Scene Segmentation from Visual Motion Using Global Optimization
IEEE Transactions on Pattern Analysis and Machine Intelligence
Robust regression and outlier detection
Robust regression and outlier detection
Image Flow Segmentation and Estimation by Constraint Line Clustering
IEEE Transactions on Pattern Analysis and Machine Intelligence
Computation of component image velocity from local phase information
International Journal of Computer Vision
Multidimensional Orientation Estimation with Applications to Texture Analysis and Optical Flow
IEEE Transactions on Pattern Analysis and Machine Intelligence
Bayesian Estimation of Motion Vector Fields
IEEE Transactions on Pattern Analysis and Machine Intelligence
Motion recovery from image sequences using only first order optical flow information
International Journal of Computer Vision
Motion analysis from first-order properties of optical flow
CVGIP: Image Understanding - Special issue on purposive, qualitative, active vision
Performance of optical flow techniques
International Journal of Computer Vision
Region-based tracking using affine motion models in long image sequences
CVGIP: Image Understanding
Optical flow estimation: advances and comparisons
ECCV '94 Proceedings of the third European conference on Computer vision (vol. 1)
Robust computation of optical flow in a multi-scale differential framework
International Journal of Computer Vision
The robust estimation of multiple motions: parametric and piecewise-smooth flow fields
Computer Vision and Image Understanding
International Journal of Computer Vision
Robust computation of optical flow
BMVC '95 Proceedings of the 6th British conference on Machine vision (Vol. 2)
Robot Vision
Multimodal Estimation of Discontinuous Optical Flow using Markov Random Fields
IEEE Transactions on Pattern Analysis and Machine Intelligence
Cooperative Robust Estimation Using Layers of Support
IEEE Transactions on Pattern Analysis and Machine Intelligence
Optic Flow Field Segmentation and Motion Estimation Using a Robust Genetic Partitioning Algorithm
IEEE Transactions on Pattern Analysis and Machine Intelligence
Robust multiresolution computation of optical flow
ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 04
The application of mean field theory to image motion estimation
IEEE Transactions on Image Processing
Design and Use of Linear Models for Image Motion Analysis
International Journal of Computer Vision
Image Registration Using Wavelet-Based Motion Model
International Journal of Computer Vision
Estimation of Motion through Inverse Finite Element Methods with Triangular Meshes
CAIP '01 Proceedings of the 9th International Conference on Computer Analysis of Images and Patterns
Estimating Piecewise-Smooth Optical Flow with Global Matching and Graduated Optimization
IEEE Transactions on Pattern Analysis and Machine Intelligence
Adaptive Grid Refinement Procedures for Efficient Optical Flow Computation
International Journal of Computer Vision
Robust Adaptive-Scale Parametric Model Estimation for Computer Vision
IEEE Transactions on Pattern Analysis and Machine Intelligence
Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods
International Journal of Computer Vision
Accurate optical flow computation under non-uniform brightness variations
Computer Vision and Image Understanding
Hardware implementation of optical flow constraint equation using FPGAs
Computer Vision and Image Understanding
IEEE Transactions on Pattern Analysis and Machine Intelligence
Optical-flow based on an edge-avoidance procedure
Computer Vision and Image Understanding
Accurate optical flow computation under non-uniform brightness variations
Computer Vision and Image Understanding
Hardware implementation of optical flow constraint equation using FPGAs
Computer Vision and Image Understanding
Motion vision based structure estimation in forest environment
IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Variational method for super-resolution optical flow
Signal Processing
The effect of presmoothing image sequences on the computation of optical flow
ICIAR'06 Proceedings of the Third international conference on Image Analysis and Recognition - Volume Part I
Hi-index | 0.00 |
An optical flow estimation technique is presented which isbased on the least-median-of-squares (LMedS) robust regressionalgorithm enabling more accurate flow estimates to be computed in thevicinity of motion discontinuities. The flow is computed in ablockwise fashion using an affine model. Through the use ofoverlapping blocks coupled with a block shifting strategy, redundancyis introduced into the computation of the flow. This eliminatesblocking effects common in most other techniques based on blockwiseprocessing and also allows flow to be accurately computed in regionscontaining three distinct motions.A multiresolution version of the technique is also presented, againbased on LMedS regression, which enables image sequences containinglarge motions to be effectively handled.An extensive set of quantitative comparisons with a wide range ofpreviously published methods are carried out using synthetic,realistic (computer generated images of natural scenes with knownflow) and natural images. Both angular and absolute flow errors arecalculated for those sequences with known optical flow. Displacedframe difference error, used extensively in video compression, isused for those natural scenes with unknown flow. In all of thesequences tested, a comparison with those methods that result in adense flow field (greater than 80% spatial coverage), show that theLMedS technique produces the least error irrespective of the errormeasure used.