Revisiting the Brightness Constraint: Probabilistic Formulation and Algorithms

Govindu, Venu Madhav

doi:10.1007/11744078_14

Cited by 8 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One way to mitigate this problem is to add a prior (soft constraint) on the expected range of motions (Simoncelli et al 1991, Govindu 2006. This can be accomplished by adding a small value to the diagonal of A, which essentially biases the solution towards smaller ∆u values that still (mostly) minimize the squared error.…”

mentioning

confidence: 99%

Image Alignment and Stitching: A Tutorial

Szeliski

2007

FNT in Computer Graphics and Vision

1,194

660

View full text Add to dashboard Cite

This tutorial reviews image alignment and image stitching algorithms. Image alignment algorithms can discover the correspondence relationships among images with varying degrees of overlap. They are ideally suited for applications such as video stabilization, summarization, and the creation of panoramic mosaics. Image stitching algorithms take the alignment estimates produced by such registration algorithms and blend the images in a seamless manner, taking care to deal with potential problems such as blurring or ghosting caused by parallax and scene movement as well as varying image exposures. This tutorial reviews the basic motion models underlying alignment and stitching algorithms, describes effective direct (pixel-based) and feature-based alignment algorithms, and describes blending algorithms used to produce seamless mosaics. It closes with a discussion of open research problems in the area.

show abstract

mentioning

confidence: 99%

Image Alignment and Stitching: A Tutorial

Szeliski

2007

FNT in Computer Graphics and Vision

1,194

660

View full text Add to dashboard Cite

show abstract

“…However, many of these works are based on simplifying assumptions such as locally constant flow or a Gaussian distribution of brightness constancy errors. In [19,26,44], probabilistic approaches are applied to obtain improved models of optical flow. In contrast to our work, these methods do not apply a fully probabilistic approach, but fall back to a maximum aposteriori (MAP) estimate, i.e.…”

Section: Related Workmentioning

confidence: 99%

ProbFlow: Joint Optical Flow and Uncertainty Estimation

Wannenwetsch

Keuper

Roth

2017

2017 IEEE International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

Optical flow estimation remains challenging due to untextured areas, motion boundaries, occlusions, and more. Thus, the estimated flow is not equally reliable across the image. To that end, post-hoc confidence measures have been introduced to assess the per-pixel reliability of the flow. We overcome the artificial separation of optical flow and confidence estimation by introducing a method that jointly predicts optical flow and its underlying uncertainty. Starting from common energy-based formulations, we rely on the corresponding posterior distribution of the flow given the images. We derive a variational inference scheme based on mean field, which incorporates best practices from energy minimization. An uncertainty measure is obtained along the flow at every pixel as the (marginal) entropy of the variational distribution. We demonstrate the flexibility of our probabilistic approach by applying it to two different energies and on two benchmarks. We not only obtain flow results that are competitive with the underlying energy minimization approach, but also a reliable uncertainty measure that significantly outperforms existing post-hoc approaches.

show abstract

“…Optical flow methods are classified into local methods, such as the Lucas/Kanade technique (Lucas and Kanade, 1981), and into global techniques as the Horn/Schunck approach (Horn and Schunck, 1981). For general information on optical flow algorithms, the reader is referred to the following references, which include performance evaluations of different optical flow techniques (Barron et al, 1994;Govindu, 2006), first applications of optical flow techniques to fluid flows (Corpetti et al, 2006;Liu and Shen, 2008) and a comparison between optical flow and cross-correlation methods (Liu et al, 2015).…”

Section: Introductionmentioning

confidence: 99%

Optical flow estimations in aerated spillway flows: Filtering and discussion on sampling parameters

Kramer

Chanson

2019

Experimental Thermal and Fluid Science

View full text Add to dashboard Cite

Image-based velocimetry has captured great interest in physical modelling of highly-aerated flows, for example in stepped spillways. The present study investigated the performance of a novel filtering technique based upon a detailed systematic comparison with intrusive phase-detection probe data, recorded in a large-size stepped spillway. A sensitivity analysis provided recommendations in terms of optimum sampling and processing parameters for optical flow measurements in high-velocity air-water flows.

show abstract

Revisiting the Brightness Constraint: Probabilistic Formulation and Algorithms

Cited by 8 publications

References 22 publications

Image Alignment and Stitching: A Tutorial

Image Alignment and Stitching: A Tutorial

ProbFlow: Joint Optical Flow and Uncertainty Estimation

Optical flow estimations in aerated spillway flows: Filtering and discussion on sampling parameters

Contact Info

Product

Resources

About