Questions tagged [optical-flow]

The tag has no usage guidance.

14 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
3
votes
0answers
104 views

Nagel, 1987, On the estimation of optical flow - attributes of this method

I know Horn and Schunck and Lucas-Kanade (81) as optic flow methods. But Nagel is way to complex for me. Anyway I have an blackbox implementation of this method but would like to understand the ...
2
votes
0answers
55 views

How to calculate Walsh hadamard transform for image patches of odd sizes?

I was reading this paper on optical flow, which as apart of the algorithm makes use Walsh-Hadamard transform on image patches of size 2r+1. So far, where ever I have looked, I could only find that ...
2
votes
0answers
180 views

Is it possible to calculate the optical flow magnitude for rigid motion?

For objects in 2D plane, it is pretty simple to calculate the displacement vectors using optical flow algorithms such as SLIC, LK, Färneback etc. But how it is possible to know the magnitude of the ...
2
votes
0answers
51 views

Determining Optic Flow - Horn and Schunck - robust/insensitive to …

Can somebody explain to me why the Horn and Schunck algorithm (probably mostly the smoothness constraint) is robust to image sequences that are quantized rather coarsely in space and/or time. (Thought ...
2
votes
0answers
640 views

Understanding Farneback Displacement Estimation

I am having some trouble in my attempt to understand some of the operations in the Farneback optical flow algorithm, and i would really appriciate if somebody could help me a bit along the way (and i ...
1
vote
0answers
68 views

Position vector of Lukas-Kanade optical flow algorithm

The classical optical flow equation by Lukas-Kanade can be simplified as follow: $$ \frac{\delta I}{\delta x}\triangle x+\frac{\delta I}{\delta y}\triangle y + \frac{\delta I}{\delta t}\triangle t=0 $$...
1
vote
1answer
148 views

Motion detection one threshold over dataset

We're working on a project where we have to detect the moments where motions happen in a medical scene. I have a data set of 20 videos that are closely resemble (Same camera & configuration used, ...
1
vote
0answers
186 views

Image warping with subpixel accuracy

I am trying to test the sub-pixel accuracy of an optical flow method and need to generate some synthetic data to do so. I start with an image $I_0$, which is a Perlin noise image and a set of sub-...
0
votes
0answers
10 views

Gaussian Pyramid - Expand Operator

I'm trying to understand the EXPAND operator in Burt and Adelson's paper (https://s3.amazonaws.com/content.udacity-data.com/courses/ud810/readings/Burt-Adelson1983Laplacian-Pyramid.pdf) and I'm a bit ...
0
votes
0answers
17 views

Questions about Optical Flow implementations

I have some doubts related to some of the optical flow implementations. How to compute angular error for optical flow algorithms? I know the formula for computing, $\theta=\arccos(\vec{v}_c\cdot\vec{...
0
votes
0answers
13 views

Sparse to Dense Flow

I'm trying to upgrade a flow from sparse to dense and have been recommended this for my use-case https://uk.mathworks.com/matlabcentral/fileexchange/25634-smoothn . When I run the interpolation, ...
0
votes
0answers
15 views

Optical flow Horn & Schunck smoothness error

I was reading about the Horn & Schunck method and they define the smoothness error as (Robot Control 1988 (SYROCO'88): Selected Papers from the 2nd IFAC Symposium p. 348): $E_{sm} = \iint{\left(...
0
votes
0answers
29 views

Linear equation set construction for Brox et al. optical flow optimization

I'm trying to implement an optical flow calculation program for two successive images based on this article by Brox et al. The Euler-Lagrange combined with a fixed point iteration loop yields two ...
0
votes
0answers
29 views

Simple question about HS algorithm's formul(Optical flow)

In the below pic, I can not understand what U vector is? It says flow field but I can not imagie what really is the flow field?