Stereo Disparity

3D reconstruction can be done based on depth information obtained from a pair of cameras. Stereo disparity map basically tells us the distance between each point in image and the camera.


Optical Flow

Optical Flow gives us information related to how the pixels move between images taken at two different points in time. Color coding can be used to display the movement direction.



Pixels of the image can be segmented into meaningful groups. Segmented images can be used for object detection, grasping etc.


Tutorials and Code

Getting started initially can be difficult. Check out my tutorials and code examples in order to get a jump start!


This is the personal website of Dr. Jarno Ralli, related to artificial vision (also known as machine- or computer vision) and other computer sciences related areas. I made this website with the idea of communicating my, and my colleagues, work to the public! The idea is to bring 'science' closer to the end-users. With end-user I mean people, not necessarily scientists, working in fields related to the research topics presented here...they can be engineers, students, teachers and so on. I hope that the material presented here, along with the related code, tutorials and so on, will be useful!!

Who is Jarno Ralli?

If you want to know more about me, check out HOME - JARNO RALLI from the navigation bar. I try to keep my LinkedIn profile updated. Take a look at some of my COLLABORATORS (not directly affiliated with me).


Jarno in Helsinki, 2012

Image taken by Esko Tuomisto (esko AT neodes DOT fi), in Helsinki 2012, for the Skoda Magazine interview.


Two things are infinite: the universe and human stupidity; and I'm not sure about the the universe.

- Albert Einstein -


Optical Flow and Stereo Disparity

Some of the main ideas presented in this site are related to optical flow and stereo disparity calculation, and segmentation of images. One interesting branch of methods for approximating both optical flow and stereo disparity maps are based on the field of mathematics known as calculus of variations. Interestingly, some segmentation problems can also be addressed using calculus of variations. Code examples are available for the following:

  1. optical flow code
  2. stereo disparity code
  3. nonlinear diffusion code
  4. active contours code

Interesting tutorials/papers are available at:

  1. Tutorial about non-linear diffusion and AOS (Additive Operator Splitting), HTML, PDF
  2. Paper about spatio-temporal constraining in disparity and optical flow calculation, HTML, PDF
  3. Disparity densification using voting mask scheme, HTML, PDF



Let's get social!

FacebookTwitterGoogle BookmarksLinkedIn