Rank: 279 based on 411 downloads (last 30 days) and 6 files submitted
photo

Stefan Karlsson

E-mail
Company/University
Halmstad University

Personal Profile:

Post doc in Image analysis/computer vision/biometrics


 

Watch this Author's files

 

Files Posted by Stefan Karlsson View all
Updated   File Tags Downloads
(last 30 days)
Comments Rating
25 Nov 2014 Screenshot Tutorial and Toolbox on real-time optical flow Code with visualization and excercises. Camera supported Author: Stefan Karlsson computer vision, optical flow, image processing, video processing 197 13
  • 5.0
5.0 | 6 ratings
05 Oct 2014 Screenshot Visual Studio Toolbar for mex interface with video tutorial Seamless interface, VS 2010 and 2012 and Matlab for MEX. Video linked to step you through. Author: Stefan Karlsson mex development, external dependencies..., external dependencies, video tutorial 25 3
  • 5.0
5.0 | 1 rating
10 Mar 2014 Optical Flow with Matlabs Computer vision toolbox optical flow on camera, synthetic video and video files Author: Stefan Karlsson computer vision, optical flowmotion es... 48 1
  • 4.6
4.6 | 5 ratings
02 Dec 2013 VideoResize A MUCH faster version of "imresize", specifically for videoprocessing Author: Stefan Karlsson video processing, computer vision, real time processing 13 0
28 Mar 2013 Screenshot Real time optical flow, and video processing Real time optical flow, and video processing, with support for camera input in Matlab. Author: Stefan Karlsson motion estimation, optical flow, tracking, video processing, mex, real time 113 10
  • 4.5
4.5 | 2 ratings
Comments and Ratings by Stefan Karlsson View all
Updated File Comments Rating
17 Nov 2014 Tutorial and Toolbox on real-time optical flow Code with visualization and excercises. Camera supported Author: Stefan Karlsson

@Achmad,

Thanks for your interest. To name two people who made contributions and that I know share code:
Michael J. Black,
Bill Triggs

Many of their suggested frameworks would work with the simple algorithms in this submission. There are two major classical issues in using this tutorial code straight away with real-world problems: higher motions and multiple motions. For problems such as pedestrian detection, the higher motion problem can be fixed with some simple pyramid tricks. The multiple motions problem would be a bit more tricky. Phrased differently, you do not want the output flow to be dependent on what the background of the scene happens to be. I dont know of any local, fast algorithms that deal with this, if someone does... do post me a line.

05 Oct 2014 Real time optical flow, and video processing Real time optical flow, and video processing, with support for camera input in Matlab. Author: Stefan Karlsson

@sachin,

1) folder c-code has a file make.m
2) for most purposes, you would probably be better off looking at my other optical flow submission, its a more stable implementation

29 Jun 2014 Horn-Schunck optical flow method for 3-D images An implementation of Horn-Schunck optical flow method for 3-D images Author: Mohammad Mustafa

Easy to understand, straightforward implementation of the original 1980 paper.

It has all the classic drawbacks, like sensitivity to noise and deviations from non-translational motions.

13 Jun 2014 Anisotropic Diffusion (Perona & Malik) A set of filters that perform 1D, 2D and 3D conventional anisotropic diffusion (gray scale data). Author: Daniel Lopes

There is no productive 2D example provided that show the superiority of this method over regular gaussian smoothing. A simple combination of Gaussian and Median filtering provides better denoising than what is proposed:

s = phantom(512) + randn(512);
num_iter = 55;
delta_t = 1/7;
kappa = 30;
option = 2;
ad = anisodiff2D(s,num_iter,delta_t,kappa,option);

It is very likely that the authors generalization of using 8 point neighbourhoods is valid, but if so it changes the valid range of the parameters, and thus one cant easily recreate the results of the original Perona-Malik paper. If a simple example was provided that showed how the 2D method actually outperforms gaussian blurring, then I might be inclined to read the secondary paper referenced.

the interpretation of the kappa parameter is nicely given in weickerts book: http://www.lpi.tel.uva.es/muitic/pim/docus/anisotropic_diffusion.pdf, chapter 1, figure 1.1, b... (its called lambda there)

I cant get that interpretation to work for me here. Whats wrong? How can i strengthen the edges in the image using this, while blurring along isolines!?

Again, if only a positive example was provided for the 2D case, this might all be cleared up.

11 Jun 2014 Tutorial and Toolbox on real-time optical flow Code with visualization and excercises. Camera supported Author: Stefan Karlsson

@Adam

be sure to use a simple option to toggle the video recording on/off. Especially the way you implemented it is likely to suck up alot of processing time from Matlab. Real-time should still not be an issue, as long as you keep your video small and your machine powerful. Would be a shame if you want to show a fast script for someone, and it lags up your computer.

Comments and Ratings on Stefan Karlsson's Files View all
Updated File Comment by Comments Rating
17 Nov 2014 Tutorial and Toolbox on real-time optical flow Code with visualization and excercises. Camera supported Author: Stefan Karlsson Stefan Karlsson

@Achmad,

Thanks for your interest. To name two people who made contributions and that I know share code:
Michael J. Black,
Bill Triggs

Many of their suggested frameworks would work with the simple algorithms in this submission. There are two major classical issues in using this tutorial code straight away with real-world problems: higher motions and multiple motions. For problems such as pedestrian detection, the higher motion problem can be fixed with some simple pyramid tricks. The multiple motions problem would be a bit more tricky. Phrased differently, you do not want the output flow to be dependent on what the background of the scene happens to be. I dont know of any local, fast algorithms that deal with this, if someone does... do post me a line.

13 Nov 2014 Optical Flow with Matlabs Computer vision toolbox optical flow on camera, synthetic video and video files Author: Stefan Karlsson Achmad Solichin

13 Nov 2014 Tutorial and Toolbox on real-time optical flow Code with visualization and excercises. Camera supported Author: Stefan Karlsson Achmad Solichin

Thanks for sharing Mr Stefan. I would like to ask, if the optical flow can be used to detect the movement patterns of objects? For example in the detection of pedestrian behavior. Is any example code?

Thanks for replying

05 Oct 2014 Real time optical flow, and video processing Real time optical flow, and video processing, with support for camera input in Matlab. Author: Stefan Karlsson Stefan Karlsson

@sachin,

1) folder c-code has a file make.m
2) for most purposes, you would probably be better off looking at my other optical flow submission, its a more stable implementation

30 Jul 2014 Real time optical flow, and video processing Real time optical flow, and video processing, with support for camera input in Matlab. Author: Stefan Karlsson sachin

I am using Matlab R2013a , when i have runMe.m file , i have got error like please let me know how i can solve ???
Undefined function or variable 'Grad3D7do'.

Error in vidProcessing (line 87)
Grad3D7do();

Error in runMe (line 56)
vidProcessing(movieType, method,
spdFactor,bFineScale,nofTimeSlices);

Contact us