Abstract
Optical flow estimation is classically marked by the requirement of dense sampling in time. While coarse-to-fine warping schemes have somehow relaxed this constraint, there is an inherent dependency between the scale of structures and the velocity that can be estimated. This particularly renders the estimation of detailed human motion problematic, as small body parts can move very fast. In this paper, we present a way to approach this problem by integrating rich descriptors into the variational optical flow setting. This way we can estimate a dense optical flow field with almost the same high accuracy as known from variational optical flow, while reaching out to new domains of motion analysis where the requirement of dense sampling in time is no longer satisfied.
Keywords
Optical flowImage warpingComputer scienceMotion estimationFlow (mathematics)Constraint (computer-aided design)Sampling (signal processing)Matching (statistics)AlgorithmDisplacement (psychology)Motion (physics)Scale (ratio)Computer visionDependency (UML)Vector fieldArtificial intelligenceMathematical optimizationMathematicsImage (mathematics)GeometryPhysics
Affiliated Institutions
Related Publications
ORB: An efficient alternative to SIFT or SURF
Feature matching is at the base of many computer vision problems, such as object recognition or structure from motion. Current methods rely on costly descriptors for detection a...
Snakes, shapes, and gradient vector flow
Snakes, or active contours, are used extensively in computer vision and image processing applications, particularly to locate object boundaries. Problems associated with initial...
Learning Hierarchical Features for Scene Labeling
Scene labeling consists of labeling each pixel in an image with the category of the object it belongs to. We propose a method that uses a multiscale convolutional network traine...
Deep Colorization
This paper investigates into the colorization problem which converts a grayscale image to a colorful version. This is a very difficult problem and normally requires manual adjus...
A Variational Method in Image Recovery
This paper is concerned with a classical denoising and deblurring problem in image recovery. Our approach is based on a variational method. By using the Legendre--Fenchel transf...
Publication Info
- Year
- 2010
- Type
- article
- Volume
- 33
- Issue
- 3
- Pages
- 500-513
- Citations
- 1286
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
1286
OpenAlex
Cite This
Thomas Brox,
Jitendra Malik
(2010).
Large Displacement Optical Flow: Descriptor Matching in Variational Motion Estimation.
IEEE Transactions on Pattern Analysis and Machine Intelligence
, 33
(3)
, 500-513.
https://doi.org/10.1109/tpami.2010.143
Identifiers
- DOI
- 10.1109/tpami.2010.143