18.2.7 Discontinuous Optic Flow Computation, Occlusions

Chapter Contents (Back)
Optical Flow, Discontinuous. Optical Flow, Occlusions. Occlusions.

Buxton, B.F., Buxton, H.,
Computation of Optic Flow from the Motion of Edge Features in Image Sequences,
IVC(2), No. 2, May 1984, pp. 59-75.
Elsevier DOI Extension of Marr-Hildreth.
See also Monocular Depth Perception from Optical Flow by Space Time Signal Processing. BibRef 8405

Buxton, B.F., Murray, D.W.,
Optic Flow Segmentation as an Ill-Posed and Maximum Likelihood Problem,
IVC(3), No. 4, November 1985, pp. 163-169.
Elsevier DOI minimum entropy regularization. BibRef 8511

Murray, D.W., Buxton, B.F.,
Reconstructing the Optic Flow Field from Edge Motion: An Examination of Two Different Approaches,
CAIA84(382-388). BibRef 8400

Schunck, B.G.[Brian],
Image Flow Segmentation and Estimation by Constraint Line Clustering,
PAMI(11), No. 10, October 1989, pp. 1010-1027.
IEEE DOI BibRef 8910
Earlier:
Image Flow: Fundamentals and Algorithms,
MU88(23-80). BibRef
And:
Motion Segmentation and Estimation by Constraint Line Filtering,
CVWS84(58-62). Survey, Motion. Motion, Survey. Optical Flow, Evaluation. This papers discusses techniques for image flow analysis with discontinuities in the flow. BibRef

Thompson, W.B., Mutch, K.M., and Berzins, V.B.,
Dynamic Occlusion Analysis in Optical Flow Fields,
PAMI(7), No. 4, July 1985, pp. 374-383. BibRef 8507
Earlier: Univ. of MinnesotaComp. Sci. 84-6, May 1984. An expanded version of: BibRef
Edge Detection in Optical Flow Fields,
AAAI-82(26-29). Edge Detection. The application of the Marr-Hildreth zero crossing technique edge detection to vector fields. Apply the operator to each component then combine them to find 2-d zero-crossings (i.e. zero crossings in one component) - change in the vector of 180 (approx). BibRef

Thompson, W.B.[William B.],
Exploiting Discontinuities in Optical Flow,
IJCV(30), No. 3, December 1998, pp. 163-173.
DOI Link BibRef 9812

Thompson, W.B., Mutch, K.M., and Berzins, V.A.,
Analyzing Object Motion Based on Optical Flow,
ICPR84(791-794). BibRef 8400

Shulman, D., Aloimonos, Y.,
(Non-) Rigid Motion Interpretation: A Regularized Approach,
RoyalP(B-233), 1988, pp. 217-234. BibRef 8800

Shulman, D., and Herve, J.Y.,
Regularization of Discontinuous Flow Fields,
Motion89(81-86). Regularization. BibRef 8900

Mahmoud, S.A.,
Motion Analysis of Multiple Moving Objects Using Hartley Transform,
SMC(21), 1991, pp. 280-287. BibRef 9100

Schnorr, C.,
Determining Optical Flow for Irregular Domains by Minimizing Quadratic Functionals of a Certain Class,
IJCV(6), No. 1, April 1991, pp. 25-38.
Springer DOI Addresses the solution of equations of
See also Determining Optical Flow. and
See also On the Estimation of Optical Flow: Relations between Different Approaches and Some New Results. approaches to optical flow. BibRef 9104

Schnorr, C.,
Computation of Discontinuous Optical Flow by Domain Decomposition and Shape Optimization,
IJCV(8), No. 2, August 1992, pp. 153-165.
Springer DOI BibRef 9208
Earlier: BMVC90(xx-yy).
PDF File. 9009

See also Theoretical Framework for Convex Regularizers in PDE-Based Computation of Image Motion, A. BibRef

Schnorr, C.,
On Functionals with Greyvalue-Controlled Smoothness Terms for Determining Optical Flow,
PAMI(15), No. 10, October 1993, pp. 1074-1079.
IEEE DOI BibRef 9310

Schnorr, C.,
Unique Reconstruction of Piecewise Smooth Images by Minimizing Strictly Convex Nonquadratic Functionals,
JMIV(4), 1994, pp. 189-198. BibRef 9400
Earlier:
Segmentation of Visual Motion by Minimizing Convex Non-Quadratic Functionals,
ICPR94(A:661-663).
IEEE DOI BibRef

Nesi, P.[Paolo],
Variational Approach to Optical-Flow Estimation Managing Discontinuities,
IVC(11), No. 7, September 1993, pp. 419-439.
Elsevier DOI BibRef 9309

Zheng, H.Y., Blostein, S.D.,
An Error-Weighted Regularization Algorithm for Image Motion-Field Estimation,
IP(2), No. 2, April 1993, pp. 246-252.
IEEE DOI BibRef 9304

Namazi, N.M., Lee, C.H.,
Nonuniform Image Motion Estimation from Noisy Data,
ASSP(38), No. 2, February 1990, pp. 364-366. BibRef 9002

Fan, C.M.[Chieh-Min], Namazi, N.M.,
Image motion estimation from blurred and noisy image sequences,
ICIP98(II: 228-232).
IEEE DOI 9810
BibRef
Earlier:
Estimation of image motion parameters using the EM algorithm,
ICIP95(I: 195-198).
IEEE DOI 9510
BibRef

Fan, C.M., Namazi, N.M.,
Simultaneous Motion Estimation and Filtering of Image Sequences,
IP(8), No. 12, December 1999, pp. 1788-1795.
IEEE DOI 9912
BibRef
Earlier: ICIP97(II: 156-159).
IEEE DOI BibRef
Earlier:
Simultaneous Parameter Estimation and Image Segmentation for Image Sequence Coding,
ICASSP96(XX) BibRef
And:
Simultaneous motion parameter estimation and image segmentation using the EM algorithm,
ICIP95(I: 542-545).
IEEE DOI 9510

See also Nonuniform Image Motion Estimation Using Kalman Filtering.
See also Bayes Decision Test for Detecting Uncovered Background and Moving Pixels in Image Sequences, A. BibRef

Namazi, N.M., Lipp, J.I.,
Nonuniform Image Motion Estimation Using the Maximum a Posteriori Principle,
IP(1), No. 4, October 1992, pp. 520-525.
IEEE DOI BibRef 9210

Namazi, N.M., Lipp, J.I.,
Nonuniform Image Motion Estimation in Reduced Coefficient Transformed-Domains,
IP(2), No. 2, April 1993, pp. 236-246.
IEEE DOI BibRef 9304

Namazi, N.M., Penafiel, P.B., Fan, C.M.,
Nonuniform Image Motion Estimation Using Kalman Filtering,
IP(3), No. 5, September 1994, pp. 678-683.
IEEE DOI
See also Simultaneous Motion Estimation and Filtering of Image Sequences. BibRef 9409

Fan, C.M., Namazi, N.M., Penafiel, P.B.,
A New Image Motion Estimation Algorithm Based on the EM Technique,
PAMI(18), No. 3, March 1996, pp. 348-352.
IEEE DOI Expectation-Maximization. Impose, smoothness constraint. Use low-pass property of the motion. DCT representation for motion. BibRef 9603

Namazi, N.M., Foxall, D.W.,
On the Convergence of the Generalized Maximum Likelihood Algorithm for Nonuniform Image Motion Estimation,
IP(1), No. 1, January 1992, pp. 116-119.
IEEE DOI BibRef 9201
And: Correction: IP(1), No. 3, 1992, pp. 440. BibRef

Wu, S.F., Kittler, J.V.,
A Gradient-Based Method For General Motion Estimation And Segmentation,
JVCIR(4), 1993, pp. 25-38. BibRef 9300

Otte, M.[Michael], Nagel, H.H.[Hans-Hellmut],
Estimation of Optical-Flow Based on Higher-Order Spatiotemporal Derivatives in Interlaced and Noninterlaced Image Sequences,
AI(78), No. 1-2, October 1995, pp. 5-43.
Elsevier DOI BibRef 9510
Earlier:
Optical Flow Estimation: Advances and Comparisons,
ECCV94(A:49-60).
Springer DOI BibRef

Nagel, H.H., Socher, G., Kollnig, H., Otte, M.,
Motion Boundary Detection in Image Sequences by Local Stochastic Tests,
ECCV94(B:305-315).
Springer DOI BibRef 9400

Nagel, H.H., Gehrke, A.,
Spatiotemporally Adaptive Estimation and Segmentation of Optical Flow Fields,
ECCV98(II: 86).
Springer DOI BibRef 9800

Middendorf, M.[Markus], Nagel, H.H.[Hans-Hellmut],
Estimation and Interpretation of Discontinuities in Optical Flow Fields,
ICCV01(I: 178-183).
IEEE DOI 0106
BibRef

Huntsberger, T.L., Jayaramamurthy, S.N.,
Determination of the Optic Flow Field in the Presence of Occlusion,
PRL(8), 1988, pp. 325-333.
See also Determination of the Optic Flow Field Using the Spatiotemporal Deformation of Region Properties. BibRef 8800

Reddi, S., Loizou, G.,
First-Order Algorithm with Three Clusters of Optical-Flow Vectors,
IJIST(7), No. 1, Spring 1996, pp. 33-40. BibRef 9600

Chang, M.M., Tekalp, A.M., Sezan, M.I.,
Simultaneous Motion Estimation and Segmentation,
IP(6), No. 9, September 1997, pp. 1326-1333.
IEEE DOI 9709
Optical flow estimation and segmentation. BibRef

Convertino, G., Stella, E., Branca, A., Distante, A.,
Optic Flow Estimation by a Hopfield Neural-Network Using Geometrical Constraints,
MVA(10), No. 3, 1997, pp. 114-122.
Springer DOI 9709
BibRef
Earlier: A3, A1, A2, A4:
A Neural Network for Egomotion Estimation from Optical Flow,
BMVC95(xx-yy).
PDF File. 9509
BibRef

Branca, A., Attolico, G., Stella, E., Distante, A.,
Classification and Segmentation of Vector Flow-Fields Using a Neural-Network,
MVA(10), No. 4, 1997, pp. 174-187.
Springer DOI 9801
BibRef

Sim, D.G., Park, R.H.,
Robust Reweighted MAP Motion Estimation,
PAMI(20), No. 4, April 1998, pp. 353-365.
IEEE DOI 9806
Comparisons with Black/Anandan (
See also Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow-Fields, The. ), Weber/Malik (
See also Rigid-Body Segmentation and Shape-Description from Dense Optical-Flow Under Weak Perspective. ) and Bober/Kittler (
See also Robust Motion Analysis. ). BibRef

Aubert, G., Kornprobst, P.,
A Mathematical Study of the Relaxed Optical Flow Problem in the Space V,
MathAnal(30), No. 6, 1999, pp. 1282-1308.
WWW Link. or:
PS File. BibRef 9900

Kornprobst, P.[Pierre], Deriche, R.[Rachid], Aubert, G.[Gilles],
Image Sequence Analysis via Partial Differential Equations,
JMIV(11), No. 1, September 1999, pp. 5-26.
DOI Link BibRef 9909
Earlier:
Image Sequence Restoration: A PDE-Based Coupled Method for Image Restoration and Motion Segmentation,
ECCV98(II: 548).
Springer DOI BibRef
And: INRIANo. 3308, November 1997.
PS File. BibRef
Earlier:
Image Coupling, Restoration and Enhancement via PDE's,
ICIP97(II: 458-461).
IEEE DOI
PS File. BibRef

Deriche, R., Kornprobst, P., and Aubert, G.,
Optical Flow Estimation While Preserving its Discontinuities: A Variational Approach,
ACCV95(xx-yy).
PS File. BibRef 9500

Beauchemin, S.S.[Steven S.], Barron, J.L.[John L.],
The Frequency Structure of 1D Occluding Image Signals,
PAMI(22), No. 2, February 2000, pp. 200-206.
IEEE DOI 0003
Analysis of the changes along occluding line. BibRef

Beauchemin, S.S.[Steven S.], Barron, J.L.[John L.],
On the Fourier Properties of Discontinuous Motion,
JMIV(13), No. 3, December 2000, pp. 155-172.
DOI Link 0106
BibRef

Martens, H.A.[Harald Aagaard], Reberg, J.O.[Jan Otto],
Method and apparatus for depth modelling and providing depth information of moving objects,
US_Patent6,252,974, Jun 26, 2001
WWW Link. occlusions BibRef 0106

Amiaz, T.[Tomer], Kiryati, N.[Nahum],
Piecewise-Smooth Dense Optical Flow via Level Sets,
IJCV(68), No. 2, June 2006, pp. 111-124.
Springer DOI 0606
Active Contours. BibRef
Earlier:
Dense Discontinuous Optical Flow via Contour-Based Segmentation,
ICIP05(III: 1264-1267).
IEEE DOI 0512
Embed (
See also High Accuracy Optical Flow Estimation Based on a Theory for Warping. ) within a 2 phase active contour model. Piecewise smooth flow fields and crisp boundaries. Apply level set methods. BibRef

Amiaz, T.[Tomer], Lubetzky, E.[Eyal], Kiryati, N.[Nahum],
Coarse to over-fine optical flow estimation,
PR(40), No. 9, September 2007, pp. 2496-2503.
Elsevier DOI 0705
Handle discontinuities. BibRef

Ince, S.[Serdar], Konrad, J.[Janusz],
Occlusion-Aware Optical Flow Estimation,
IP(17), No. 8, August 2008, pp. 1443-1451.
IEEE DOI 0808

See also Occlusion-Aware View Interpolation. BibRef

Brune, C.[Christoph], Maurer, H.[Helmut], Wagner, M.[Marcus],
Detection Of Intensity And Motion Edges Within Optical Flow Via Multidimensional Control,
SIIMS(2), No. 4, 2009, pp. 1190-1210. optical flow; edge detection; partial differential equation constrained optimization; optimal control problem; direct methods
DOI Link 1002
BibRef

Estellers, V.[Virginia], Soatto, S.[Stefano],
Detecting Occlusions as an Inverse Problem,
JMIV(54), No. 2, February 2016, pp. 181-198.
Springer DOI 1602
BibRef

Hadhri, H.[Hela], Vernier, F.[Flavien], Atto, A.M.[Abdourrahmane M.], Trouvé, E.[Emmanuel],
Time-lapse optical flow regularization for geophysical complex phenomena monitoring,
PandRS(150), 2019, pp. 135-156.
Elsevier DOI 1903
Time series, Temporal regularization, Remote/proximal sensing, Natural Outdoor Environment, Tracking BibRef

Zhang, C.X.[Cong-Xuan], Zhou, Z.K.[Zhong-Kai], Chen, Z.[Zhen], Hu, W.M.[Wei-Ming], Li, M.[Ming], Jiang, S.F.[Shao-Feng],
Self-Attention-Based Multiscale Feature Learning Optical Flow With Occlusion Feature Map Prediction,
MultMed(24), 2022, pp. 3340-3354.
IEEE DOI 2207
Optical flow, Estimation, Image motion analysis, Optical losses, Computational modeling, Robustness, Learning optical flow, occlusions BibRef

Wang, Z.[Zige], Chen, Z.[Zhen], Zhang, C.X.[Cong-Xuan], Zhou, Z.K.[Zhong-Kai], Chen, H.[Hao],
LCIF-Net: Local criss-cross attention based optical flow method using multi-scale image features and feature pyramid,
SP:IC(112), 2023, pp. 116921.
Elsevier DOI 2302
Optical flow, Large displacement, Edge-blurring, Image features and feature pyramids, Local criss-cross attention BibRef


Neoral, M.[Michal], Šochman, J.[Jan], Matas, J.G.[Jirí G.],
Continual Occlusion and Optical Flow Estimation,
ACCV18(IV:159-174).
Springer DOI 1906
BibRef

Wang, Y., Yang, Y., Yang, Z., Zhao, L., Wang, P., Xu, W.,
Occlusion Aware Unsupervised Learning of Optical Flow,
CVPR18(4884-4893)
IEEE DOI 1812
Optical imaging, Optical variables control, Adaptive optics, Estimation, Optical computing, Optical losses, Unsupervised learning BibRef

Lao, D.[Dong], Sundaramoorthi, G.[Ganesh],
Extending Layered Models to 3D Motion,
ECCV18(X: 441-457).
Springer DOI 1810
BibRef

Zhu, Y., Newsam, S.,
Learning Optical Flow via Dilated Networks and Occlusion Reasoning,
ICIP18(3333-3337)
IEEE DOI 1809
Estimation, Optical imaging, Convolution, Cognition, Adaptive optics, Benchmark testing, Image reconstruction, Optical flow estimation, occlusion reasoning BibRef

Zhu, Y., Newsam, S.,
DenseNet for dense flow,
ICIP17(790-794)
IEEE DOI 1803
Computer architecture, Estimation, Image reconstruction, Motion estimation, Optical imaging, Semantics, Training, Unsupervised learning BibRef

Kennedy, R.[Ryan], Taylor, C.J.[Camillo J.],
Hierarchically-constrained optical flow,
CVPR15(3340-3348)
IEEE DOI 1510
BibRef
And:
Optical Flow with Geometric Occlusion Estimation and Fusion of Multiple Frames,
EMMCVPR15(364-377).
Springer DOI 1504
BibRef

Yu, S.[Sha], Molloy, D.,
Oriented geodesic distance based non-local regularisation approach for optic flow estimation,
VCIP13(1-7)
IEEE DOI 1402
estimation theory BibRef

Bereziat, D., Herlin, I.,
Non-linear observation equation for motion estimation,
ICIP12(1521-1524).
IEEE DOI 1302
BibRef

Zhang, J.Y.[Jie-Yu], Barron, J.L.[John L.],
Optical Flow at Occlusion,
CRV12(198-205).
IEEE DOI 1207
BibRef

Han, J.Y.[Jun-Yu], Qi, F.[Fei], Shi, G.M.[Guang-Ming],
Gradient sparsity for piecewise continuous optical flow estimation,
ICIP11(2341-2344).
IEEE DOI 1201
BibRef
And:
Enhancing Gradient Sparsity for Parametrized Motion Estimation,
BMVC11(xx-yy).
HTML Version. 1110
Optical flow. BibRef

Sundberg, P.[Patrik], Brox, T.[Thomas], Maire, M.[Michael], Arbelaez, P.[Pablo], Malik, J.[Jitendra],
Occlusion boundary detection and figure/ground assignment from optical flow,
CVPR11(2233-2240).
IEEE DOI 1106
BibRef

Shen, X.H.[Xiao-Hui], Wu, Y.[Ying],
Exploiting sparsity in dense optical flow,
ICIP10(741-744).
IEEE DOI 1009
BibRef
And:
Sparsity model for robust optical flow estimation at motion discontinuities,
CVPR10(2456-2463).
IEEE DOI 1006
BibRef

Chen, F.L.[Fa-Ling], Luo, H.B.[Hai-Bo],
A Robust and Discontinuity-Preserving Approach to Optical Flow Estimation,
CISP09(1-5).
IEEE DOI 0910
BibRef

Ren, X.F.[Xiao-Feng],
Local grouping for optical flow,
CVPR08(1-8).
IEEE DOI 0806
BibRef

Cassisa, C., Simoens, S., Prinet, V.,
Two-Frame Optical Flow Formulation in an Unwarping Multiresolution Scheme,
CIARP09(790-797).
Springer DOI 0911
BibRef

Prinet, V., Cassisa, C., Tang, F.F.,
MRF Modeling for Optical Flow Computation from Multi-Structure Objects,
ICIP06(1093-1096). 0610

IEEE DOI BibRef

Xiao, J.J.[Jiang-Jian], Cheng, H.[Hui], Sawhney, H.S.[Harpreet S.], Rao, C.[Cen], Isnardi, M.A.[Michael A.],
Bilateral Filtering-Based Optical Flow Estimation with Occlusion Detection,
ECCV06(I: 211-224).
Springer DOI 0608
BibRef

Zitnick, C.L.[C. Lawrence], Jojic, N.[Nebojsa], Kang, S.B.[Sing Bing],
Consistent Segmentation for Optical Flow Estimation,
ICCV05(II: 1308-1315).
IEEE DOI 0510
BibRef

Molton, N.D., Davison, A.J., Reid, I.D.,
Locally Planar Patch Features for Real-Time Structure from Motion,
BMVC04(xx-yy).
HTML Version. 0508
BibRef

Lu, M.L.[Min-Long], Deng, Z.W.[Zhi-Wei], Li, Z.N.[Ze-Nian],
Learning Contextual Dependencies for Optical Flow with Recurrent Neural Networks,
ACCV16(IV: 68-83).
Springer DOI 1704
BibRef

Jiang, H.[Hao], Li, Z.N.[Ze-Nian], Drew, M.S.,
Optimizing motion estimation with linear programming and detail-preserving variational method,
CVPR04(I: 738-745).
IEEE DOI 0408
Two images. BibRef

Laurent, N.,
Hierarchical Mesh-based Global Motion Estimation, Including Occlusion Areas Detection,
ICIP00(Vol III: 620-623).
IEEE DOI 0008
BibRef

Guichard, F.[Frederic], Rudin, L.[Lenny],
Accurate Estimation of Discontinuous Optical Flow by Minimizing Divergence Related Functionals,
ICIP96(I: 497-500).
IEEE DOI BibRef 9600

Hebert, T.J., Yang, X.,
A sequential algorithm for motion estimation from point correspondences with intermittent occlusions,
ICIP95(II: 221-224).
IEEE DOI 9510
BibRef

Proesmans, M., Van Gool, L.J., Pauwels, E.J., Oosterlinck, A.,
Determination of Optical Flow and Its Discontinuities Using Non-Linear Diffusion,
ECCV94(B:294-304).
Springer DOI BibRef 9400

Spetsakis, M.E.[Minas E.],
Optical Flow Estimation Using Discontinuity Conforming Filters,
BMVC94(xx-yy).
PDF File. 9409
BibRef

Anandan, P.,
Computing Dense Fields Displacement with Confidence Measures in Scenes Containing Occlusion,
DARPA84(236-246). BibRef 8400

Raghavan, S., Gupta, S., Kanal, L.N.,
Computing Discontinuity-Preserved Image Flow,
ICPR92(I:764-767).
IEEE DOI BibRef 9200

Chapter on Optical Flow Field Computations and Use continues in
Optical Flow -- Hierarchical, Pyramid, Multi-Grid, Multi-Scale Approaches .


Last update:Mar 16, 2024 at 20:36:19