19-37. 9702
WWW Version. BibRef

Pei, S.C., Liou, L.G.,
Motion Based Grouping of Optical Flow Fields: The Extrapolation and Subtraction Technique,
IP(6), No. 10, October 1997, pp. 1358-1363.
WWW Version. 9710 BibRef

Bors, A.G.[Adrian G.], Pitas, I.[Ioannis],
Optical-Flow Estimation and Moving Object Segmentation Based on Median Radial Basis Function Network,
IP(7), No. 5, May 1998, pp. 693-702.
WWW Version. 9805 BibRef
Earlier:
Segmentation and estimation of the optical flow,
CAIP95(680-685).
WWW Version. 9509 BibRef

Torr, P.H.S.[Philip H.S.], Szeliski, R.[Richard], Anandan, P.,
An Integrated Bayesian Approach to Layer Extraction from Image Sequences,
PAMI(23), No. 3, March 2001, pp. 297-303.
IEEE Abstract. IEEE Top Reference.
WWW Version. 0103 BibRef
Earlier: ICCV99(983-990).
WWW Version. Model 3D scenes as a collection of approximately planar layers in arbitrary position and orientation. Compute 3D descriptions. Uses a Bayesian version of RANSAC. BibRef

Langley, K., Fleet, D.J., and Hibbard, P.,
Linear and nonlinear transparency in binocular vision,
RoyalP(B-265), 1998, pp. 1837-1845.
HTML Version. BibRef 9800

Argyros, A.A., Trahanias, P.E., Orphanoudakis, S.C.,
Robust Regression for the Detection of Independent 3D Motion by a Binocular Observer,
RealTimeImg(4), No. 2, April 1998, pp. 125-141. 9806 BibRef

Argyros, A.A., Orphanoudakis, S.C.,
Independent 3D Motion Detection Based on Depth Elimination in Normal Flow Fields,
CVPR97(672-677).
IEEE Abstract. IEEE Top Reference.
WWW Version. 97042 cameras. Use depth to separate different motions. BibRef

Argyros, A.A., Lourakis, M.I.A., Trahanias, P.E., and Orphanoudakis, S.C.,
Independent 3D Motion Detection through Robust Regression in Depth Layers,
BMVC96(Poster Session 2). 9608FORTH and University of Crete BibRef

Lourakis, M.I.A.[Manolis I.A.], Argyros, A.A.[Antonis A.], and Orphanoudakis, S.C.[Stelios C.],
Independent 3D Motion Detection Using Residual Parallax Normal Flow Fields,
ICCV98(1012-1017).
WWW Version. BibRef 9800

Torr, P.H.S.[Philip H.S.], Fitzgibbon, A.W.[Andrew W.], Zisserman, A.[Andrew],
The Problem of Degeneracy in Structure and Motion Recovery from Uncalibrated Image Sequences,
IJCV(32), No. 1, August 1999, pp. 27-44.
WWW Version. BibRef 9908
Earlier:
Maintaining Multiple Motion Model Hypotheses over Many Views to Recover Matching and Structure,
ICCV98(485-491).
WWW Version. BibRef

Fitzgibbon, A.W., Zisserman, A.,
Multibody Structure and Motion: 3-D Reconstruction of Independently Moving Objects,
ECCV00(I: 891-906).
WWW Version. 0003
Postscript Version. BibRef

Yu, W.C.[Wei-Chuan], Sommer, G.[Gerald], Beauchemin, S.[Steven], Daniilidis, K.[Kostas],
Oriented Structure of the Occlusion Distortion: Is It Reliable?,
PAMI(24), No. 9, September 2002, pp. 1286-1290.
IEEE Abstract. IEEE Top Reference. Or:
PDF Version. 0209Analysis of multiple motions. Argue that oriented velocity term cannot always work as a reliable feature. ( See also Unified Computational Theory for Motion Transparency and Motion Boundaries Based on Eigenenergy Analysis, A. ). BibRef

Yu, W.C.[Wei-Chuan], Sommer, G.[Gerald], Daniilidis, K.[Kostas],
Three dimensional orientation signatures with conic kernel filtering for multiple motion analysis,
IVC(21), No. 5, 2003, pp. 447-458.
WWW Version. 0304 BibRef
Earlier:
3D-Orientation Signatures with Conic Kernel Filtering for Multiple Motion Analysis,
CVPR01(I:299-306).
IEEE Abstract. IEEE Top Reference. 0110Recover multiple motions. Accumulation based approach. BibRef

Yu, W.C.[Wei-Chuan], Sommer, G.[Gerald], Daniilidis, K.[Kostas],
Multiple motion analysis: in spatial or in spectral domain?,
CVIU(90), No. 2, May 2003, pp. 129-152.
WWW Version. 0307 BibRef

Yu, W.C.[Wei-Chuan], Daniilidis, K.[Kostas], Beauchemin, S.[Steven], Sommer, G.[Gerald],
Detection and Characterization of Multiple Motion Points,
CVPR99(I: 171-177).
IEEE Abstract. IEEE Top Reference.
WWW Version. Or:
Postscript Version. BibRef 9900

Tweed, D.S., Calway, A.D.,
Integrated Segmentation and Depth Ordering of Motion Layers in Image Sequences,
IVC(20), No. 9-10, August 2002, pp. 709-723.
WWW Version. 0208 BibRef
Earlier: BMVC00(xx-yy).
PDF Version. 0009 BibRef
And:
Moving Object Graphs and Layer Extraction from Image Sequences,
BMVC01(Poster Session 1. ).
HTML Version. University of Bristol 0110 BibRef

Toro, J.[Javier], Owens, F.[Frank], Medina, R.[Rubén],
Using known motion fields for image separation in transparency,
PRL(24), No. 1-3, January 2003, pp. 597-605.
HTML Version. 0211 BibRef

Nicolescu, M.[Mircea], Medioni, G.[Gérard],
Layered 4D representation and voting for grouping from motion,
PAMI(25), No. 4, April 2003, pp. 492-501.
IEEE Abstract. IEEE Top Reference. 0304Grouping motion, formulat as 4D problem. Tensor to enforce smoothness. BibRef

Nicolescu, M.[Mircea], Medioni, G.[Gérard],
Perceptual Grouping from Motion Cues Using Tensor Voting in 4-D,
ECCV02(III: 423 ff.).
HTML Version. 0205 BibRef

Nicolescu, M., Medioni, G.,
A Voting-Based Computational Framework for Visual Motion Analysis and Interpretation,
PAMI(27), No. 5, May 2005, pp. 739-752.
IEEE Abstract. IEEE Top Reference. 0501 BibRef
Earlier:
Voting-based grouping and interpretation of visual motion,
Southwest04(211-215).
IEEE Abstract. IEEE Top Reference. 0411 BibRef

Nicolescu, M., Medioni, G.,
Motion segmentation with accurate boundaries: A tensor voting approach,
CVPR03(I: 382-389).
IEEE Abstract. IEEE Top Reference. 0307 BibRef

Nicolescu, M., Medioni, G.,
4-D voting for matching, densification and segmentation into motion layers,
ICPR02(III: 303-308).
WWW Version. 0211 BibRef

Smith, P.A.[Paul A.], Drummond, T.W.[Tom W.], Cipolla, R.[Roberto],
Layered motion segmentation and depth ordering by tracking edges,
PAMI(26), No. 4, April 2004, pp. 479-494.
IEEE Abstract. IEEE Top Reference. 0403 BibRef
Earlier:
Motion Segmentation by Tracking Edge Information over Multiple Frames,
ECCV00(II: 396-410).
WWW Version. 0003
HTML Version.
Postscript Version. BibRef
Earlier:
Edge tracking for motion segmentation and depth ordering,
BMVC99(Movement and Tracking).
HTML Version.
Postscript Version. Bayesian may not be in the title. BibRef

Smith, P.A., Drummond, T.W., Cipolla, R.,
Segmentation of Multiple Motions by Edge Tracking between Two Frames,
BMVC00(xx-yy).
PDF Version. 0009 BibRef

Guo, Q.[Qinghong], Mandal, M.K.[Mrinal K.], Li, M.Y.[Micheal Y.],
Efficient Hodge-Helmholtz decomposition of motion fields,
PRL(26), No. 4, March 2005, pp. 493-501.
WWW Version. 0501 BibRef

Mota, C.[Cicero], Stuke, I.[Ingo], Aach, T.[Til], Barth, E.[Erhardt],
Spatial and spectral analysis of occluded motions,
SP:IC(20), No. 6, July 2005, pp. 529-536.
WWW Version. 0506 BibRef
Earlier: A4, A2, A3, A1:
Spatio-temporal motion estimation for transparency and occlusions,
ICIP03(III: 65-68).
IEEE Abstract. IEEE Top Reference. 0312 BibRef

Barth, E., Stuke, I., Mota, C.,
Analysis of motion and curvature in image sequences,
Southwest02(206-210).
IEEE Top Reference. 0208 BibRef

Mota, C., Stuke, I., Barth, E.,
Analytic Solutions for Multiple Motions,
ICIP01(II: 917-920).
IEEE Abstract. IEEE Top Reference. 0108 BibRef

Xiao, J.J.[Jiang-Jian], Shah, M.[Mubarak],
Motion Layer Extraction in the Presence of Occlusion Using Graph Cuts,
PAMI(27), No. 10, October 2005, pp. 1644-1659.
WWW Version. 0509 BibRef
Earlier: CVPR04(II: 972-979).
IEEE Abstract. IEEE Top Reference. 0408 BibRef

Mrak, M., Sprljan, N., Izquierdo, E.,
Evaluation of Techniques for Modeling of Layered Motion Structure,
ICIP06(1905-1908). 0610
WWW Version. BibRef

Reid, I.D., Connor, K.R.,
Multiview Segmentation and Tracking of Dynamic Occluding Layers,
BMVC05(xx-yy).
HTML Version. 0509 BibRef

Auvray, V., Bouthemy, P., Lienard, J.,
Multiresolution Parametric Estimation of Transparent Motions,
ICIP05(I: 141-144).
WWW Version. 0512 BibRef

Sarel, B.[Bernard], Irani, M.[Michal],
Separating Transparent Layers of Repetitive Dynamic Behaviors,
ICCV05(I: 26-32).
WWW Version. 0510 BibRef
Earlier:
Separating Transparent Layers through Layer Information Exchange,
ECCV04(Vol IV: 328-341).
WWW Version. 0405 BibRef

Chamorro-Martínez, J.[Jesús], Martínez-Baena, J.[Javier], Galán-Perales, E.[Elena], Prados-Suárez, B.[Beén],
Dealing with Multiple Motions in Optical Flow Estimation,
IbPRIA05(I:52).
WWW Version. 0509 BibRef

Jacobs, A.[Arne], Hermes, T.[Thorsten], Herzog, O.[Otthein],
Hybrid Model-Based Estimation of Multiple Non-dominant Motions,
DAGM04(87-94).
WWW Version. 0505 BibRef

Zhang, Y.J.[Yun-Jun], Xiao, J.J.[Jiang-Jian], Shah, M.[Mubarak],
Motion Layer Based Object Removal in Videos,
WACV05(I: 516-521).
WWW Version. 0502 BibRef

Yalcin, H.[Hulya], Black, M.J.[Michael J.], Fablet, R.[Ronan],
The Dense Estimation of Motion and Appearance in Layers,
VideoRegister04(165).
HTML Version. 0502 BibRef

Spies, H.[Hagen], Forssén, P.E.[Per-Erik],
Two-Dimensional Channel Representation for Multiple Velocities,
SCIA03(356-362).
WWW Version. 0310 BibRef

Singh, M., Huang, X.L.[Xiao-Lei],
Computing layered surface representations: an algorithm for detecting and separating transparent overlays,
CVPR03(II: 11-18).
IEEE Abstract. IEEE Top Reference. 0307 BibRef

Ben-Ezra, M., Nayar, S.K.,
What does motion reveal about transparency?,
ICCV03(1025-1032).
WWW Version. 0311 BibRef

Ke, Q.[Qifa], Baker, S., Kanade, T.,
Textureless Layers,
CMU-RI-TR-04-17, March, 2004.
HTML Version. 0501 BibRef

Ke, Q.[Qifa], Kanade, T.,
Transforming camera geometry to a virtual downward-looking camera: robust ego-motion estimation and ground-layer detection,
CVPR03(I: 390-397).
IEEE Abstract. IEEE Top Reference. 0307 BibRef
Earlier:
A robust subspace approach to layer extraction,
Motion02(37-43).
IEEE Abstract. IEEE Top Reference. 0303 BibRef

Langley, K.[Keith],
Degenerate Models of Additive and Multiplicative Motion Transparency,
BMVC97(xx-yy).
HTML Version. 0209 BibRef

Zucchelli, M., Santos-Victor, J., Christensen, H.I.,
Multiple Plane Segmentation Using Optical Flow,
BMVC02(Poster Session). 0208 BibRef

Jepson, A.D., Fleet, D.J., Black, M.J.,
A Layered Motion Representation with Occlusion and Compact Spatial Support,
ECCV02(I: 692 ff.).
HTML Version. 0205 BibRef

Bartolini, F., Cappellini, V., and Tucci, L.,
Simultaneous Optic Flow Estimation and Segmentation by Means of LS Techniques,
ICIP97(I: 97-100).
WWW Version. BibRef 9700

Weiss, Y.[Yair],
Smoothness in Layers: Motion Segmentation Using Nonparametric Mixture Estimation,
CVPR97(520-526).
IEEE Abstract. IEEE Top Reference.
WWW Version. 9704Fit multiple curves/surfaces. BibRef

Wiles, C.S.[Charles Stephen], Brady, M.[Michael],
Closing the Loop on Multiple Motions,
ICCV95(308-313).
WWW Version.
WWW Version. BibRef 9500
And: Ph.D.Thesis. Multiple Motions. Tracking through a sequence, segmentation into multiple motions by clustering trajectories. Uses corner features for tracking. Possible to introduce motion constraints (e.g. ground plane for driving applications) to aid in segmentation. Thesis available.
HTML Version. BibRef

Hsu, S., Anandan, P., Peleg, S.,
Accurate Computation of Optical Flow by Using Layered Motion Representations,
ICPR94(A:743-746).
WWW Version. BibRef 9400

Bergen, J.R.[James R.], Anandan, P., Hanna, K.J., Hingorani, R.[Rajesh],
Hierarchical Model-Based Motion Estimation,
ECCV92(237-252).
WWW Version. BibRef 9200

Shizawa, M.[Masahiko],
On visual ambiguities due to transparency in motion and stereo,
ECCV92(411-419).
WWW Version. 9205 See also Direct Estimation of Multiple Disparities for Transparent Multiple Surfaces in Binocular Stereo. BibRef

Shizawa, M., and Mase, K.,
A Unified Computational Theory for Motion Transparency and Motion Boundaries Based on Eigenenergy Analysis,
CVPR91(289-295).
IEEE Abstract. IEEE Top Reference. BibRef 9100
And:
Principle of Superposition: A Common Computational Framework for Analysis of Multiple Motion,
Motion91(164-172). BibRef
And:
Simultaneous Multiple Optical Flow Estimations,
ICPR90(I: 274-278).
WWW Version. Decompose motions into components and work on each separatelyf. Transparent surfaces with motion. BibRef

Rognone, A., Campani, M., Verri, A.,
Identifying Multiple Motions from Optical Flow,
ECCV92(258-266).
WWW Version. BibRef 9200

Bergen, J.R.[James R.], Burt, P.J.[Peter J.], Hingorani, R.[Rajesh], Peleg, S.[Shmuel],
Transparent-motion analysis,
ECCV90(566-569).
WWW Version. 9004 BibRef

Sadjadi, F.A., Hwang, J.J., Hall, E.L., Roberts, M.J.,
Measurement of Two Phase Flow Velocities Using Image Correlation,
ICPR80(386-392). BibRef 8000

Gose, E.E., Rose, W.H., Barnes, W.E., Kaplan, E., Arnold, J.S.,
Decomposition of Image Sequnces of Overlapping Homogeneous Transparent Radiating Objects,
ICPR80(971-973). BibRef 8000

Chapter on Optical Flow Field Computations and Use continues in
Optical Flow Field -- Information Extraction .