18.9.4 Integration over a Sequence

Chapter Contents (Back)
Sequences. Motion, Many Frames. Fusion.

Charnley, D., and Blissett, R.J.,
Surface Reconstruction from Outdoor Image Sequences,
IVC(7), No. 1, February 1989, pp. 10-16.
WWW Version. BibRef 8902

Harris, C.G., Pike, J.M.,
3D positional integration from image sequences,
IVC(6), No. 2, May 1988, pp. 87-90.
WWW Version. BibRef 8805
Earlier: Alvey87(233-236). The points are tracked through the sequence, and their 3D locations are accurately determined by use of Kalman filters. The egomotion of the camera is also determined. BibRef

Hildreth, E.C., and Grzywacz, N.M., Adelson, E.H., and Inada, V.K.,
The Perceptual Buildup of Three-Dimensional Structure from Motion,
PandP(48), No. 1, 1990, pp. 19-26. BibRef 9000
And: MIT AI Memo-1141, August 1989. BibRef

Grzywacz, N.M.[Norberto M.], and Hildreth, E.C.[Ellen C.],
The Incremental Rigidity Scheme for Recovering Structure from Motion: Position vs. Velocity Based Formulations,
MIT AI Memo-845, October 1985.
WWW Version. BibRef 8510

Hildreth, E.C., and Grzywacz, N.M.,
The Incremental Recovery of Structure from Motion: Position vs. Velocity Based Formulations,
Motion86(137-143). This and the Ullman invited talk covered the topic. MIT has now learned that long range methods do not have thesame noise problems as the short range methods. The rigid object assumption is used to limit how much the 3-D model of the object changes from one view to the next, but given no 3-D to begin with, the actual structure is determined. The examples were for simple polygons, and they did not reall show what the input looked like - more a presentation problem. BibRef 8600

Hildreth, E.C.[Ellen C.], Ando, H.[Hiroshi], Andersen, R.[Richard], and Treue, S.[Stefan],
Recovering Three-Dimensional Structure from Motion with Surface Reconstruction,
MIT AI Memo-1314, December 1991. BibRef 9112

Levine, M.D., Nobel, P.B., and Youssef, Y.M.,
Understanding Blood Cell Motion,
CVGIP(21), No. 1, January 1983, pp. 58-84.
WWW Version. BibRef 8301
And:
A Rule-Based System for Characterizing Blood Cell Motion,
ISPDSA83(663-709). BibRef

Choi, K.J.[Kwang-Jin], Park, S.H.[Sang-Hyun], Ko, H.S.[Hyeong-Seok],
Processing Motion Capture Data to Achieve Positional Accuracy,
GMIP(61), No. 5, September 1999, pp. 260-273. BibRef 9909

Aguiar, P.M.Q.[Pedro M.Q.], Moura, J.M.F.[Jose M.F.],
Three-dimensional modeling from two-dimensional video,
IP(10), No. 10, October 2001, pp. 1541-1551.
IEEE DOI Link 0110
BibRef
Earlier:
Image Motion Estimation: Convergence and Error Analysis,
ICIP01(II: 937-940).
IEEE Abstract. 0108
BibRef
Earlier:
A Fast Algorithm for Rigid Structure from Image Sequences,
ICIP99(III:125-129).
IEEE Abstract. BibRef
Earlier:
Video representation via 3D shaped mosaics,
ICIP98(I: 823-827).
IEEE DOI Link 9810
BibRef

Goldberger, J.[Jacob],
Reconstructing camera projection matrices from multiple pairwise overlapping views,
CVIU(97), No. 3, March 2005, pp. 283-296.
WWW Version. 0412
Factorization requires all views, others triplets of views. Only pairs of views required. BibRef

Ji, H.[Hui], Fermuller, C.[Cornelia],
A 3D Shape Constraint on Video,
PAMI(28), No. 6, June 2006, pp. 1018-1023.
IEEE DOI Link 0605
BibRef
Earlier:
Integration of Motion Fields through Shape,
CVPR05(II: 663-669).
IEEE DOI Link 0507
BibRef
Earlier:
Bias in Shape Estimation,
ECCV04(Vol III: 405-416).
WWW Version. 0405
BibRef

Pugeault, N.[Nicolas], Kruger, N.[Norbert],
Temporal accumulation of oriented visual features,
JVCIR(22), No. 2, February 2011, pp. 153-163.
Elsevier DOI Link
WWW Version. 1102
Object model building; Visual representation; Feature tracking; Temporal filtering; Unscented Kalman filtering; Edge features; Multiple hypotheses tracking; Structure from motion BibRef

Pugeault, N., Woergoetter, F., Krueger, N.,
Accumulated Visual Representation for Cognitive Vision,
BMVC08(xx-yy).
PDF Version. 0809
BibRef

Miura, M.[Masato], Arai, J.[Jun], Sasaki, H.[Hisayuki], Okui, M.[Makoto], Okano, F.[Fumio], Yamazaki, J.[Junichi], Sobue, S.I.[Shin-Ichi],
Extracting 3D images from lunar orbiter Kaguya data,
SPIE(Newsroom), March 14, 2011
WWW Version. 1103
Geometric analysis of movies captured by a single high-definition TV camera gives depth to 2D images from space. BibRef


Klopschitz, M.[Manfred], Irschara, A.[Arnold], Reitmayr, G.[Gerhard], Schmalstieg, D.[Dieter],
Robust Incremental Structure from Motion,
3DPVT10(xx-yy).
WWW Version. 1005
BibRef

Sur, F.[Frederic],
Robust Matching in an Uncertain World,
ICPR10(2350-2353).
IEEE DOI Link 1008
BibRef

Bhat, S.K.K.[Srikrishna K.K.], Berger, M.O.[Marie-Odile], Sur, F.[Frederic],
Visual Words for 3D Reconstruction and Pose Computation,
3DIMPVT11(326-333).
IEEE DOI Link 1109
BibRef

Bhat, S.K.K.[Srikrishna K.K.], Berger, M.O.[Marie-Odile], Simon, G.[Gilles], Sur, F.[Frederic],
Transitive Closure Based Visual Words for Point Matching in Video Sequence,
ICPR10(3300-3303).
IEEE DOI Link 1008
BibRef

Stühmer, J.[Jan], Gumhold, S.[Stefan], Cremers, D.[Daniel],
Real-Time Dense Geometry from a Handheld Camera,
DAGM10(11-20).
Springer DOI Link 1009
BibRef

Newcombe, R.A.[Richard A.], Lovegrove, S.J.[Steven J.], Davison, A.J.[Andrew J.],
DTAM: Dense tracking and mapping in real-time,
ICCV11(2320-2327).
IEEE DOI Link 1201
BibRef

Newcombe, R.A.[Richard A.], Davison, A.J.[Andrew J.],
Live dense reconstruction with a single moving camera,
CVPR10(1498-1505).
IEEE DOI Link 1006
BibRef

Gherardi, R.[Riccardo], Farenzena, M.[Michela], Fusiello, A.[Andrea],
Improving the efficiency of hierarchical structure-and-motion,
CVPR10(1594-1600).
IEEE DOI Link 1006
BibRef
Earlier: A2, A3, A1:
Structure-and-motion pipeline on a hierarchical cluster tree,
3DIM09(1489-1496).
IEEE DOI Link 0910
BibRef
And: A2, A3, A1:
SAMANTHA: Structure-and-Motion Pipeline on a Hierarchical Cluster Tree,
Online2010.
WWW Version. How to structure sequence for computation. BibRef

Yamaguchi, T.[Tatsuhisa], Nobuhara, S.[Shohei], Matsuyama, T.[Takashi],
Cell-based object tracking method for 3D shape reconstruction using multi-viewpoint active cameras,
VS09(1306-1313).
IEEE DOI Link 0910
Localized calibration. BibRef

Jiang, Z.H.[Zhu-Han],
Object Modelling in Videos via Multidimensional Features of Colours and Textures,
DICTA09(154-161).
IEEE DOI Link 0912
Model a tracked object by distinctive features. BibRef

Knoblauch, D.[Daniel], Kuester, F.[Falko],
Focused Volumetric Visual Hull with Color Extraction,
ISVC09(II: 208-217).
Springer DOI Link 0911
voxels from moving object. BibRef

Knoblauch, D.[Daniel], Hess-Flores, M.[Mauricio], Duchaineau, M.[Mark], Kuester, F.[Falko],
Factorization of Correspondence and Camera Error for Unconstrained Dense Correspondence Applications,
ISVC09(I: 720-729).
Springer DOI Link 0911
BibRef

Li, C.[Chuan], Zheng, J.J.[Jin-Jin], Dang, C.Y.[Chuang-Yin], Zhou, H.J.[Hong-Jun],
A Method of 3D Reconstruction from Image Sequence,
CISP09(1-5).
IEEE DOI Link 0910
BibRef

Leordeanu, M.[Marius], Collins, R.[Robert],
Unsupervised Learning of Object Features from Video Sequences,
CVPR05(I: 1142-1149).
IEEE DOI Link 0507
Single or multiple objects, change in pose, low res video. Related features tend to move the same. BibRef

Le, H.V.[Ha Vu],
A structure-from-motion method for 3-d reconstruction of moving objects from multiple-view image sequences,
ICIP04(III: 1955-1958).
IEEE DOI Link 0505
BibRef
And:
A Structure-from-Motion Method: Use of Motion in Three-Dimensional Reconstruction of Moving Objects from Multiple-View Image Sequences,
3DPVT04(341-347).
IEEE Abstract. 0412
BibRef

Nguyen, H.V., Hanajík, M.,
3-D scene reconstruction from image sequences,
CAIP95(182-189).
Springer DOI Link 9509
From line segments. BibRef

Weng, J., Cui, Y., Ahuja, N., and Singh, A.,
Integration of Transitory Image Sequences,
CVPR94(966-969).
IEEE Abstract. BibRef 9400

Kim, Y.C., and Price, K.E.,
Multiple Frame Analysis of Translation Dominant Motion,
DARPA90(339-347). BibRef 9000 USC Computer VisionSimple application of multiple frame techniques to extract structure. BibRef

Ferrie, F.P., and Levine, M.D.,
Integrating Information from Multiple Views,
CVWS87(117-122). BibRef 8700
Earlier:
Piecing Together the 3D Shape of Moving Objects: An Overview,
CVPR85(574-584). Generate description, transformations, then the model. Integration of data for 3-D representation. Precursor to his thesis which should be dated about May 1986. BibRef

Altman, E.J., Ahuja, N.,
A Dynamical Systems Approach to Integration in Stereo,
DARPA90(423-427). BibRef 9000

Heel, J.[Joachim],
Temporal Surface Reconstruction,
CVPR91(607-612).
IEEE Abstract. BibRef 9100
And: Longer: MIT AI-TR-1296, May 1991.
WWW Version. BibRef

Heel, J.,
Temporally Integrated Surface Reconstruction,
ICCV90(292-295).
IEEE DOI Link BibRef 9000
And:
Dynamic Motion Vision,
DARPA89(702-713). BibRef
And: SPIE(1192), 1990, pp. 758-769. Using a sequence, predict the depth, predict the motion, use each prediction to estimate the other and update, using Bayesian estimation theory and a Kalman filter. BibRef

Heel, J.[Joachim],
Direct dynamic motion vision,
CRA90(II: 1142-1147). BibRef 9000

Heel, J.[Joachim],
Direct Estimation of Structure and Motion from Multiple Frames,
MIT AI Memo-1190, March 1990.
WWW Version. BibRef 9003

Heel, J., Rao, S.,
Temporal Integration of Visual Surface Reconstruction,
DARPA90(376-382). BibRef 9000

Chapter on Motion Analysis --Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion continues in
Error Analysis of Motion and Structure Computations .


Last update:Feb 8, 2012 at 11:25:05