18.2.2 Optical Flow -- Matching Using Areas

Chapter Contents (Back)
Matching, Areas. Optical Flow, Regions.

Huntsberger, T.L., Jayaramamurthy, S.N.,
Determination of the Optic Flow Field Using the Spatiotemporal Deformation of Region Properties,
PRL(6), 1987, pp. 169-177.
See also Determination of the Optic Flow Field in the Presence of Occlusion. BibRef 8700

Kottke, D.P., Sun, Y.,
Motion Estimation Via Cluster Matching,
PAMI(16), No. 11, November 1994, pp. 1128-1132.
IEEE DOI First cluster according to position and intensity, estimate displacement by matching cluster centers. Compares results to gradient and block matching. BibRef 9411

Mahmoud, S.A., Afifi, M.S., Green, R.J.,
Recognition and Velocity Computation of Large Moving Objects in Images,
ASSP(36), 1988, pp. 1790-1791. BibRef 8800

Chhabra, A.K., Grogan, T.A.,
On Poisson Solvers and Semidirect Methods for Computing Area Based Optical-Flow,
PAMI(16), No. 11, November 1994, pp. 1133-1138.
IEEE DOI BibRef 9411
Earlier: CVPR92(857-860).
IEEE DOI Direct computation of area based optical flow.
See also Direct Analytical Methods for Solving Poisson Equations in Computer Vision Problems. BibRef

Chhabra, A.K., and Grogan, T.A.,
Uniqueness, the Minimum Norm Constraint, and Analog Networks for Optical Flow Along Contours,
ICCV90(80-84).
IEEE DOI BibRef 9000

Chhabra, A.K.,
Fast direct methods for computing optical flow along contours,
ICIP94(II: 242-246).
IEEE DOI 9411
BibRef

Stiller, C.,
Object-Based Estimation Of Dense Motion Fields,
IP(6), No. 2, February 1997, pp. 234-250.
IEEE DOI 9703
BibRef
Earlier:
Object-Based Motion Computation,
ICIP96(I: 913-916).
IEEE DOI BibRef

Ye, M.[Ming], Haralick, R.M., Shapiro, L.G.,
Estimating piecewise-smooth optical flow with global matching and graduated optimization,
PAMI(25), No. 12, December 2003, pp. 1625-1630.
IEEE Abstract. 0401
BibRef
Earlier:
Estimating optical flow using a global matching formulation and graduated optimization,
ICIP02(II: 289-292).
IEEE DOI 0210
Three frame matching with global optimization. Use local and global gradient. BibRef

Ye, M.[Ming], Haralick, R.M.[Robert M.],
Two-Stage Robust Optical Flow Estimation,
CVPR00(II: 623-628).
IEEE DOI 0005
BibRef
And:
Optical Flow Estimation: A Two-Stage Robust Approach,
ICPR00(xx-yy). 0005
BibRef

Ye, M.[Ming], Haralick, R.M.,
Optical Flow from a Least-trimmed Squares Based Adaptive Approach,
ICPR00(Vol III: 1052-1055).
IEEE DOI
IEEE DOI 0009
BibRef

Ye, M.[Ming], Haralick, R.M.[Robert M.],
Local Gradient, Global Matching, Piecewise-Smooth Optical Flow,
CVPR01(II:712-717).
IEEE DOI 0110
BibRef

Ahmadianpour, F.[Farzin], Ahmad, M.O.[M. Omair],
A Fast Algorithm for Motion Estimation Under the Varying Inter-Frame Brightness Characteristics,
GVIP(05), No. V1, December 2004, pp. xx-yy
HTML Version. BibRef 0412

Le Besnerais, G., Champagnat, F.,
B-Spline Image Model for Energy Minimization-Based Optical Flow Estimation,
IP(15), No. 10, October 2006, pp. 3201-3206.
IEEE DOI 0609
BibRef
Earlier:
Dense Optical Flow by Iterative Local Window registration,
ICIP05(I: 137-140).
IEEE DOI 0512
BibRef

Chung, P.C., Huang, C.L., Chen, E.L.,
A region-based selective optical flow back-projection for genuine motion vector estimation,
PR(40), No. 3, March 2007, pp. 1066-1077.
Elsevier DOI 0611
Horn-Schunck optical flow constraint; Motion estimation; Optical flow computation; Region-based matching BibRef

Hu, Y.L.[Yin-Lin], Song, R.[Rui], Li, Y.S.[Yun-Song], Rao, P.[Peng], Wang, Y.L.[Yang-Li],
Highly accurate optical flow estimation on superpixel tree,
IVC(52), No. 1, 2016, pp. 167-177.
Elsevier DOI 1609
Optical flow BibRef

Hu, Y.L.[Yin-Lin], Li, Y.S.[Yun-Song], Song, R.[Rui], Rao, P.[Peng], Wang, Y.L.[Yang-Li],
Minimum barrier superpixel segmentation,
IVC(70), 2018, pp. 1-10.
Elsevier DOI 1804
Superpixels, Minimum barrier distance, Clustering BibRef

Ren, Z.[Zhe], Yan, J.C.[Jun-Chi], Yang, X.K.[Xiao-Kang], Yuille, A.L.[Alan L.], Zha, H.Y.[Hong-Yuan],
Unsupervised learning of optical flow with patch consistency and occlusion estimation,
PR(103), 2020, pp. 107191.
Elsevier DOI 2005
Patch consistency, Optical flow estimation, Occlusion estimation, Unsupervised learning, Deep learning BibRef

Ren, Z.[Zhe], Luo, W.H.[Wen-Han], Yan, J.C.[Jun-Chi], Liao, W.L.[Wen-Long], Yang, X.K.[Xiao-Kang], Yuille, A.L.[Alan L.], Zha, H.Y.[Hong-Yuan],
STFlow: Self-Taught Optical Flow Estimation Using Pseudo Labels,
IP(29), 2020, pp. 9113-9124.
IEEE DOI 2009
Optical imaging, Estimation, Optical variables control, Machine learning, Adaptive optics, Unsupervised learning, unsupervised learning BibRef

Dong, C.[Chong], Wang, Z.S.[Zhi-Sheng], Han, J.M.[Jia-Ming], Xing, C.D.[Chang-Da], Tang, S.F.[Shu-Fang],
A non-local propagation filtering scheme for edge-preserving in variational optical flow computation,
SP:IC(93), 2021, pp. 116143.
Elsevier DOI 2103
Variational optical flow, Median filtering, Propagation filtering, Edge-preserving BibRef


Alhawwary, A.[Ahmed], Mustaniemi, J.[Janne], Heikkilä, J.[Janne],
Patchflow: A Two-stage Patch-based Approach for Lightweight Optical Flow Estimation,
ACCV22(VII:535-551).
Springer DOI 2307
BibRef

Zheng, Z.[Zihua], Nie, N.[Ni], Ling, Z.[Zhi], Xiong, P.F.[Peng-Fei], Liu, J.Y.[Jiang-Yu], Wang, H.[Hao], Li, J.K.[Jian-Kun],
DIP: Deep Inverse Patchmatch for High-Resolution Optical Flow,
CVPR22(8915-8924)
IEEE DOI 2210
Measurement, Correlation, Tracking, Memory management, Estimation, Benchmark testing, Stereo vision, Motion and tracking BibRef

Lee, J.[Junghyup], Kim, D.[Dohyung], Ponce, J.[Jean], Ham, B.[Bumsub],
SFNet: Learning Object-Aware Semantic Correspondence,
CVPR19(2273-2282).
IEEE DOI 2002
establishing a dense flow field between images depicting different instances of the same object. BibRef

Maurer, D.[Daniel], Marniok, N.[Nico], Goldluecke, B.[Bastian], Bruhn, A.[Andrés],
Structure-from-Motion-Aware PatchMatch for Adaptive Optical Flow Estimation,
ECCV18(VIII: 575-592).
Springer DOI 1810
BibRef

Mahato, M., Gedam, S.S.,
Integration of Variational Optical Flow and Surface Splines for Dense Correspondence Estimation of Remotely Sensed Images,
DICTA17(1-8)
IEEE DOI 1804
geophysical image processing, image sequences, matrix algebra, remote sensing, splines (mathematics), stereo image processing, Splines (mathematics) BibRef

Helala, M.A., Qureshi, F.Z.,
Fast Estimation of Large Displacement Optical Flow Using Dominant Motion Patterns Sub-Volume PatchMatch Filtering,
CRV17(64-71)
IEEE DOI 1804
computational complexity, estimation theory, filtering theory, image matching, image motion analysis, image sequences, patch match filtering BibRef

Schuster, T., Wolf, L.B.[Lior B.], Gadot, D.[David],
Optical Flow Requires Multiple Strategies (but Only One Network),
CVPR17(6921-6930)
IEEE DOI 1711
Benchmark testing, Fasteners, Learning systems, Optical imaging, Optical losses, Pipelines, Training BibRef

Gadot, D.[David], Wolf, L.B.[Lior B.],
PatchBatch: A Batch Augmented Loss for Optical Flow,
CVPR16(4236-4245)
IEEE DOI 1612
BibRef

Drayer, B.[Benjamin], Brox, T.[Thomas],
Combinatorial Regularization of Descriptor Matching for Optical Flow Estimation,
BMVC15(xx-yy).
DOI Link 1601
BibRef

Shen, C.D.[Cheng-Dong], Li, S.K.[Si-Kun],
Fast Prediction Mode Decision Algorithm for H.264 Based on Hierarchical Mode Classification Framework,
ISVC06(II: 882-890).
Springer DOI 0611
BibRef

Shen, C.D.[Cheng-Dong], Li, T.J.[Tie-Jun], Li, S.K.[Si-Kun],
A Predictive Direction Guided Fast Motion Estimation Algorithm,
CAIP05(188).
Springer DOI 0509
BibRef

López-Nicolás, G.[Gonzalo], Sagüés, C.[Carlos], Guerrero, J.J.[José J.],
Automatic Matching and Motion Estimation from Two Views of a Multiplane Scene,
IbPRIA05(I:69).
Springer DOI 0509
BibRef

Li, M.[Min], Biswas, M., Kumar, S., Nguyen, T.[Truong],
DCT-based phase correlation motion estimation,
ICIP04(I: 445-448).
IEEE DOI 0505
BibRef

Wu, Y.S.[Yun-Song], Megson, G.[Graham], Nie, Z.G.[Zhen-Gang], Alavi, F.N.,
Linear Hashtable Method Predicted Hexagonal Search Algorithm with Spatial Related Criterion,
SCIA05(1208-1217).
Springer DOI 0506
BibRef

Wu, Y.S.[Yun-Song], Megson, G.[Graham],
Linear Algorithm and Hexagonal Search Based Two-Pass Algorithm for Motion Estimation,
CAIP05(554).
Springer DOI 0509
BibRef
And:
Two-pass hexagonal algorithm with improved hashtable structure for motion estimation,
AVSBS05(564-569).
IEEE DOI 0602
BibRef

Krajsek, K.[Kai], Mester, R.[Rudolf],
Bayesian Model Selection for Optical Flow Estimation,
DAGM07(142-151).
Springer DOI 0709
BibRef
Earlier:
A Maximum Likelihood Estimator for Choosing the Regularization Parameters in Global Optical Flow Methods,
ICIP06(1081-1084). 0610

IEEE DOI BibRef
Earlier:
Signal and Noise Adapted Filters for Differential Motion Estimation,
DAGM05(476).
Springer DOI 0509
BibRef

Cheng, Y.[Yun], Wang, Z.Y.[Zhi-Ying], Dai, K.[Kui], Guo, J.J.[Jian-Jun],
A Fast Motion Estimation Algorithm Based on Diamond and Triangle Search Patterns,
IbPRIA05(I:419).
Springer DOI 0509
BibRef

Yoon, H.S.[Hyo Sun], Lee, G.S.[Guee Sang],
Low Complexity Motion Estimation Based on Spatio-Temporal Correlations and Direction of Motion Vectors,
CAIP03(173-181).
Springer DOI 0311
BibRef

Yoon, K.S.[Kyo-Sun], Lee, G.S.[Guee-Sang],
Motion estimation based on spatio -temporal correlations,
ICIP03(II: 359-362).
IEEE DOI 0312
BibRef

Béréziat, D.[Dominique], Herlin, I.[Isabelle],
Object Based Optical Flow Estimation with an Affine Prior Model,
ICPR00(Vol III: 1048-1051).
IEEE DOI
IEEE DOI 0009
BibRef

Neumann, U., You, S.,
Integration of region tracking and optical flow for image motion estimation,
ICIP98(III: 658-662).
IEEE DOI 9810
BibRef

Lucius, C.[Christian],
Measurement of Motion Deformation in a Sequence of Images,
(In French), M.S.Dissertation, June 1996. gzip-ed Postcript file, 2640386 bytes:
PS File. BibRef 9606

Vlontzos, J.A., and Geiger, D.,
A MRF Approach to Optical Flow Estimation,
CVPR92(853-856).
IEEE DOI First get an adaptive window match, then process for continuity and occlusions. BibRef 9200

Geiger, D., Diamantaras, K.J.,
Occlusion Ambiguities in Motion,
ECCV94(A:175-180).
Springer DOI BibRef 9400

Chapter on Optical Flow Field Computations and Use continues in
Optical Flow Along Contours .


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