Revision as of 17:36, 21 June 2008 by Keithcu (talk | contribs) (Hardware)

Why work on Vision?

Here is Why.



Have a Milestone 1 demo on or before September 8th, 2008.

Hard Questions

Put your hard questions here. (Answers are preferred...) If you have more precise phrasing, please fix :-)

  • Vision
OCR Is Google's Tesseract [1] supersetted by Intel's OpenCV Library? (Aleks)
What is the roadmap for how we will use more and more of the Intel logic? (Aleks)
For M1 demo, how do we focus it on only finding cars in front of it? Just getting the pipeline running will be work. We will need to configure the right brightness constants so it knows what it is looking at, for example...
What about doing training and object detection? Their website says we can hand it lots of pictures of cars, and non-cars and it will start to figure things out. How is that data stored? Can we tweak it?
If we know the size of the car, you could use that to estimate distance without having 3-D images to deal with. (We should sketch out 3-D on the roadmap...)
I think we should do blob first, and then attack objects. It might be that blobs are useless, and object recognition is much better. Fine, then blobs will only be used for a few days ;-) We should be working our way up.
  • Control theory / Machine learning
It seems like we encode rules like: standard practice is to trail a car by 2 seconds
And then we mention things like avoid other cars, don't make 3-G turns. The question is, how are those rules encoded?
What about the situation where we want to make notice of things for later, like the location of potholes. Assuming the vision has decided that is a pothole, how do we add that to map, remove it when we go by because it has been fixed? In a racing game, we should make note about a jump so that we don't go off a cliff. Supposed we would just drive the car through the map to have it gather data. What is the maximum speed it could go through the map the first time?

Programmer stuff

Free Software codebase investigations

The questions are: which codebases do we use? How clean is the code and how active is the community?

In general we should be looking for the biggest community. The one with 2x as many developers will win, unless both have achieved critical mass.

Any codebases we use we will want to be able to program in a Mono language. (Reasons for this do not fit into the margin) Finding managed bindings is a part of the development, and they are all out there, except for the driving logic, which is in progress.

Codebase Analysis


We will buy it as much as possible. If we have anything more than a computer and soldering iron, we have gone too far!

What hardware should we buy to do some demo of an object that can drive around, stay away from things, map out the location, recognize objects, be given a set of waypoints, etc.