Detecting Motion and Optic Flow Cmput 610 Martin

Detecting Motion and Optic Flow Cmput 610 Martin Jagersand

Today: l l l Image motion and optic flow More on projects Decide on project schedules

Image motion l l Somehow quantify differences in image sequences. Image differences. Optic flow 3 -6 dim motion

Motion is used to: l l l Attention: Detect and direct using eye and head motions Control: Locomotion, manipulation, tools Vision: Segment, depth, trajectory

Small camera re-orientation Note: Almost all pixels change!

Classes of motion l l Still camera, single moving object Still camera, several moving objects Moving camera, still background Moving camera, moving objects

The motion field l l Vector field over the image: [u, v] = f(x, y), u, v = Vel vector, x, y = Im pos FOE, FOC Focus of Expansion, Contraction

Optic/image flow l Assumption: Image intensities from object points remain constant over time.

Taylor expansion of intensity variation l Keep linear terms Use constancy assumption and rewrite: l Notice: Linear constraint, but no unique solution

Aperture problem l Rewrite as dot product l Notice: Can only detect vectors normal to gradient direction

Aperture problem 2

Using several points l Over determined equation system l Im = Mu Can be solved in e. g. least squares sense using matlab u = MIm

3 -6 D Optic flow l Generalize to many freedooms (DOFs)

All 6 freedoms X Y Rotation Scale Aspect Shear

Flow vectors l Norbert’s trick: Use an mpeg-card to speed up motion computation

Application: mpeg compression

Other applications: l l Recursive depth recovery: Kostas and Jane Motion control (we will cover) Segmentation Tracking

Part 2: Project discussion l l How to start and carry out a literature search and reading project What is a reasonable schedule?

Literature search l l Goal: Find the 10 -15 most relevant and recent papers in a subarea. Method: 1. 2. 3. 4. Seed with a few relevant papers. Do citation search backwards and forwards. Find common “buzz words”. Do title and abstract text search. Do internet search. e. g. “Cora” from justresearch

Literature search 2 l Expect to: – – – l Read the titles of hundreds of papers Read the abstract of 30 -50 of papers Skim through dozens of papers In order to find the 10 -15 or so most relevant.

Report: l l Write a review article summarizing the main contributions and comparing the results in the papers. Challenge: Master the concepts of the papers from only reading. – – Some papers are difficult to fully grasp without trying the concepts Some are wrong or incomplete

Alternative: Practical project l l l Read a few papers (Provided by Martin) Do a computer implementation and perform experiments based on the papers Write a report on the papers, your work and the experimental results

Projects: rest of semester: l l l Decide on project, consult with Martin Write project proposal and time plan Course presentations: – – l Reading project: Select one or two papers and present to class Practical project: Present your work. Final report