18.6 Optical Flow Field -- Information Extraction

Chapter Contents (Back)

18.6.1 Egomotion or Ego Motion Computation from Flow Fields

Chapter Contents (Back)
Motion, Parameters. Optical Flow, Features. Motion, Observer. Ego Motion. Egomotion. ego-motion.
See also Loop Closure, Simultaneous Localization and Mapping.

Zacharias, G.L., Caglayan, A.K., Sinacori, J.B.,
A Model for Visual Flow-Field Cueing and Self-Motion Estimation,
SMC(15), 1985, pp. 385-389. BibRef 8500

van Doorn, A.J., and Koenderink, J.J.,
Visibility of Movement Gradients,
BioCyber(44), 1982, pp. 167-175. BibRef 8200

Koenderink, J.J., and van Doorn, A.J.,
Affine Structure from Motion,
JOSA-A(8), No. 2, 1991, pp. 377-385. BibRef 9100

Koenderink, J.J., and van Doorn, A.J.,
Invariant Properties of the Motion Parallax Field Due to the Movement of Rigid Bodies Relative to an Observer,
Optica Acta(22), No. 9, 1975, pp. 773-791.
See also Local Structure of Movement Parallax of the Plane. BibRef 7500

Koenderink, J.J., and van Doorn, A.J.,
Exterospecific Component of the Motion Parallax Field,
JOSA(66), 1976, pp. 953-957.
See also Local Structure of Movement Parallax of the Plane. BibRef 7600

Rosenholtz, R.[Ruth], Koenderink, J.J.[Jan J.],
Affine Structure and Photometry,
CVPR96(790-795).
IEEE DOI BibRef 9600

Bruss, A.R.[Anna R.], and Horn, B.K.P.[Berthold K.P.],
Passive Navigation,
CVGIP(21), No. 1, January 1983, pp. 3-20.
Elsevier DOI BibRef 8301
Earlier: DARPA82(204-214). BibRef
And: MIT AI Memo-662, November 1981. A lot of equations to show what can be done with optic flow data. Determine the motion of a body relative to a fixed environment using the changing image seen by the camera attached to the moving body. The optic flow in the image is the input. BibRef

Negahdaripour, S., and Horn, B.K.P.,
Direct Passive Navigation,
PAMI(9), No. 1, January 1987, pp. 168-176. BibRef 8701
Earlier: MIT AI Memo-821, February 1984. BibRef
Earlier:
Direct Passive Navigation: Analytical Solution for Planes,
DARPA85(381-387). BibRef
And: A1 only ?: MIT AI Memo-863, August 1985. Motion of the observer relative to a planar surface using image brightness derivatives. No optical flow is computed, just derivatives at 8 points. BibRef

Negahdaripour, S.[Shahriar], Yuille, A.L.[Alan L.],
Direct Passive Navigation: Analytical Solution for Quadratic Patches,
MIT AI Memo-876, March 1986. BibRef 8603

Negahdaripour, S., Kolagani, N., and Hayashi, B.Y.,
Direct Motion Stereo for Passive Navigation,
CVPR92(425-431).
IEEE DOI Consider axial translation and panning translation, computed from image gradients and time derivatives. Uses stereo image sequences. BibRef 9200

Hayashi, B.Y.,
Direct Motion Stereo: Recovery of Observer Motion and Scene Structure,
ICCV90(446-450).
IEEE DOI BibRef 9000

Negahdaripour, S.,
Motion Recovery from Image Sequences Using Only First Order Optical Flow Information,
IJCV(9), No. 3, 1992, pp. 163-184.
Springer DOI BibRef 9200
Earlier: add A2 Lee, S.,
Motion Recovery from Image Sequences Using First-Order Optical Flow Information,
Motion91(132-139). Use optical flow in two regions to get ego motion. BibRef

Inigo, R.M., McVey, E.S., Berger, B.J., Wirtz, M.J.,
Machine Vision Applied to Vehicle Guidance,
PAMI(6), No. 6, November 1984, pp. 820-826. BibRef 8411

Inigo, R.M., and McVey, E.S.,
Machine vision applied to vehicle guidance and safety,
Conference(469-474). 32nd IEEE Vehicular Technology Conference, 1982, Vol.32.
HTML Version. BibRef 8200

McVey, E.S., Drake, K.C., Inigo, R.M.,
Range Measurements by a Mobile Robot Using a Navigation Line,
PAMI(8), No. 1, January 1986, pp. 105-109. BibRef 8601

Drake, K.C., McVey, E.S., Inigo, R.M.,
Sensing Error for a Mobile Robot Using Line Navigation,
PAMI(7), No. 4, July 1985, pp. 485-490. BibRef 8507

Drake, K.C., McVey, E.S., Inigo, R.M.,
Sensor Roll Angle Error for a Mobile Robot Using a Navigation Line,
PAMI(10), No. 5, September 1988, pp. 727-731.
IEEE DOI BibRef 8809

Drake, K.C., McVey, E.S., Inigo, R.M.,
Experimental Position and Ranging Results for a Mobile Robot,
RA(3), 1987, pp. 31-42. BibRef 8700

Lawton, T.B.[Teri B.],
Method and apparatus for predicting the direction of movement in machine vision,
US_Patent5,109,425, Apr 28, 1992
WWW Link. BibRef 9204

Heeger, D.J., and Jepson, A.D.,
Subspace Methods for Recovering Rigid Motion I: Algorithms and Implementation,
IJCV(7), No. 2, January 1992, pp. 95-117.
Springer DOI BibRef 9201
And: RBCV-TR-90-35, Toronto, November 1990. BibRef
And: A2, A1:
Subspace Methods for Recovering Rigid Motion, Part II: Theory,
RBCV-TR-90-36, Toronto, November 1990. BibRef
And:
Linear Subspace Methods for Recovering Translation Direction,
RBCV-TR-92-40, Toronto, 1992. Depth from optical flow. BibRef

Heeger, D.J.[David J.], Jepson, A.D.[Allan D.],
Method and apparatus for image processing to obtain three dimensional motion and depth,
US_Patent4,980,762, Dec 25, 1990
WWW Link. BibRef 9012

Heeger, D.J., Jepson, A.D.,
Simple Method for Computing 3D Motion and Depth,
ICCV90(96-100).
IEEE DOI BibRef 9000

Heeger, D.J., and Jepson, A.D.,
A Fast Subspace Methods for Recovering Rigid Motion,
Motion91(124-131). Egomotion, recover translation direction, then a linear method to get rotation and depth. BibRef 9100

Heeger, D.J., Hager, G.,
Egomotion and the Stabilized World,
ICCV88(435-440).
IEEE DOI BibRef 8800

Dvornychenko, V.N., Kong, M.S., Soria, S.M.,
Mission Parameters Derived from Optical Flow,
JMIV(2), 1992, pp. 27-38. BibRef 9200

Hummel, R.A., and Sundareswaran, V.,
Motion Parameter Estimation from Global Flow Field Data,
PAMI(15), No. 5, May 1993, pp. 459-476.
IEEE DOI Two iterative algorithms to get the parameters of motion given the flow field. The first is flow circulation, the second is the FOE search algorithm. BibRef 9305

Sundareswaran, V.,
Egomotion from Global Flow Field Data,
Motion91(140-145). Get T and R given the optical flow field. The curl of FF is approximately linear in R. The FoE is at the center of a circle where the line integral of the FF projected on the circle is 0. BibRef 9100

Sundareswaran, V.,
Global Methods for Image Motion Analysis,
Ph.D.October 1992, BibRef 9210 NYU BibRef

Barron, J.L.[John L.],
A Survey of Approaches for Determining Optic Flow, Environmental Layout and Egomotion,
RBCV-TR-84-5, November 1984, Toronto. Survey, Optic Flow. A good survey of motion papers up to 1984, especially the optic flow papers. There are summaries of most of the equations that people use and a lot of diagrams. BibRef 8411

Prazdny, K.,
Ego Motion and a Relative Depth Map from Optical Flow,
BioCyber(36), 1980, pp. 87-102. BibRef 8000
And:
A Simple Method for Recovering Relative Depth Map in the Case of a Translating Sensor,
IJCAI81(698-699). BibRef
And:
Relative Depth and Local Surface Orientation from Image Motions,
DARPA81(47-60). Develop equations to use optical flow to recover rotation and translation direction, orientation of approaching surface. The magnitude of translation is not possible. BibRef

Prazdny, K.,
Determining the Instantaneous Direction of Motion from Optical Flow Generated by a Curvilinearly Moving Observer,
CGIP(17), No. 3, November 1981, pp. 238-248.
Elsevier DOI BibRef 8111
Earlier: DARPA81(14-21). BibRef
And: PRIP81(109-114). Decompose into rotational and translational. Focus of expansion to get translational. BibRef

Prazdny, K.,
Motion and Structure from Optical Flow,
IJCAI79(702-704). BibRef 7900

Prazdny, K.,
Computing Motions of Planar Surfaces from Spatio-Temporal Changes in Image Brightness,
PRIP82(256-258). BibRef 8200

Prazdny, K.,
A Sketch of a (Computational) Theory of Visual Kinesthesis,
HMV83(413-423). BibRef 8300

Rieger, J.H., and Lawton, D.T.,
Determining the Instantaneous Axis of Translation from Optic Flow Generated by Arbitrary Sensor Motion,
Motion83(33-41). BibRef 8300
And: COINSTR 83-1, UMass., January 1983. Method: compute (locally) the difference vectors from optic flow field; Threshold difference vectors; Minimize the angle between the difference vector field. BibRef

Rieger, J.H., and Lawton, D.T.,
Processing Differential Image Motion,
JOSA-A(2), 1985, pp. 254-260. BibRef 8500
Earlier: COINSTR 84-28, 1984. BibRef
Earlier: A2, A1:
The Use of Difference Fields in Processing Sensor Motion,
DARPA83(77-83). Identical paper (different title): BibRef
Sensor Motion and Relative Depth from Difference Fields of Optic Flows,
IJCAI83(1027-1031). Recover the motion of the sensor only. This is about the same as the above report (COINS 83-1). BibRef

Horn, B.K.P., and Weldon, Jr., E.J.,
Direct Methods for Recovering Motion,
IJCV(2), No. 1, June 1988, pp. 51-76.
Springer DOI Pure rotation, pure translation, or general motion with known pure rotation, using first order derivatives of the image. BibRef 8806

Horn, B.K.P., and Weldon, Jr., E.J.,
Computationally-Efficient Methods for Recovering Translational Motion,
ICCV87(2-11). Translation of the observer using a gradient approach. BibRef 8700

Sinclair, D.A., Blake, A., Murray, D.W.,
Robust Estimation of Egomotion from Normal Flow,
IJCV(13), No. 1, September 1994, pp. 57-69.
Springer DOI BibRef 9409
Earlier:
Robust ego-motion estimation,
BMVC90(xx-yy).
PDF File. 9009
BibRef

Duric, Z.[Zoran], Rosenfeld, A., and Davis, L.S.,
Egomotion Analysis Based on the Frenet-Serret Motion Model,
IJCV(15), No. 1-2, June 1995, pp. 105-122.
Springer DOI BibRef 9506
Earlier: ICCV93(703-712).
IEEE DOI
See also Estimating The Heading Direction Using Normal Flow. BibRef

Heeger, D.J., and Jepson, A.D.,
Visual Perception of Three-Dimensional Motion,
NeurComp(2), 1990, pp. 129-137. BibRef 9000

Silva, C.[Cesar], Santos-Victor, J.[Jose],
Robust Egomotion Estimation from the Normal Flow Using Search Subspaces,
PAMI(19), No. 9, September 1997, pp. 1026-1034.
IEEE DOI 9710
BibRef
And:
Egomotion Estimation on a Topological Space,
ICPR98(Vol I: 64-66).
IEEE DOI 9808
BibRef

Silva, C.[César], and Santos-Victor, J.[José],
Egomotion Estimation Using Log-Polar Images,
ICCV98(967-972).
IEEE DOI BibRef 9800

Silva, C.[César], and Santos-Victor, J.[José],
Direct Egomotion Estimation,
ICPR96(I: 702-706).
IEEE DOI 9608
(Inst. de Sistemas e Robotica, P) BibRef

Brooks, M.J.[Michael J.], Chojnacki, W.[Wojciech], Baumela, L.,
Determining the Egomotion of an Uncalibrated Camera from Instantaneous Optical Flow,
JOSA-A(14), No. 10, October 1997, pp. 2670-2677. 9710

See also From FNS to HEIV: A Link Between Two Vision Parameter Estimation Methods. BibRef

Brooks, M.J., Chojnacki, W., van den Hengel, A.J., Baumela, L.,
Robust Techniques for the Estimation of Structure from Motion in the Uncalibrated Case,
ECCV98(I: 281).
Springer DOI BibRef 9800

Irani, M.[Michal], Rousso, B.[Benny], Peleg, S.[Shmuel],
Recovery of Ego-Motion Using Region Alignment,
PAMI(19), No. 3, March 1997, pp. 268-272.
IEEE DOI 9704
BibRef
Earlier:
Recovery of Ego-Motion Using Image Stabilization,
CVPR94(454-460).
IEEE DOI BibRef
Earlier:
Robust recovery of ego-motion,
CAIP93(371-378).
Springer DOI 9309
2D image motion is used to align the image regions, this registration removed the rotation effects. The resulting residual parallax gives the FOE, and thus the ego-translation. Rotation comes from the translation and the 2D image motion. BibRef

Cameron, S., Grossberg, S., Guenther, F.H.,
A Self-Organizing Neural-Network Architecture for Navigation Using Optic Flow,
NeurComp(10), No. 2, February 15 1998, pp. 313-352. 9802
BibRef

Verri, A.[Alessandro], and Trucco, E.[Emanuele],
Finding the Epipole from Uncalibrated Optical Flow,
IVC(17), No. 8, June 1999, pp. 605-609.
Elsevier DOI BibRef 9906
Earlier: ICCV98(987-991).
IEEE DOI BibRef BMVC97(xx-yy).
HTML Version. 0209
projective transform, optical flow at 6 locations. BibRef

Fejes, S.[Sandor], Davis, L.S.[Larry S.],
Detection of Independent Motion Using Directional Motion Estimation,
CVIU(74), No. 2, May 1999, pp. 101-120.
DOI Link BibRef 9905
Earlier: UMD--TR3815, August 1997. Partial Egomotion Estimation. Detection of Moving Objects. Robust Line Fitting. Spatio-Temporal Filtering.
WWW Link. BibRef
Earlier:
Exploring Visual Motion Using Projections of Motion Fields,
DARPA97(113-122). BibRef

Fejes, S.[Sandor], and Davis, L.S.[Larry S.],
What Can Projections of Flow Fields Tell Us About Visual Motion,
ICCV98(979-986).
IEEE DOI BibRef 9800

Fejes, S.[Sandor], Davis, L.S.[Larry S.],
Direction-Selective Filters for Egomotion Estimation,
UMD--CS-TR-3814, July 1997. Egomotion Estimation. Fisher Discriminant. Robust Line Fitting.
PS File. BibRef 9707

Fermüller, C.[Cornelia], Pless, R.[Robert],
The Ouchi Illusion as an Artifact of Biased Flow Estimation,
Vision Research(40), No. 1, 2000, pp. 77-95. BibRef 0001
Earlier: Add A3: Aloimonos, Y.[Yiannis], UMD--TR3917, July 1998
WWW Link.
WWW Link. BibRef

Fermüller, C.[Cornelia], Aloimonos, Y.[Yiannis],
Global Rigidity Constraints in Image Displacement Fields,
ICCV95(245-250).
IEEE DOI Analysis of optical flow. BibRef 9500

Fermüller, C., Alimonos, Y.[Yiannis],
Recognizing 3d Motion,
IJCAI93(1624-1630). BibRef 9300

Fermüller, C.,
Global 3-D Motion Estimation,
CVPR93(415-421).
IEEE DOI BibRef 9300
And:
Motion Constraint Patterns,
WQV93(128-139). BibRef
And: DARPA93(629-640). Find egomotion based on the sign of the normal flow. BibRef

Tzovaras, D., Ploskas, N., Strintzis, M.G.,
Rigid 3-D Motion Estimation Using Neural Networks and Initially Estimated 2-D Motion Data,
CirSysVideo(10), No. 1, February 2000, pp. 158.
IEEE Top Reference. 0003
BibRef

Ploskas, N., Simitopoulos, D., Tzovaras, D., Triantafyllidis, G.A., Strintzis, M.G.,
Rigid and non-rigid 3D motion estimation from multiview image sequences,
SP:IC(18), No. 3, March 2003, pp. 185-202.
Elsevier DOI 0304
BibRef

Demirdjian, D.[David], Horaud, R.[Radu],
Motion-Egomotion Discrimination and Motion Segmentation from Image-Pair Streams,
CVIU(78), No. 1, April 2000, pp. 53-68. 0004

DOI Link Robust techniques. BibRef

Branca, A., Stella, E., Distante, A.,
Passive navigation using egomotion estimates,
IVC(18), No. 10, July 2000, pp. 833-841.
Elsevier DOI 0005
2 state approach, feature matching and egomotion computation. BibRef

Branca, A., Stella, E., Ancona, N., Distante, A.,
Planar Surface Reconstruction using Projective Geometry,
SCIA99(Computer Vision III). BibRef 9900

Chen, Y.S.[Yong-Sheng], Liou, L.G.[Lin-Gwo], Hung, Y.P.[Yi-Ping], Fuh, C.S.[Chiou-Shann],
Three-dimensional ego-motion estimation from motion fields observed with multiple cameras,
PR(34), No. 8, August 2001, pp. 1573-1583.
Elsevier DOI 0105
BibRef

Tsao, A.T., Hung, Y.P., Fuh, C.S., Chen, Y.S.,
Ego Motion Estimation Using Optical Flow Fields Observed from Multiple Cameras,
CVPR97(457-462).
IEEE DOI 9704
BibRef

Harding, C.M.[Cressida M.], Lane, R.G.[Richard G.],
Passive navigation from image sequences by use of a volumetric approach,
JOSA-A(19), No. 2, February 2002, pp. 295-305.
WWW Link. 0202
BibRef

Chiuso, A.[Alessandro], Favaro, P.[Paolo], Jin, H.L.[Hai-Lin], Soatto, S.[Stefano],
Structure from Motion Causally Integrated Over Time,
PAMI(24), No. 4, April 2002, pp. 523-535.
IEEE DOI
PDF File. 0204
BibRef
Earlier:
3-D Motion and Structure from 2-D Motion Causally Integrated over Time: Implementation,
ECCV00(II: 734-750).
Springer DOI 0003
3-D structure in real time from monocular sequence. Prove it is minimal and stable. Handle occlusions. 20-40 high contrast points with small motion relative to sampling.
See also semi-direct approach to structure from motion, A. BibRef

Gurnsey, R., Fleet, D.J., and Potechin, C.,
Second-order motions contribute to vection,
Vision Research(38), No. 18, 1998, pp. 2801-2816.
HTML Version. BibRef 9800

Ota, T.[Takaaki], Schaffer, M.[Mark],
Video motion vector detection including rotation and/or zoom vector generation,
US_Patent6,236,682, May 22, 2001
WWW Link. BibRef 0105

Mandelbaum, R.[Robert], Salgian, G.[Garbis], Sawhney, H.S.[Harpreet Singh],
Method and apparatus for estimating scene structure and ego-motion from multiple images of a scene using correlation,
US_Patent6,307,959, Oct 23, 2001
WWW Link. BibRef 0110
And:
Correlation-based Estimation of Ego-Motion and Structure from Motion and Stereo,
ICCV99(544-550).
IEEE DOI BibRef

Wang, H.[Han], Song, W.L.[Wei-Lin],
Correction of bias for motion estimation algorithms,
PRL(23), No. 13, November 2002, pp. 1505-1514.
Elsevier DOI 0206
Egomotion from epipolar qquations. Minimize error of point from epiploar line. BibRef

Armangué, X.[Xavier], Araújo, H.[Helder], Salvi, J.[Joaquim],
A review on egomotion by means of differential epipolar geometry applied to the movement of a mobile robot,
PR(36), No. 12, December 2003, pp. 2927-2944.
Elsevier DOI 0310
BibRef
Earlier:
Differential epipolar constraint in mobile robot egomotion estimation,
ICPR02(III: 599-602).
IEEE DOI 0211
Restrict to movement on a plane. BibRef

Park, S.C.[Sang-Cheol], Lee, H.S.[Hyoung-Suk], Lee, S.W.[Seong-Whan],
Qualitative estimation of camera motion parameters from the linear composition of optical flow,
PR(37), No. 4, April 2004, pp. 767-779.
Elsevier DOI 0403
BibRef

Escalante-Ramírez, B.[Boris], Silván-Cárdenas, J.L.[José L.],
Advanced modeling of visual information processing: A multi-resolution directional-oriented image transform based on Gaussian derivatives,
SP:IC(20), No. 9-10, October-November 2005, pp. 801-812.
Elsevier DOI 0510
BibRef
Earlier: A2, A1:
Optic-flow Information Extraction with Directional Gaussian-derivatives,
ICPR00(Vol III: 190-193).
IEEE DOI 0009
From Gaussian Derivitave model for early vision. BibRef

Jang, S.W.[Seok-Woo], Pomplun, M.[Marc], Kim, G.Y.[Gye-Young], Choi, H.I.[Hyung-Il],
Adaptive robust estimation of affine parameters from block motion vectors,
IVC(23), No. 14, 12 December 2005, pp. 1250-1263.
Elsevier DOI 0601
BibRef

Mann, R.[Richard], Langer, M.S.[Michael S.],
Spectrum analysis of motion parallax in a 3D cluttered scene and application to egomotion,
JOSA-A(22), No. 9, September 2005, pp. 1717-1731.
WWW Link. 0601
BibRef
Earlier:
Estimating camera motion through a 3D cluttered scene,
CRV04(472-479).
IEEE DOI 0408

See also Optical Snow. BibRef

Pauwels, K.[Karl], van Hulle, M.M.[Marc M.],
Optimal instantaneous rigid motion estimation insensitive to local minima,
CVIU(104), No. 1, October 2006, pp. 77-86.
Elsevier DOI 0609
BibRef
Earlier:
Robust Instantaneous Rigid Motion Estimation,
CVPR05(II: 980-985).
IEEE DOI 0507
Egomotion; Optic flow; Calibrated camera; Local minima; Reweighting Estimation of rigid camera motion from instantaneous velocity measurements. BibRef

Pauwels, K.[Karl], van Hulle, M.M.[Marc M.],
Optic flow from unstable sequences through local velocity constancy maximization,
IVC(27), No. 5, 2 April 2009, pp. 579-587.
Elsevier DOI 0904
BibRef
Earlier:
Optic Flow from Unstable Sequences containing Unconstrained Scenes through Local Velocity Constancy Maximization,
BMVC06(I:397).
PDF File. 0609
Multiscale optic flow; Video stabilization; Phase-based techniques BibRef

Burl, M.C.[Michael Christopher], Pirjanian, P.[Paolo],
Systems and methods for the automated sensing of motion in a mobile robot using visual data,
US_Patent7,162,056, Jan 9, 2007
WWW Link. BibRef 0701

Kim, S.W.[Se Wan], Hong, C.H.[Chan Hee],
Mobile robot using image sensor and method for measuring moving distance thereof,
US_Patent7,171,285, Jan 30, 2007
WWW Link. BibRef 0701

Dong, H., Hsiang, S.M., Smith, J.L.,
An Optimal-Control Model of Vision-Gait Interaction in a Virtual Walkway,
SMC-B(39), No. 1, February 2009, pp. 156-166.
IEEE DOI 0902
Model vision-posture coupling for astronaut locomotion in partial gravity. optical flow stabilization. BibRef

Hu, C.X.[Chuan-Xin], Cheong, L.F.[Loong Fah],
Linear Quasi-Parallax SfM Using Laterally-Placed Eyes,
IJCV(84), No. 1, August 2009, pp. xx-yy.
Springer DOI 0905
BibRef
Earlier:
Linear ego-motion recovery algorithm based on quasi-parallax,
ICIP08(233-236).
IEEE DOI 0810
Visual systems with multiple eyes and little overlap in visual fields. BibRef

Ngo, T.T.[Trung Thanh], Kojima, Y.[Yuichiro], Nagahara, H.[Hajime], Sagawa, R.[Ryusuke], Mukaigawa, Y.[Yasuhiro], Yachida, M.[Masahiko], Yagi, Y.S.[Yasu-Shi],
Real-Time Estimation of Fast Egomotion with Feature Classification Using Compound Omnidirectional Vision Sensor,
IEICE(E93-D), No. 1, January 2010, pp. 152-166.
WWW Link. 1001
BibRef

Ngo, T.T.[Thanh Trung], Nagahara, H.[Hajime], Sagawa, R.[Ryusuke], Mukaigawa, Y.[Yasuhiro], Yachida, M.[Masahiko], Yagi, Y.S.[Yasu-Shi],
Adaptive-Scale Robust Estimator Using Distribution Model Fitting,
ACCV09(III: 287-298).
Springer DOI 0909
BibRef

Alenya, G., Torras, C.,
Camera motion estimation by tracking contour deformation: Precision analysis,
IVC(28), No. 3, March 2010, pp. 474-490.
Elsevier DOI 1001
Egomotion estimation; Active contours; Precision analysis; Unscented transformation BibRef

Hao, J.[Jia], Shibata, T.[Tadashi],
An Ego-Motion Detection System Employing Directional-Edge-Based Motion Field Representations,
IEICE(E93-D), No. 1, January 2010, pp. 94-106.
WWW Link. 1001
BibRef

Yuan, H., Chang, Y., Lu, Z., Ma, Y.,
Model Based Motion Vector Predictor for Zoom Motion,
SPLetters(17), No. 9, September 2010, pp. 787-790.
IEEE DOI 1007
BibRef

Yuan, H., Liu, J., Sun, J., Liu, H., Li, Y.,
Affine Model Based Motion Compensation Prediction for Zoom,
MultMed(14), No. 4, 2012, pp. 1370-1375.
IEEE DOI 1208
BibRef

Raudies, F.[Florian], Neumann, H.[Heiko],
A review and evaluation of methods estimating ego-motion,
CVIU(116), No. 5, May 2012, pp. 606-633.
Elsevier DOI 1203
Survey, Ego-Motion. BibRef
And:
An Efficient Linear Method for the Estimation of Ego-Motion from Optical Flow,
DAGM09(11-20).
Springer DOI 0909
Ego-motion estimation; Visual motion field; Robust estimators; Optic flow; Random sample consensus; m-Functions; Hough transform; Statistical bias; Consistency; Gaussian noise; Outlier noise BibRef

Pradeep, V.[Vivek], Lim, J.W.[Jong-Woo],
Egomotion Estimation Using Assorted Features,
IJCV(98), No. 2, June 2012, pp. 202-216.
WWW Link. 1204
BibRef
Earlier:
Egomotion using assorted features,
CVPR10(1514-1521).
IEEE DOI 1006
BibRef

Sung, C.H.[Chang-Hun], Chung, M.J.[Myung Jin],
Multi-Scale Descriptor for Robust and Fast Camera Motion Estimation,
SPLetters(20), No. 7, 2013, pp. 725-728.
IEEE DOI 1307
multiscale descriptor BibRef

Onkarappa, N.[Naveen], Sappa, A.D.[Angel Domingo],
Speed and Texture: An Empirical Study on Optical-Flow Accuracy in ADAS Scenarios,
ITS(15), No. 1, February 2014, pp. 136-147.
IEEE DOI 1403
BibRef
Earlier:
Laplacian Derivative Based Regularization for Optical Flow Estimation in Driving Scenario,
CAIP13(II:483-490).
Springer DOI 1311
BibRef

Onkarappa, N.[Naveen],
Optical Flow in Driver Assistance Systems,
ELCVIA(13), No. 2, 2014, pp. xx-yy.
DOI Link 1407
Ph.D.. Thesis. BibRef

Choi, M.K.[Min-Kook], Park, J.[Joonseok], Lee, S.C.[Sang-Chul],
Event classification for vehicle navigation system by regional optical flow analysis,
MVA(25), No. 3, April 2014, pp. 547-559.
WWW Link. 1404
BibRef

Yuan, D.[Ding], Liu, M.[Miao], Yin, J.[Jihao], Hu, J.K.[Jian-Kun],
Camera motion estimation through monocular normal flow vectors,
PRL(52), No. 1, 2015, pp. 59-64.
Elsevier DOI 1412
Camera motion estimation BibRef

Bastanlar, Y.L.[Ya-Lin],
Reduced egomotion estimation drift using omnidirectional views,
ELCVIA(13), No. 3, 2014, pp. xx-yy.
DOI Link 1505
BibRef

Uhm, T.[Taeyoung], Ryu, M.S.[Min-Soo], Park, J.I.[Jong-Il],
Fine-Motion Estimation Using Ego/Exo-Cameras,
ETRI(37), No. 4, August 2015, pp. 766-771.
DOI Link 1511
BibRef

Jayaraman, D.[Dinesh], Grauman, K.[Kristen],
Learning Image Representations Tied to Egomotion from Unlabeled Video,
IJCV(125), No. 1-3, December 2018, pp. 136-161.
Springer DOI 1711
BibRef
Earlier:
Learning Image Representations Tied to Ego-Motion,
ICCV15(1413-1421)
IEEE DOI 1602
How images and objects behave with egomotion. Cameras BibRef

Ramakrishnan, S.K.[Santhosh K.], Jayaraman, D.[Dinesh], Grauman, K.[Kristen],
An Exploration of Embodied Visual Exploration,
IJCV(129), No. 5, May 2021, pp. 1616-1649.
Springer DOI 2105
BibRef

Gao, R.H.[Ruo-Han], Jayaraman, D.[Dinesh], Grauman, K.[Kristen],
Object-Centric Representation Learning from Unlabeled Videos,
ACCV16(V: 248-263).
Springer DOI 1704
BibRef

Gee, T.[Trevor], Gong, R.[Rui], Delmas, P.[Patrice], Gimel'farb, G.L.[Georgy L.],
Robust Tracking in Weakly Dynamic Scenes,
ACIVS17(301-312).
Springer DOI 1712
Inter-frame motion of a free-moving camera. Static and dynamic objects. BibRef

Dehghani, M.[Mehdi], Kharrati, H.[Hamed], Seyedarabi, H.[Hadi], Baradarannia, M.[Mahdi],
Improvement of angular velocity and position estimation in gyro-free inertial navigation based on vision aid equipment,
IET-CV(12), No. 3, April 2018, pp. 261-275.
DOI Link 1804
BibRef

Liu, L., Li, H., Dai, Y., Pan, Q.,
Robust and Efficient Relative Pose With a Multi-Camera System for Autonomous Driving in Highly Dynamic Environments,
ITS(19), No. 8, August 2018, pp. 2432-2444.
IEEE DOI 1808
Cameras, Robustness, Heuristic algorithms, Vehicle dynamics, Motion estimation, Pose estimation, Road vehicles, conjugate motion BibRef

Liu, Y.[Yu], Shen, J.B.[Jian-Bing], Wang, W.G.[Wen-Guan], Sun, H.Q.[Han-Qiu], Shao, L.[Ling],
Better Dense Trajectories by Motion in Videos,
Cyber(49), No. 1, January 2019, pp. 159-170.
IEEE DOI 1901
Trajectory, Videos, Tracking, Color, Optical imaging, Integrated optics, Motion segmentation, Boundaries, motion, video BibRef

Kesana, V.[Varun], Okade, M.[Manish],
Compressed domain zoom motion classification using local tetra patterns,
SIViP(13), No. 5, July 2019, pp. 879-885.
Springer DOI 1906
BibRef

Chermak, L.[Lounis], Aouf, N.[Nabil], Richardson, M.[Mark], Visentin, G.[Gianfranco],
Real-time smart and standalone vision/IMU navigation sensor,
RealTimeIP(16), No. 4, August 2019, pp. 1189-1205.
Springer DOI 1908
standalone, multi-platform stereo vision/IMU-based navigation system, providing ego-motion estimation. BibRef

Li, C.T.[Chu-Tak], Siu, W.C.[Wan-Chi], Lun, D.P.K.[Daniel P.K.],
Semi-Supervised Deep Vision-Based Localization Using Temporal Correlation Between Consecutive Frames,
ICIP19(1985-1989)
IEEE DOI 1910
Egomotion analysis. Visual localization, temporal correlation, scene recognition, autonomous driving, deep learning BibRef

Yoon, J.S.[J. Shin], Kim, K., Gallo, O., Park, H.S., Kautz, J.,
Novel View Synthesis of Dynamic Scenes With Globally Coherent Depths From a Monocular Camera,
CVPR20(5335-5344)
IEEE DOI 2008
Image reconstruction, Cameras, Geometry, Dynamics, Vehicle dynamics, Estimation BibRef

Zhang, K.X.[Kai-Xiang], Chen, J.[Jian], Yu, G.Q.[Guo-Qing], Zhang, X.F.[Xin-Fang], Li, Z.J.[Zhao-Jian],
Visual Trajectory Tracking of Wheeled Mobile Robots With Uncalibrated Camera Extrinsic Parameters,
SMCS(51), No. 11, November 2021, pp. 7191-7200.
IEEE DOI 2110
Cameras, Robot vision systems, Visualization, Trajectory tracking, Mobile robots, Trajectory, Extrinsic parameter identification, wheeled mobile robots (WMRs) BibRef

Wang, G.M.[Guang-Ming], Zhang, C.[Chi], Wang, H.S.[He-Sheng], Wang, J.C.[Jing-Chuan], Wang, Y.[Yong], Wang, X.L.[Xin-Lei],
Unsupervised Learning of Depth, Optical Flow and Pose With Occlusion From 3D Geometry,
ITS(23), No. 1, January 2022, pp. 308-320.
IEEE DOI 2201
Optical imaging, Training, Optical fiber networks, Optical losses, Estimation, Adaptive optics, Image reconstruction, unsupervised learning BibRef

Wang, G.M.[Guang-Ming], Ren, S.Q.[Shuai-Qi], Wang, H.S.[He-Sheng],
Unsupervised Learning of Optical Flow With Non-Occlusion From Geometry,
ITS(23), No. 11, November 2022, pp. 20850-20859.
IEEE DOI 2212
Optical imaging, Geometrical optics, Optical losses, Estimation, Unsupervised learning, Optical fiber networks, Automobiles, occlusion BibRef

Ando, S.[Shigeru], Kindo, T.[Toshiki],
Direct Imaging of Stabilized Optical Flow and Possible Anomalies From Moving Vehicle,
ITS(23), No. 12, December 2022, pp. 24044-24056.
IEEE DOI 2212
Optical sensors, Cameras, Visualization, Roads, Optical flow, Image sensors, Optical flow, ego-motion, gaze, autonomous vehicle, correlation image sensor BibRef

Rozsa, Z.[Zoltan], Golarits, M.[Marcell], Sziranyi, T.[Tamas],
Immediate Vehicle Movement Estimation and 3D Reconstruction for Mono Cameras by Utilizing Epipolar Geometry and Direction Prior,
ITS(23), No. 12, December 2022, pp. 23548-23558.
IEEE DOI 2212
Cameras, Image reconstruction, Estimation, Trajectory, MONOS devices, Vehicle dynamics, Vehicle trajectory, 3D reconstruction, intelligent transportation BibRef

Wang, G.M.[Guang-Ming], Zhong, J.[Jiquan], Zhao, S.J.[Shi-Jie], Wu, W.H.[Wen-Hua], Liu, Z.[Zhe], Wang, H.S.[He-Sheng],
3D Hierarchical Refinement and Augmentation for Unsupervised Learning of Depth and Pose From Monocular Video,
CirSysVideo(33), No. 4, April 2023, pp. 1776-1786.
IEEE DOI
WWW Link. 2304
Pose estimation, Training, Optical imaging, Optical variables control, Image reconstruction, 3D augmentation BibRef

Lee, W.Y.[Wan Yeon], Choi, Y.S.[Yun-Seok], Kim, T.M.[Tong Min],
Quantitative Estimation of Video Forgery with Anomaly Analysis of Optical Flow,
IEICE(E106-D), No. 10, October 2023, pp. 1757-1760.
WWW Link. 2310
BibRef

Zhou, B.B.[Bei-Bei], Xie, J.[Jin], Jin, Z.[Zhong], Kong, H.[Hui],
Geometry-Aware Network for Unsupervised Learning of Monocular Camera's Ego-Motion,
ITS(24), No. 12, December 2023, pp. 14226-14236.
IEEE DOI 2312
BibRef

Shiba, S.[Shintaro], Klose, Y.[Yannick], Aoki, Y.[Yoshimitsu], Gallego, G.[Guillermo],
Secrets of Event-Based Optical Flow, Depth and Ego-Motion Estimation by Contrast Maximization,
PAMI(46), No. 12, December 2024, pp. 7742-7759.
IEEE DOI 2411
Optical imaging, Optical sensors, Cameras, Estimation, Adaptive optics, Biomedical optical imaging, high dynamic range BibRef

Bar, A.[Amir], Bakhtiar, A.[Arya], Tran, D.[Danny], Loquercio, A.[Antonio], Rajasegaran, J.[Jathushan], Le Cun, Y.[Yann], Globerson, A.[Amir], Darrell, T.J.[Trevor J.],
EGOPET: Egomotion and Interaction Data from an Animal's Perspective,
ECCV24(XXXVII: 377-394).
Springer DOI 2412
BibRef

Yuan, S.[Shuai], Yu, S.Z.[Shu-Zhi], Kim, H.[Hannah], Tomasi, C.[Carlo],
SemARFlow: Injecting Semantics into Unsupervised Optical Flow Estimation for Autonomous Driving,
ICCV23(9532-9543)
IEEE DOI Code:
WWW Link. 2401
BibRef

Xu, C.X.[Chen-Xin], Tan, R.T.[Robby T.], Tan, Y.H.[Yu-Hong], Chen, S.[Siheng], Wang, Y.G.[Yu Guang], Wang, X.C.[Xin-Chao], Wang, Y.F.[Yan-Feng],
EqMotion: Equivariant Multi-Agent Motion Prediction with Invariant Interaction Reasoning,
CVPR23(1410-1420)
IEEE DOI 2309
BibRef

Boulahbal, H.E.[Houssem Eddine], Voicila, A.[Adrian], Comport, A.I.[Andrew I.],
Forecasting of depth and ego-motion with transformers and self-supervision,
ICPR22(3706-3713)
IEEE DOI 2212
Geometry, Convolution, Benchmark testing, Transformers, Feature extraction, Forecasting BibRef

Sekkati, H.[Hicham], Lapointe, J.F.[Jean-Francois],
Back to Old Constraints to Jointly Supervise Learning Depth, Camera Motion and Optical Flow in a Monocular Video,
ICIP22(336-340)
IEEE DOI 2211
Deep learning, Optical losses, Geometry, Structure from motion, Simultaneous localization and mapping, Estimation, Unsupervised Deep-Learning BibRef

Lee, S.[Seokju], Rameau, F.[Francois], Pan, F.[Fei], Kweon, I.S.[In So],
Attentive and Contrastive Learning for Joint Depth and Motion Field Estimation,
ICCV21(4842-4851)
IEEE DOI 2203
Dynamics, Semantics, Estimation, Cameras, Rigidity, Vehicle dynamics, Vision applications and systems, Vision for robotics and autonomous vehicles BibRef

Neumann, L.[Lukáš], Vedaldi, A.[Andrea],
Pedestrian and Ego-vehicle Trajectory Prediction from Monocular Camera,
CVPR21(10199-10207)
IEEE DOI 2111
Training, Drives, Cameras, Trajectory, Autonomous vehicles BibRef

Ding, Y.Q.[Ya-Qing], Barath, D.[Daniel], Kukelova, Z.[Zuzana],
Homography-based Egomotion Estimation Using Gravity and Sift Features,
ACCV20(I:278-294).
Springer DOI 2103
BibRef

Vasiljevic, I., Guizilini, V., Ambrus, R., Pillai, S., Burgard, W., Shakhnarovich, G., Gaidon, A.,
Neural Ray Surfaces for Self-Supervised Learning of Depth and Ego-motion,
3DV20(1-11)
IEEE DOI 2102
Cameras, Calibration, Training, Standards, Adaptation models, Solid modeling BibRef

Tishchenko, I., Lombardi, S., Oswald, M.R., Pollefeys, M.,
Self-Supervised Learning of Non-Rigid Residual Flow and Ego-Motion,
3DV20(150-159)
IEEE DOI 2102
Cameras, Estimation, Training, Lattices, Deep learning, Transforms, Deep Learning, Scene Flow, Self Supervised Learning BibRef

Shu, C.[Chang], Yu, K.[Kun], Duan, Z.X.[Zhi-Xiang], Yang, K.Y.[Kui-Yuan],
Feature-metric Loss for Self-supervised Learning of Depth and Egomotion,
ECCV20(XIX:572-588).
Springer DOI 2011
BibRef

Tzabari, M.[Masada], Schechner, Y.Y.[Yoav Y.],
Polarized Optical-flow Gyroscope,
ECCV20(XVI: 363-381).
Springer DOI 2010
BibRef

Yuan, Y.[Ye], Kitani, K.[Kris],
Ego-Pose Estimation and Forecasting As Real-Time PD Control,
ICCV19(10081-10091)
IEEE DOI 2004
Proportional-Derivative (PD). image motion analysis, learning (artificial intelligence), PD control, pose estimation, stereo image processing, Physics BibRef

Bozorgtabar, B.[Behzad], Rad, M.S.[Mohammad Saeed], Mahapatra, D.[Dwarikanath], Thiran, J.P.[Jean-Philippe],
SynDeMo: Synergistic Deep Feature Alignment for Joint Learning of Depth and Ego-Motion,
ICCV19(4209-4218)
IEEE DOI 2004
feature extraction, image representation, image sensors, image sequences, learning (artificial intelligence), BibRef

Zhong, Y.R.[Yi-Ran], Ji, P.[Pan], Wang, J.Y.[Jian-Yuan], Dai, Y.C.[Yu-Chao], Li, H.D.[Hong-Dong],
Unsupervised Deep Epipolar Flow for Stationary or Dynamic Scenes,
CVPR19(12087-12096).
IEEE DOI 2002
BibRef

Prasad, V., Bhowmick, B.,
SfMLearner++: Learning Monocular Depth Ego-Motion Using Meaningful Geometric Constraints,
WACV19(2087-2096)
IEEE DOI 1904
image reconstruction, image sequences, learning (artificial intelligence), motion estimation, Pose estimation BibRef

Mahjourian, R., Wicke, M., Angelova, A.,
Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints,
CVPR18(5667-5675)
IEEE DOI 1812
Cameras, Geometry, Image reconstruction, Training, Unsupervised learning, Google BibRef

Cai, H., Ye, S., Vardy, A., Gong, M.,
3D Visual Homing for Commodity UAVs,
CRV18(269-276)
IEEE DOI 1812
Visualization, Feature extraction, Cameras, Robots, Real-time systems, Mobile handsets, visual homing, robot navigation BibRef