Analysis of recent advances in optical flow estimation methods

Authors:
Javier S$#225/nchez
Affiliations:
Imaging Technology Center (www.ctim.es), University of Las Palmas de Gran Canaria, Las Palmas de Gran Canaria, Spain
Venue:
EUROCAST'11 Proceedings of the 13th international conference on Computer Aided Systems Theory - Volume Part I
Year:
2011

Citing 12
Cited 0

An Investigation of Smoothness Constraints for the Estimation of Displacement Vector Fields from Image Sequences

IEEE Transactions on Pattern Analysis and Machine Intelligence
Nonlinear total variation based noise removal algorithms

Proceedings of the eleventh annual international conference of the Center for Nonlinear Studies on Experimental mathematics : computational issues in nonlinear science: computational issues in nonlinear science
Variational Optic Flow Computation with a Spatio-Temporal Smoothness Constraint

Journal of Mathematical Imaging and Vision
Extending the 'Oriented Smoothness Constraint' into the Temporal Domain and the Estimation of Derivatives of Optical Flow

ECCV '90 Proceedings of the First European Conference on Computer Vision
Symmetrical Dense Optical Flow Estimation with Occlusions Detection

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
Object Recognition from Local Scale-Invariant Features

ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods

International Journal of Computer Vision
Highly Accurate Optic Flow Computation with Theoretically Justified Warping

International Journal of Computer Vision
Learning for Optical Flow Using Stochastic Optimization

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part II
Large Displacement Optical Flow: Descriptor Matching in Variational Motion Estimation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Optic Flow in Harmony

International Journal of Computer Vision
Dense estimation and object-based segmentation of the optical flow with robust techniques

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

One of the key problems in computer vision is the estimation of motion in image sequences. The apparent displacement of the pixels through the image sequence is generally called optical flow. This is a low-level task that is the base for many other high-level applications, such us stereoscopic vision and 3D scene reconstruction, object tracking, ambient intelligence, video surveillance, medical image analysis, meteorological prediction and analysis, and so on. After many years of intense research, we may consider that the optical flow research field is not mature yet. The quality and amount of recent publications, with many important contributions, reflect that this is a very active field. It is attracting many researchers in computer vision that make evolve the field in a steady way. In this paper we examine the last contributions and most important ideas about optical flow that have appeared during the last years.