Difference between revisions of "Vision"

From SpaceElevatorWiki.com
m (Hardware)
(Goals)
 
(20 intermediate revisions by the same user not shown)
Line 1: Line 1:
 +
[[Image:Torcs.jpg|500 px|thumb|Analyze this!]]
 +
 +
== Meta ==
 +
To create a page on the wiki, just go to the URL and mediawiki will create one on demand.
 +
 +
I go through and polish wordings just to try to make it easier for people to read. After (nearly) writing a book, I understand how important readability is. I might make mistakes, so please fix it and don't be offended that I am making changes...
 +
 
== Why work on Vision? ==
 
== Why work on Vision? ==
 
Here is [[Why]].
 
Here is [[Why]].
Line 4: Line 11:
 
== Goals ==
 
== Goals ==
 
[[Goals]]
 
[[Goals]]
 
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 [http://code.google.com/p/tesseract-ocr/] 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 ==
 
== Programmer stuff ==
 
+
* [http://www.monobotics.ic.uach.cl/ GUI tool for doing vision analysis]
 
* [[Software Architecture]]
 
* [[Software Architecture]]
* Setting up [[Build]] environment
+
* [[Build]] environment
* [[Readability]]
+
* [[Codebase Analysis]]
 
 
== 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]]
 
  
 
== Hardware ==
 
== Hardware ==
 
We will buy it as much as possible. If we have anything more than a computer and soldering iron, we have gone too far!
 
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.
+
What hardware should we buy to do some demo of an object that can program to move precisely and have it give us input about what it is seeing.
  
 
http://www.mobilerobots.com/applications.html
 
http://www.mobilerobots.com/applications.html

Latest revision as of 00:49, 26 November 2008

Analyze this!

Meta

To create a page on the wiki, just go to the URL and mediawiki will create one on demand.

I go through and polish wordings just to try to make it easier for people to read. After (nearly) writing a book, I understand how important readability is. I might make mistakes, so please fix it and don't be offended that I am making changes...

Why work on Vision?

Here is Why.

Goals

Goals

Programmer stuff

Hardware

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 program to move precisely and have it give us input about what it is seeing.

http://www.mobilerobots.com/applications.html

http://www.festo-didactic.com/int-en/learning-systems/new-robotino/

http://www.dyson.com/about/story/anotherproblem.asp

People

People