The DOI matches its Crossref record.
Determining Three-Dimensional Motion and Structure from Optical Flow Generated by Several Moving Objects
Abstract
A new approach for the interpretation of optical flow fields is presented. The flow field, which can be produced by a sensor moving through an environment with several independently moving, rigid objects, is allowed to be sparse, noisy, and partially incorrect. The approach is based on two main stages. In the first stage, the flow field is partitioned into connected segments of flow vectors, where each segment is consistent with a rigid motion of a roughly planar surface. In the second stage, segments are grouped under the hypothesis that they are induced by a single, rigidly moving object. Each hypothesis is tested by searching for three-dimensional (3-D) motion parameters which are compatible with all the segments in the corresponding group. Once the motion parameters are recovered, the relative environmental depth can be estimated as well. Experiments based on real and simulated data are presented.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
No references could be resolved yet.
Research works printed but not linked: 33
- adiv, 1983, Recovering 2-D motion parameters in scenes containing multiple moving objects, Proc DARPA Image Understanding Workshop, 285
- 1984, Determining 3-D motion and structure from optical flow generated by several moving objects, Proc DARPA Image Understanding Workshop, 113
- williams, 1981, Computer interpretation of a dynamic image from a moving vehicle
- waxman, 1984, Contour Evolution Neighborhood Deformation and Global Image Flow Planar Surfaces in Motion
- waxman, 1984, An image flow paradigm, Proceedings of the Workshop on Visual Computing, 49
- waxman, 1983, Surface structure and 3-D motion from image flow A kinematic approach
- fang, 1983, Estimating 3-D movement of a rigid object: Experimental results, Proc Int Joint Conf Artif Intell, 1035
- 10.1016/0146-664X(79)90097-2 · DOI · Paper page
- 1978, Computer Vision Systems, 303
- 10.1109/TPAMI.1984.4767558 · DOI
- lawton, 1982, Motion analysis via local translational processing, Proceedings of the Workshop on Visual Computing, 59
- lawton, 1984, Processing Dynamic Image Sequences From a Moving Sensor
- 10.1098/rspb.1980.0057 · DOI · Paper page
- 10.1038/293133a0 · DOI · Paper page
- nagel, 1981, On the derivation of 3-D rigid point configurations from image sequences, Proc IEEE Conf Pattern Recog Image Proc, 103
- nagel, 1981, On 3-D reconstruction from two perspective views, Proc Int Joint Conf Artif Intell, 661
- ullman, 1979, The Interpretation of Visual Motion, 10.7551/mitpress/3877.001.0001 · DOI · Paper page
- 1985, Interpreting Optical Flow
- 10.1109/TPAMI.1984.4767471 · DOI · Paper page
- ballard, 1981, Parameter networks: Towards a theory of low-level vision, Proc Int Joint Conf Artif Intell, 1068
- 10.1109/C-M.1981.220564 · DOI
- anandan, 1984, Computing dense displacement fields with confidence measures in scenes containing occlusion, Proc DARPA Image Understanding Workshop, 236
- bruss, 1981, Passive Navigation
- ballard, 1981, Rigid Body Motion from Depth and Optical Flow
- 1983, Recovering motion parameters in scenes containing multiple moving objects, Proc IEEE Conf Comput Vis Pattern Recog, 399
- fang, 1983, Solving three-dimensional smallrotation motion equations, Proc IEEE Conf Comput Vis Pattern Recog, 253
- neumann, 1980, Motion analysis of image sequences for object grouping and reconstruction, Proc Int Conf Pattern Recog, 1262
- 10.1007/BF00361077 · DOI · Paper page
- o'rourke, 1981, Motion detection using Hough techniques, Proc IEEE Conf Pattern Recog Image Proc, 82
- rieger, 1983, Determining the instantaneous axis of translation from optic flow generated by arbitrary sensor motion, Proc Workshop Motion Representation Perception, 33
- 10.1016/0146-664X(81)90004-6 · DOI
- sloan, 1981, Dynamically quantized pyramids, Proc Int Joint Conf Artif Intell, 734
- 10.1109/TPAMI.1980.6447703 · DOI · Paper page
Cited by
A Database and Evaluation Methodology for Optical Flow
Baker, S., Scharstein, D., Lewis, J. P., Roth, S., Black, M. J., & Szeliski, R. (2011) · International Journal of Computer Vision · doi:10.1007/s11263-010-0390-2 · Cited by 2,205
“These constraints have both been strictly enforced [1, 29,52] and added as a soft prior [78,79].”
BackgroundMethodA computational framework and an algorithm for the measurement of visual motion
Anandan, P. (1989) · International Journal of Computer Vision · doi:10.1007/bf00158167 · Cited by 1,073
A Database and Evaluation Methodology for Optical Flow
Baker, S., Roth, S., Scharstein, D., Black, M. J., Lewis, J. P., & Szeliski, R. (2007) · 2007 IEEE 11th International Conference on Computer Vision · doi:10.1109/iccv.2007.4408903 · Cited by 618
Recognizing Facial Expressions in Image Sequences Using Local Parameterized Models of Image Motion
Black, M. J., & Yacoob, Y. (1997) · International Journal of Computer Vision · doi:10.1023/a:1007977618277 · Cited by 514
Error modeling in stereo navigation
Matthies, L., & Shafer, S. (1987) · IEEE Journal on Robotics and Automation · doi:10.1109/jra.1987.1087097 · Cited by 509
Hierarchical Model-Based Motion Estimation
Anandan, P., Bergen, J. R., Hanna, K. J., & Hingorani, R. (1993) · Motion Analysis and Image Sequence Processing · doi:10.1007/978-1-4615-3236-1_1 · Cited by 193
Stretchable multichannel antennas in soft wireless optoelectronic implants for optogenetics
Park, S. I., Shin, G., McCall, J. G., Al-Hasani, R., Norris, A., Xia, L., Brenner, D. S., Noh, K. N., Bang, S. Y., Bhatti, D. L., et al. (2016) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1611769113 · Cited by 135
Metadata
- Authors
- Adiv, G.
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 1985-07
- Volume
- PAMI-7
- Issue
- 4
- Pages
- 384-401
- ISSN
- 0162-8828 (ISSN-L)
- OpenAlex
- W2043003144
- Cited by
- 800
- References
- 0
- FWCI
- 19.02
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.
