Gradient Based Image Motion Estimation Without Computing Gradients
Explore this paper's citation graph
Summary
This work integrates the above constraint equation over a significant spatio-temporal support and uses Gauss's Divergence theorem to replace the volume integrals by surface integrals, thereby eliminating the intensity derivatives and numerical differentiation.
- Type
- article
- Published
- 1997-02-21
- Cited by
- 23
- References
- 25
- OpenAlex
- https://openalex.org/W10065857
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:19879400
Keywords
Optical flow, Mathematics, Affine transformation, Constraint (computer-aided design), Divergence theorem
References
- Computations Underlying the Measurement of Visual Motion
- Against Quantitative Optical Flow
- Generalized image matching by the method of differences
- Hierarchical Motion Detection
- A computer algorithm for reconstructing a scene from two projections
- Motion recovery from image sequences using First-order optical flow information
- Surface Structure and Three-Dimensional Motion from Image Flow Kinematics
- Representation of Moving Rigid Objects Based on Visual Observations
- Visual control of orientation behaviour in the fly: Part II. Towards the underlying neural interactions
- The interpretation of a moving retinal image
- Velocity determination in scenes containing several moving objects
- Optical flow using spatiotemporal filters
- An Investigation of Smoothness Constraints for the Estimation of Displacement Vector Fields from Image Sequences
- Computation of component image velocity from local phase information
- 3-D Motion Estimation from Motion Field
- Optical motions and space perception: an extension of Gibson's analysis.
- A computational framework and an algorithm for the measurement of visual motion
- Computing discontinuity-preserved image flow
- Recovering shape and motion from a sequence of images
- Determining Optical Flow
Cited by
- FPGA implementation of Santos-Victor optical flow algorithm for real-time image processing: an useful attempt
- Micro-vision-based displacement measurement with high accuracy
- A patch algorithm for fast registration of distortions
- Regularization of optical flow with M-band wavelet transform
- A multiscale optimal filter method for micro-motion measurement with high accuracy
- Real time lane detector hardware system
- Multiscale MSE-Minimizing Filters for Gradient-based Motion Estimation
- A novel approach to photometric motion
- In-plane micro-motion measurement with high accuracy based on computer microvision
- Real time hardware vision system applications: optical flow and time to contact detector units
- Affine registration: a comparison of several programs.
- Segmentation for robust tracking in the presence of severe occlusion
- Biological computation of image motion from flows over boundaries.
- Multi-image gradient-based algorithms for motion measurement using wavelet transform
- Robust visual motion analysis: piecewise-smooth optical flow and motion-based detection and tracking
- Human motion description in multimedia database
- Egomotion estimation with large field-of-view vision
- Robust multiscale algorithms for gradient‐based motion estimation
- Computing Slow Optical Flow By Interpolated Quadratic Surface Matching
- Efficient and robust algorithms for sparse 3-D reconstruction from image sequences
Related papers
- A Probe into the Applying of Gauss THeorem
- Effective motion field description based on affine models and global motion information
- A New Method of 3D Motion and Structure Estimation Based on Spare Optical Flow
- A generalization of Gauss' divergence theorem
- A New Block Based Motion Estimation with True Region Motion Field
- Block/object-based algorithm for estimating true motion fields
- Parameter estimation of non-translational motion fields
- Time-sequential structure and motion estimation without optical flow